mirror of
https://github.com/APIParkLab/APIPark.git
synced 2026-06-14 20:41:15 +08:00
Merge branch 'feature/1.5-local-model' into 'main'
Feature/1.5 local model See merge request apipark/APIPark!199
This commit is contained in:
刘健
@@ -1,7 +1,9 @@
|
||||
package ai
|
||||
package ai_provider_local
|
||||
|
||||
var (
|
||||
ollamaSvg = `<?xml version="1.0" standalone="no"?>
|
||||
OllamaBase = "http://apipark-ollama:11434"
|
||||
OllamaConfig = "{\n \"mirostat\": 0,\n \"mirostat_eta\": 0.1,\n \"mirostat_tau\": 5.0,\n \"num_ctx\": 4096,\n \"repeat_last_n\":64,\n \"repeat_penalty\": 1.1,\n \"temperature\": 0.7,\n \"seed\": 42,\n \"num_predict\": 42,\n \"top_k\": 40,\n \"top_p\": 0.9,\n \"min_p\": 0.5\n}\n"
|
||||
OllamaSvg = `<?xml version="1.0" standalone="no"?>
|
||||
<!DOCTYPE svg PUBLIC "-//W3C//DTD SVG 20010904//EN"
|
||||
"http://www.w3.org/TR/2001/REC-SVG-20010904/DTD/svg10.dtd">
|
||||
<svg version="1.0" xmlns="http://www.w3.org/2000/svg"
|
||||
+38
@@ -0,0 +1,38 @@
|
||||
model: claude-3-5-haiku-20241022
|
||||
label:
|
||||
en_US: claude-3-5-haiku-20241022
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: '1.00'
|
||||
output: '5.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
+40
@@ -0,0 +1,40 @@
|
||||
model: claude-3-5-sonnet-20241022
|
||||
label:
|
||||
en_US: claude-3-5-sonnet-20241022
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- document
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: '3.00'
|
||||
output: '15.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,26 @@
|
||||
model: ai21.jamba-1-5-large-v1:0
|
||||
label:
|
||||
en_US: Jamba 1.5 Large
|
||||
model_type: llm
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 256000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 2.0
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_gen_len
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 4096
|
||||
min: 1
|
||||
max: 4096
|
||||
pricing:
|
||||
input: '0.002'
|
||||
output: '0.008'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,26 @@
|
||||
model: ai21.jamba-1-5-mini-v1:0
|
||||
label:
|
||||
en_US: Jamba 1.5 Mini
|
||||
model_type: llm
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 256000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 2.0
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_gen_len
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 4096
|
||||
min: 1
|
||||
max: 4096
|
||||
pricing:
|
||||
input: '0.0002'
|
||||
output: '0.0004'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,53 @@
|
||||
model: amazon.nova-lite-v1:0
|
||||
label:
|
||||
en_US: Nova Lite V1
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 300000
|
||||
parameter_rules:
|
||||
- name: max_new_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 2048
|
||||
min: 1
|
||||
max: 5000
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
required: false
|
||||
type: float
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
help:
|
||||
zh_Hans: 生成内容的随机性。
|
||||
en_US: The amount of randomness injected into the response.
|
||||
- name: top_p
|
||||
required: false
|
||||
type: float
|
||||
default: 0.999
|
||||
min: 0.000
|
||||
max: 1.000
|
||||
help:
|
||||
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
|
||||
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
|
||||
- name: top_k
|
||||
required: false
|
||||
type: int
|
||||
default: 0
|
||||
min: 0
|
||||
# tip docs from aws has error, max value is 500
|
||||
max: 500
|
||||
help:
|
||||
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
|
||||
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
|
||||
pricing:
|
||||
input: '0.00006'
|
||||
output: '0.00024'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,52 @@
|
||||
model: amazon.nova-micro-v1:0
|
||||
label:
|
||||
en_US: Nova Micro V1
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: max_new_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 2048
|
||||
min: 1
|
||||
max: 5000
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
required: false
|
||||
type: float
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
help:
|
||||
zh_Hans: 生成内容的随机性。
|
||||
en_US: The amount of randomness injected into the response.
|
||||
- name: top_p
|
||||
required: false
|
||||
type: float
|
||||
default: 0.999
|
||||
min: 0.000
|
||||
max: 1.000
|
||||
help:
|
||||
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
|
||||
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
|
||||
- name: top_k
|
||||
required: false
|
||||
type: int
|
||||
default: 0
|
||||
min: 0
|
||||
# tip docs from aws has error, max value is 500
|
||||
max: 500
|
||||
help:
|
||||
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
|
||||
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
|
||||
pricing:
|
||||
input: '0.000035'
|
||||
output: '0.00014'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,53 @@
|
||||
model: amazon.nova-pro-v1:0
|
||||
label:
|
||||
en_US: Nova Pro V1
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 300000
|
||||
parameter_rules:
|
||||
- name: max_new_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 2048
|
||||
min: 1
|
||||
max: 5000
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
required: false
|
||||
type: float
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
help:
|
||||
zh_Hans: 生成内容的随机性。
|
||||
en_US: The amount of randomness injected into the response.
|
||||
- name: top_p
|
||||
required: false
|
||||
type: float
|
||||
default: 0.999
|
||||
min: 0.000
|
||||
max: 1.000
|
||||
help:
|
||||
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
|
||||
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
|
||||
- name: top_k
|
||||
required: false
|
||||
type: int
|
||||
default: 0
|
||||
min: 0
|
||||
# tip docs from aws has error, max value is 500
|
||||
max: 500
|
||||
help:
|
||||
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
|
||||
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
|
||||
pricing:
|
||||
input: '0.0008'
|
||||
output: '0.0032'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
+60
@@ -0,0 +1,60 @@
|
||||
model: anthropic.claude-3-5-haiku-20241022-v1:0
|
||||
label:
|
||||
en_US: Claude 3.5 Haiku
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
|
||||
parameter_rules:
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
type: int
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
help:
|
||||
zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
|
||||
en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
|
||||
# docs: https://docs.anthropic.com/claude/docs/system-prompts
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
required: false
|
||||
type: float
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
help:
|
||||
zh_Hans: 生成内容的随机性。
|
||||
en_US: The amount of randomness injected into the response.
|
||||
- name: top_p
|
||||
required: false
|
||||
type: float
|
||||
default: 0.999
|
||||
min: 0.000
|
||||
max: 1.000
|
||||
help:
|
||||
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
|
||||
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
|
||||
- name: top_k
|
||||
required: false
|
||||
type: int
|
||||
default: 0
|
||||
min: 0
|
||||
# tip docs from aws has error, max value is 500
|
||||
max: 500
|
||||
help:
|
||||
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
|
||||
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: '0.001'
|
||||
output: '0.005'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
+60
@@ -0,0 +1,60 @@
|
||||
model: anthropic.claude-3-5-sonnet-20241022-v2:0
|
||||
label:
|
||||
en_US: Claude 3.5 Sonnet V2
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
|
||||
parameter_rules:
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
type: int
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
help:
|
||||
zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
|
||||
en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
required: false
|
||||
type: float
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
help:
|
||||
zh_Hans: 生成内容的随机性。
|
||||
en_US: The amount of randomness injected into the response.
|
||||
- name: top_p
|
||||
required: false
|
||||
type: float
|
||||
default: 0.999
|
||||
min: 0.000
|
||||
max: 1.000
|
||||
help:
|
||||
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
|
||||
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
|
||||
- name: top_k
|
||||
required: false
|
||||
type: int
|
||||
default: 0
|
||||
min: 0
|
||||
# tip docs from aws has error, max value is 500
|
||||
max: 500
|
||||
help:
|
||||
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
|
||||
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: '0.003'
|
||||
output: '0.015'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
+60
@@ -0,0 +1,60 @@
|
||||
model: eu.anthropic.claude-3-5-sonnet-20241022-v2:0
|
||||
label:
|
||||
en_US: Claude 3.5 Sonnet V2(EU.Cross Region Inference)
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
|
||||
parameter_rules:
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
type: int
|
||||
default: 4096
|
||||
min: 1
|
||||
max: 4096
|
||||
help:
|
||||
zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
|
||||
en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
required: false
|
||||
type: float
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
help:
|
||||
zh_Hans: 生成内容的随机性。
|
||||
en_US: The amount of randomness injected into the response.
|
||||
- name: top_p
|
||||
required: false
|
||||
type: float
|
||||
default: 0.999
|
||||
min: 0.000
|
||||
max: 1.000
|
||||
help:
|
||||
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
|
||||
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
|
||||
- name: top_k
|
||||
required: false
|
||||
type: int
|
||||
default: 0
|
||||
min: 0
|
||||
# tip docs from aws has error, max value is 500
|
||||
max: 500
|
||||
help:
|
||||
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
|
||||
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: '0.003'
|
||||
output: '0.015'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,53 @@
|
||||
model: us.amazon.nova-lite-v1:0
|
||||
label:
|
||||
en_US: Nova Lite V1 (US.Cross Region Inference)
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 300000
|
||||
parameter_rules:
|
||||
- name: max_new_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 2048
|
||||
min: 1
|
||||
max: 5000
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
required: false
|
||||
type: float
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
help:
|
||||
zh_Hans: 生成内容的随机性。
|
||||
en_US: The amount of randomness injected into the response.
|
||||
- name: top_p
|
||||
required: false
|
||||
type: float
|
||||
default: 0.999
|
||||
min: 0.000
|
||||
max: 1.000
|
||||
help:
|
||||
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
|
||||
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
|
||||
- name: top_k
|
||||
required: false
|
||||
type: int
|
||||
default: 0
|
||||
min: 0
|
||||
# tip docs from aws has error, max value is 500
|
||||
max: 500
|
||||
help:
|
||||
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
|
||||
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
|
||||
pricing:
|
||||
input: '0.00006'
|
||||
output: '0.00024'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,52 @@
|
||||
model: us.amazon.nova-micro-v1:0
|
||||
label:
|
||||
en_US: Nova Micro V1 (US.Cross Region Inference)
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: max_new_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 2048
|
||||
min: 1
|
||||
max: 5000
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
required: false
|
||||
type: float
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
help:
|
||||
zh_Hans: 生成内容的随机性。
|
||||
en_US: The amount of randomness injected into the response.
|
||||
- name: top_p
|
||||
required: false
|
||||
type: float
|
||||
default: 0.999
|
||||
min: 0.000
|
||||
max: 1.000
|
||||
help:
|
||||
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
|
||||
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
|
||||
- name: top_k
|
||||
required: false
|
||||
type: int
|
||||
default: 0
|
||||
min: 0
|
||||
# tip docs from aws has error, max value is 500
|
||||
max: 500
|
||||
help:
|
||||
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
|
||||
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
|
||||
pricing:
|
||||
input: '0.000035'
|
||||
output: '0.00014'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,53 @@
|
||||
model: us.amazon.nova-pro-v1:0
|
||||
label:
|
||||
en_US: Nova Pro V1 (US.Cross Region Inference)
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 300000
|
||||
parameter_rules:
|
||||
- name: max_new_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 2048
|
||||
min: 1
|
||||
max: 5000
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
required: false
|
||||
type: float
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
help:
|
||||
zh_Hans: 生成内容的随机性。
|
||||
en_US: The amount of randomness injected into the response.
|
||||
- name: top_p
|
||||
required: false
|
||||
type: float
|
||||
default: 0.999
|
||||
min: 0.000
|
||||
max: 1.000
|
||||
help:
|
||||
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
|
||||
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
|
||||
- name: top_k
|
||||
required: false
|
||||
type: int
|
||||
default: 0
|
||||
min: 0
|
||||
# tip docs from aws has error, max value is 500
|
||||
max: 500
|
||||
help:
|
||||
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
|
||||
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
|
||||
pricing:
|
||||
input: '0.0008'
|
||||
output: '0.0032'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
+60
@@ -0,0 +1,60 @@
|
||||
model: us.anthropic.claude-3-5-haiku-20241022-v1:0
|
||||
label:
|
||||
en_US: Claude 3.5 Haiku(US.Cross Region Inference)
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
|
||||
parameter_rules:
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
type: int
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
help:
|
||||
zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
|
||||
en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
|
||||
# docs: https://docs.anthropic.com/claude/docs/system-prompts
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
required: false
|
||||
type: float
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
help:
|
||||
zh_Hans: 生成内容的随机性。
|
||||
en_US: The amount of randomness injected into the response.
|
||||
- name: top_p
|
||||
required: false
|
||||
type: float
|
||||
default: 0.999
|
||||
min: 0.000
|
||||
max: 1.000
|
||||
help:
|
||||
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
|
||||
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
|
||||
- name: top_k
|
||||
required: false
|
||||
type: int
|
||||
default: 0
|
||||
min: 0
|
||||
# tip docs from aws has error, max value is 500
|
||||
max: 500
|
||||
help:
|
||||
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
|
||||
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: '0.001'
|
||||
output: '0.005'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
+60
@@ -0,0 +1,60 @@
|
||||
model: us.anthropic.claude-3-5-sonnet-20241022-v2:0
|
||||
label:
|
||||
en_US: Claude 3.5 Sonnet V2(US.Cross Region Inference)
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
# docs: https://docs.aws.amazon.com/bedrock/latest/userguide/model-parameters-anthropic-claude-messages.html
|
||||
parameter_rules:
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
type: int
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
help:
|
||||
zh_Hans: 停止前生成的最大令牌数。请注意，Anthropic Claude 模型可能会在达到 max_tokens 的值之前停止生成令牌。不同的 Anthropic Claude 模型对此参数具有不同的最大值。
|
||||
en_US: The maximum number of tokens to generate before stopping. Note that Anthropic Claude models might stop generating tokens before reaching the value of max_tokens. Different Anthropic Claude models have different maximum values for this parameter.
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
required: false
|
||||
type: float
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 1.0
|
||||
help:
|
||||
zh_Hans: 生成内容的随机性。
|
||||
en_US: The amount of randomness injected into the response.
|
||||
- name: top_p
|
||||
required: false
|
||||
type: float
|
||||
default: 0.999
|
||||
min: 0.000
|
||||
max: 1.000
|
||||
help:
|
||||
zh_Hans: 在核采样中，Anthropic Claude 按概率递减顺序计算每个后续标记的所有选项的累积分布，并在达到 top_p 指定的特定概率时将其切断。您应该更改温度或top_p，但不能同时更改两者。
|
||||
en_US: In nucleus sampling, Anthropic Claude computes the cumulative distribution over all the options for each subsequent token in decreasing probability order and cuts it off once it reaches a particular probability specified by top_p. You should alter either temperature or top_p, but not both.
|
||||
- name: top_k
|
||||
required: false
|
||||
type: int
|
||||
default: 0
|
||||
min: 0
|
||||
# tip docs from aws has error, max value is 500
|
||||
max: 500
|
||||
help:
|
||||
zh_Hans: 对于每个后续标记，仅从前 K 个选项中进行采样。使用 top_k 删除长尾低概率响应。
|
||||
en_US: Only sample from the top K options for each subsequent token. Use top_k to remove long tail low probability responses.
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: '0.003'
|
||||
output: '0.015'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
+29
@@ -0,0 +1,29 @@
|
||||
model: us.meta.llama3-2-11b-instruct-v1:0
|
||||
label:
|
||||
en_US: US Meta Llama 3.2 11B Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- vision
|
||||
- tool-call
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 0.5
|
||||
min: 0.0
|
||||
max: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_gen_len
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 512
|
||||
min: 1
|
||||
max: 2048
|
||||
pricing:
|
||||
input: '0.00035'
|
||||
output: '0.00035'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
+26
@@ -0,0 +1,26 @@
|
||||
model: us.meta.llama3-2-1b-instruct-v1:0
|
||||
label:
|
||||
en_US: US Meta Llama 3.2 1B Instruct
|
||||
model_type: llm
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 0.5
|
||||
min: 0.0
|
||||
max: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_gen_len
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 512
|
||||
min: 1
|
||||
max: 2048
|
||||
pricing:
|
||||
input: '0.0001'
|
||||
output: '0.0001'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
+26
@@ -0,0 +1,26 @@
|
||||
model: us.meta.llama3-2-3b-instruct-v1:0
|
||||
label:
|
||||
en_US: US Meta Llama 3.2 3B Instruct
|
||||
model_type: llm
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 0.5
|
||||
min: 0.0
|
||||
max: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_gen_len
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 512
|
||||
min: 1
|
||||
max: 2048
|
||||
pricing:
|
||||
input: '0.00015'
|
||||
output: '0.00015'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
+31
@@ -0,0 +1,31 @@
|
||||
model: us.meta.llama3-2-90b-instruct-v1:0
|
||||
label:
|
||||
en_US: US Meta Llama 3.2 90B Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- tool-call
|
||||
model_properties:
|
||||
mode: completion
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 0.5
|
||||
min: 0.0
|
||||
max: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
default: 0.9
|
||||
min: 0
|
||||
max: 1
|
||||
- name: max_gen_len
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 512
|
||||
min: 1
|
||||
max: 2048
|
||||
pricing:
|
||||
input: '0.002'
|
||||
output: '0.002'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,21 @@
|
||||
model: deepseek-reasoner
|
||||
label:
|
||||
zh_Hans: deepseek-reasoner
|
||||
en_US: deepseek-reasoner
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 64000
|
||||
parameter_rules:
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 8192
|
||||
default: 4096
|
||||
pricing:
|
||||
input: "4"
|
||||
output: "16"
|
||||
unit: "0.000001"
|
||||
currency: RMB
|
||||
+46
@@ -0,0 +1,46 @@
|
||||
model: accounts/fireworks/models/llama-v3p2-11b-vision-instruct
|
||||
label:
|
||||
zh_Hans: Llama 3.2 11B Vision Instruct
|
||||
en_US: Llama 3.2 11B Vision Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
- name: context_length_exceeded_behavior
|
||||
default: None
|
||||
label:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
help:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
type: string
|
||||
options:
|
||||
- None
|
||||
- truncate
|
||||
- error
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: '0.2'
|
||||
output: '0.2'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,46 @@
|
||||
model: accounts/fireworks/models/llama-v3p2-1b-instruct
|
||||
label:
|
||||
zh_Hans: Llama 3.2 1B Instruct
|
||||
en_US: Llama 3.2 1B Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
- name: context_length_exceeded_behavior
|
||||
default: None
|
||||
label:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
help:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
type: string
|
||||
options:
|
||||
- None
|
||||
- truncate
|
||||
- error
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: '0.1'
|
||||
output: '0.1'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,46 @@
|
||||
model: accounts/fireworks/models/llama-v3p2-3b-instruct
|
||||
label:
|
||||
zh_Hans: Llama 3.2 3B Instruct
|
||||
en_US: Llama 3.2 3B Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
- name: context_length_exceeded_behavior
|
||||
default: None
|
||||
label:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
help:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
type: string
|
||||
options:
|
||||
- None
|
||||
- truncate
|
||||
- error
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: '0.1'
|
||||
output: '0.1'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
+46
@@ -0,0 +1,46 @@
|
||||
model: accounts/fireworks/models/llama-v3p2-90b-vision-instruct
|
||||
label:
|
||||
zh_Hans: Llama 3.2 90B Vision Instruct
|
||||
en_US: Llama 3.2 90B Vision Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
- name: context_length_exceeded_behavior
|
||||
default: None
|
||||
label:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
help:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
type: string
|
||||
options:
|
||||
- None
|
||||
- truncate
|
||||
- error
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: '0.9'
|
||||
output: '0.9'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,46 @@
|
||||
model: accounts/fireworks/models/qwen2p5-72b-instruct
|
||||
label:
|
||||
zh_Hans: Qwen2.5 72B Instruct
|
||||
en_US: Qwen2.5 72B Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32768
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
- name: context_length_exceeded_behavior
|
||||
default: None
|
||||
label:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
help:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
type: string
|
||||
options:
|
||||
- None
|
||||
- truncate
|
||||
- error
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: '0.9'
|
||||
output: '0.9'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: gemini-1.5-flash-001
|
||||
label:
|
||||
en_US: Gemini 1.5 Flash 001
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 1048576
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: gemini-1.5-flash-002
|
||||
label:
|
||||
en_US: Gemini 1.5 Flash 002
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 1048576
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
+41
@@ -0,0 +1,41 @@
|
||||
model: gemini-1.5-flash-8b-exp-0924
|
||||
label:
|
||||
en_US: Gemini 1.5 Flash 8B 0924
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 1048576
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: gemini-1.5-flash
|
||||
label:
|
||||
en_US: Gemini 1.5 Flash
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 1048576
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: gemini-1.5-pro-001
|
||||
label:
|
||||
en_US: Gemini 1.5 Pro 001
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 2097152
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: gemini-1.5-pro-002
|
||||
label:
|
||||
en_US: Gemini 1.5 Pro 002
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 2097152
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: gemini-1.5-pro
|
||||
label:
|
||||
en_US: Gemini 1.5 Pro
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 2097152
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: gemini-2.0-flash-001
|
||||
label:
|
||||
en_US: Gemini 2.0 Flash 001
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 1048576
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: gemini-2.0-flash-exp
|
||||
label:
|
||||
en_US: Gemini 2.0 Flash Exp
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 1048576
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
+41
@@ -0,0 +1,41 @@
|
||||
model: gemini-2.0-flash-lite-preview-02-05
|
||||
label:
|
||||
en_US: Gemini 2.0 Flash Lite Preview 0205
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 1048576
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
+39
@@ -0,0 +1,39 @@
|
||||
model: gemini-2.0-flash-thinking-exp-01-21
|
||||
label:
|
||||
en_US: Gemini 2.0 Flash Thinking Exp 01-21
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32767
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
+39
@@ -0,0 +1,39 @@
|
||||
model: gemini-2.0-flash-thinking-exp-1219
|
||||
label:
|
||||
en_US: Gemini 2.0 Flash Thinking Exp 1219
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32767
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: gemini-2.0-pro-exp-02-05
|
||||
label:
|
||||
en_US: Gemini 2.0 pro exp 02-05
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 1048576
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: gemini-exp-1114
|
||||
label:
|
||||
en_US: Gemini exp 1114
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32767
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: gemini-exp-1121
|
||||
label:
|
||||
en_US: Gemini exp 1121
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32767
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: gemini-exp-1206
|
||||
label:
|
||||
en_US: Gemini exp 1206
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 2097152
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
+41
@@ -0,0 +1,41 @@
|
||||
model: learnlm-1.5-pro-experimental
|
||||
label:
|
||||
en_US: LearnLM 1.5 Pro Experimental
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
- document
|
||||
- video
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32767
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_output_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '0.00'
|
||||
output: '0.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,36 @@
|
||||
model: deepseek-r1-distill-llama-70b
|
||||
label:
|
||||
en_US: DeepSeek R1 Distill Llama 70b
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: Response Format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '3.00'
|
||||
output: '3.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,37 @@
|
||||
model: gemma-7b-it
|
||||
label:
|
||||
zh_Hans: Gemma 7B Instruction Tuned
|
||||
en_US: Gemma 7B Instruction Tuned
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: Response Format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '0.05'
|
||||
output: '0.1'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,37 @@
|
||||
model: gemma2-9b-it
|
||||
label:
|
||||
zh_Hans: Gemma 2 9B Instruction Tuned
|
||||
en_US: Gemma 2 9B Instruction Tuned
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: Response Format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '0.05'
|
||||
output: '0.1'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,38 @@
|
||||
model: llama-3.2-11b-text-preview
|
||||
deprecated: true
|
||||
label:
|
||||
zh_Hans: Llama 3.2 11B Text (Preview)
|
||||
en_US: Llama 3.2 11B Text (Preview)
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: Response Format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '0.05'
|
||||
output: '0.1'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,38 @@
|
||||
model: llama-3.2-11b-vision-preview
|
||||
label:
|
||||
zh_Hans: Llama 3.2 11B Vision (Preview)
|
||||
en_US: Llama 3.2 11B Vision (Preview)
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: Response Format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '0.05'
|
||||
output: '0.1'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,37 @@
|
||||
model: llama-3.2-1b-preview
|
||||
label:
|
||||
zh_Hans: Llama 3.2 1B Text (Preview)
|
||||
en_US: Llama 3.2 1B Text (Preview)
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: Response Format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '0.05'
|
||||
output: '0.1'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,37 @@
|
||||
model: llama-3.2-3b-preview
|
||||
label:
|
||||
zh_Hans: Llama 3.2 3B Text (Preview)
|
||||
en_US: Llama 3.2 3B Text (Preview)
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: Response Format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '0.05'
|
||||
output: '0.1'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,38 @@
|
||||
model: llama-3.2-90b-text-preview
|
||||
depraceted: true
|
||||
label:
|
||||
zh_Hans: Llama 3.2 90B Text (Preview)
|
||||
en_US: Llama 3.2 90B Text (Preview)
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: Response Format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '0.05'
|
||||
output: '0.1'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,38 @@
|
||||
model: llama-3.2-90b-vision-preview
|
||||
label:
|
||||
zh_Hans: Llama 3.2 90B Vision (Preview)
|
||||
en_US: Llama 3.2 90B Vision (Preview)
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: Response Format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '0.05'
|
||||
output: '0.1'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,38 @@
|
||||
model: llama-3.3-70b-specdec
|
||||
label:
|
||||
zh_Hans: Llama 3.3 70B Specdec
|
||||
en_US: Llama 3.3 70B Specdec
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- multi-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 1024
|
||||
min: 1
|
||||
max: 32768
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: Response Format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: "0.05"
|
||||
output: "0.1"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@@ -0,0 +1,38 @@
|
||||
model: llama-3.3-70b-versatile
|
||||
label:
|
||||
zh_Hans: Llama 3.3 70B Versatile
|
||||
en_US: Llama 3.3 70B Versatile
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- multi-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 1024
|
||||
min: 1
|
||||
max: 32768
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: Response Format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: "0.05"
|
||||
output: "0.1"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@@ -0,0 +1,37 @@
|
||||
model: llama-guard-3-8b
|
||||
label:
|
||||
zh_Hans: Llama-Guard-3-8B
|
||||
en_US: Llama-Guard-3-8B
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: Response Format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '0.20'
|
||||
output: '0.20'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
+38
@@ -0,0 +1,38 @@
|
||||
model: llama3-groq-70b-8192-tool-use-preview
|
||||
label:
|
||||
zh_Hans: Llama3-groq-70b-8192-tool-use (PREVIEW)
|
||||
en_US: Llama3-groq-70b-8192-tool-use (PREVIEW)
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- multi-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: Response Format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '0.05'
|
||||
output: '0.08'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,38 @@
|
||||
model: hunyuan-functioncall
|
||||
label:
|
||||
zh_Hans: hunyuan-functioncall
|
||||
en_US: hunyuan-functioncall
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- multi-tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 1024
|
||||
min: 1
|
||||
max: 32000
|
||||
- name: enable_enhance
|
||||
label:
|
||||
zh_Hans: 功能增强
|
||||
en_US: Enable Enhancement
|
||||
type: boolean
|
||||
help:
|
||||
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
|
||||
en_US: Allow the model to perform external search to enhance the generation results.
|
||||
required: false
|
||||
default: true
|
||||
pricing:
|
||||
input: '0.004'
|
||||
output: '0.008'
|
||||
unit: '0.001'
|
||||
currency: RMB
|
||||
@@ -0,0 +1,38 @@
|
||||
model: hunyuan-large-longcontext
|
||||
label:
|
||||
zh_Hans: hunyuan-large-longcontext
|
||||
en_US: hunyuan-large-longcontext
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- multi-tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 134000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 1024
|
||||
min: 1
|
||||
max: 134000
|
||||
- name: enable_enhance
|
||||
label:
|
||||
zh_Hans: 功能增强
|
||||
en_US: Enable Enhancement
|
||||
type: boolean
|
||||
help:
|
||||
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
|
||||
en_US: Allow the model to perform external search to enhance the generation results.
|
||||
required: false
|
||||
default: true
|
||||
pricing:
|
||||
input: '0.006'
|
||||
output: '0.018'
|
||||
unit: '0.001'
|
||||
currency: RMB
|
||||
@@ -0,0 +1,38 @@
|
||||
model: hunyuan-large-role
|
||||
label:
|
||||
zh_Hans: hunyuan-large-role
|
||||
en_US: hunyuan-large-role
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- multi-tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 1024
|
||||
min: 1
|
||||
max: 32000
|
||||
- name: enable_enhance
|
||||
label:
|
||||
zh_Hans: 功能增强
|
||||
en_US: Enable Enhancement
|
||||
type: boolean
|
||||
help:
|
||||
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
|
||||
en_US: Allow the model to perform external search to enhance the generation results.
|
||||
required: false
|
||||
default: true
|
||||
pricing:
|
||||
input: '0.004'
|
||||
output: '0.008'
|
||||
unit: '0.001'
|
||||
currency: RMB
|
||||
@@ -0,0 +1,38 @@
|
||||
model: hunyuan-large
|
||||
label:
|
||||
zh_Hans: hunyuan-large
|
||||
en_US: hunyuan-large
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- multi-tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 1024
|
||||
min: 1
|
||||
max: 32000
|
||||
- name: enable_enhance
|
||||
label:
|
||||
zh_Hans: 功能增强
|
||||
en_US: Enable Enhancement
|
||||
type: boolean
|
||||
help:
|
||||
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
|
||||
en_US: Allow the model to perform external search to enhance the generation results.
|
||||
required: false
|
||||
default: true
|
||||
pricing:
|
||||
input: '0.004'
|
||||
output: '0.012'
|
||||
unit: '0.001'
|
||||
currency: RMB
|
||||
@@ -0,0 +1,38 @@
|
||||
model: hunyuan-role
|
||||
label:
|
||||
zh_Hans: hunyuan-role
|
||||
en_US: hunyuan-role
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- multi-tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 1024
|
||||
min: 1
|
||||
max: 32000
|
||||
- name: enable_enhance
|
||||
label:
|
||||
zh_Hans: 功能增强
|
||||
en_US: Enable Enhancement
|
||||
type: boolean
|
||||
help:
|
||||
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
|
||||
en_US: Allow the model to perform external search to enhance the generation results.
|
||||
required: false
|
||||
default: true
|
||||
pricing:
|
||||
input: '0.004'
|
||||
output: '0.008'
|
||||
unit: '0.001'
|
||||
currency: RMB
|
||||
@@ -0,0 +1,38 @@
|
||||
model: hunyuan-turbo-latest
|
||||
label:
|
||||
zh_Hans: hunyuan-turbo-latest
|
||||
en_US: hunyuan-turbo-latest
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- multi-tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 1024
|
||||
min: 1
|
||||
max: 32000
|
||||
- name: enable_enhance
|
||||
label:
|
||||
zh_Hans: 功能增强
|
||||
en_US: Enable Enhancement
|
||||
type: boolean
|
||||
help:
|
||||
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
|
||||
en_US: Allow the model to perform external search to enhance the generation results.
|
||||
required: false
|
||||
default: true
|
||||
pricing:
|
||||
input: '0.015'
|
||||
output: '0.05'
|
||||
unit: '0.001'
|
||||
currency: RMB
|
||||
@@ -0,0 +1,39 @@
|
||||
model: hunyuan-turbo-vision
|
||||
label:
|
||||
zh_Hans: hunyuan-turbo-vision
|
||||
en_US: hunyuan-turbo-vision
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- multi-tool-call
|
||||
- stream-tool-call
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 8000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 1024
|
||||
min: 1
|
||||
max: 8000
|
||||
- name: enable_enhance
|
||||
label:
|
||||
zh_Hans: 功能增强
|
||||
en_US: Enable Enhancement
|
||||
type: boolean
|
||||
help:
|
||||
zh_Hans: 功能增强（如搜索）开关，关闭时将直接由主模型生成回复内容，可以降低响应时延（对于流式输出时的首字时延尤为明显）。但在少数场景里，回复效果可能会下降。
|
||||
en_US: Allow the model to perform external search to enhance the generation results.
|
||||
required: false
|
||||
default: true
|
||||
pricing:
|
||||
input: '0.08'
|
||||
output: '0.08'
|
||||
unit: '0.001'
|
||||
currency: RMB
|
||||
@@ -0,0 +1,44 @@
|
||||
model: abab6.5t-chat
|
||||
label:
|
||||
en_US: Abab6.5t-Chat
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0.01
|
||||
max: 1
|
||||
default: 0.9
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0.01
|
||||
max: 1
|
||||
default: 0.95
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 3072
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: mask_sensitive_info
|
||||
type: boolean
|
||||
default: true
|
||||
label:
|
||||
zh_Hans: 隐私保护
|
||||
en_US: Moderate
|
||||
help:
|
||||
zh_Hans: 对输出中易涉及隐私问题的文本信息进行打码，目前包括但不限于邮箱、域名、链接、证件号、家庭住址等，默认true，即开启打码
|
||||
en_US: Mask the sensitive info of the generated content, such as email/domain/link/address/phone/id..
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
pricing:
|
||||
input: '0.005'
|
||||
output: '0.005'
|
||||
unit: '0.001'
|
||||
currency: RMB
|
||||
@@ -0,0 +1,46 @@
|
||||
model: abab7-chat-preview
|
||||
label:
|
||||
en_US: Abab7-chat-preview
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 245760
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0.01
|
||||
max: 1
|
||||
default: 0.1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0.01
|
||||
max: 1
|
||||
default: 0.95
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 2048
|
||||
min: 1
|
||||
max: 245760
|
||||
- name: mask_sensitive_info
|
||||
type: boolean
|
||||
default: true
|
||||
label:
|
||||
zh_Hans: 隐私保护
|
||||
en_US: Moderate
|
||||
help:
|
||||
zh_Hans: 对输出中易涉及隐私问题的文本信息进行打码，目前包括但不限于邮箱、域名、链接、证件号、家庭住址等，默认true，即开启打码
|
||||
en_US: Mask the sensitive info of the generated content, such as email/domain/link/address/phone/id..
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
pricing:
|
||||
input: '0.1'
|
||||
output: '0.1'
|
||||
unit: '0.001'
|
||||
currency: RMB
|
||||
@@ -0,0 +1,46 @@
|
||||
model: minimax-text-01
|
||||
label:
|
||||
en_US: Minimax-Text-01
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 1000192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0.01
|
||||
max: 1
|
||||
default: 0.1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0.01
|
||||
max: 1
|
||||
default: 0.95
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 2048
|
||||
min: 1
|
||||
max: 1000192
|
||||
- name: mask_sensitive_info
|
||||
type: boolean
|
||||
default: true
|
||||
label:
|
||||
zh_Hans: 隐私保护
|
||||
en_US: Moderate
|
||||
help:
|
||||
zh_Hans: 对输出中易涉及隐私问题的文本信息进行打码，目前包括但不限于邮箱、域名、链接、证件号、家庭住址等，默认true，即开启打码
|
||||
en_US: Mask the sensitive info of the generated content, such as email/domain/link/address/phone/id..
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
pricing:
|
||||
input: '0.001'
|
||||
output: '0.008'
|
||||
unit: '0.001'
|
||||
currency: RMB
|
||||
@@ -0,0 +1,52 @@
|
||||
model: pixtral-large-2411
|
||||
label:
|
||||
zh_Hans: pixtral-large-2411
|
||||
en_US: pixtral-large-2411
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 0.7
|
||||
min: 0
|
||||
max: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
default: 1
|
||||
min: 0
|
||||
max: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: safe_prompt
|
||||
default: false
|
||||
type: boolean
|
||||
help:
|
||||
en_US: Whether to inject a safety prompt before all conversations.
|
||||
zh_Hans: 是否开启提示词审查
|
||||
label:
|
||||
en_US: SafePrompt
|
||||
zh_Hans: 提示词审查
|
||||
- name: random_seed
|
||||
type: int
|
||||
help:
|
||||
en_US: The seed to use for random sampling. If set, different calls will generate deterministic results.
|
||||
zh_Hans: 当开启随机数种子以后，你可以通过指定一个固定的种子来使得回答结果更加稳定
|
||||
label:
|
||||
en_US: RandomSeed
|
||||
zh_Hans: 随机数种子
|
||||
default: 0
|
||||
min: 0
|
||||
max: 2147483647
|
||||
pricing:
|
||||
input: '0.008'
|
||||
output: '0.024'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,52 @@
|
||||
model: pixtral-large-latest
|
||||
label:
|
||||
zh_Hans: pixtral-large-latest
|
||||
en_US: pixtral-large-latest
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
default: 0.7
|
||||
min: 0
|
||||
max: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
default: 1
|
||||
min: 0
|
||||
max: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: safe_prompt
|
||||
default: false
|
||||
type: boolean
|
||||
help:
|
||||
en_US: Whether to inject a safety prompt before all conversations.
|
||||
zh_Hans: 是否开启提示词审查
|
||||
label:
|
||||
en_US: SafePrompt
|
||||
zh_Hans: 提示词审查
|
||||
- name: random_seed
|
||||
type: int
|
||||
help:
|
||||
en_US: The seed to use for random sampling. If set, different calls will generate deterministic results.
|
||||
zh_Hans: 当开启随机数种子以后，你可以通过指定一个固定的种子来使得回答结果更加稳定
|
||||
label:
|
||||
en_US: RandomSeed
|
||||
zh_Hans: 随机数种子
|
||||
default: 0
|
||||
min: 0
|
||||
max: 2147483647
|
||||
pricing:
|
||||
input: '0.008'
|
||||
output: '0.024'
|
||||
unit: '0.001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: Sao10K/L3-8B-Stheno-v3.2
|
||||
label:
|
||||
zh_Hans: L3 8B Stheno V3.2
|
||||
en_US: L3 8B Stheno V3.2
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.0005'
|
||||
output: '0.0005'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: deepseek/deepseek-r1
|
||||
label:
|
||||
zh_Hans: DeepSeek R1
|
||||
en_US: DeepSeek R1
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 64000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.04'
|
||||
output: '0.04'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: deepseek/deepseek_v3
|
||||
label:
|
||||
zh_Hans: DeepSeek V3
|
||||
en_US: DeepSeek V3
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 64000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.0089'
|
||||
output: '0.0089'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: sao10k/l3-8b-lunaris
|
||||
label:
|
||||
zh_Hans: "Sao10k L3 8B Lunaris"
|
||||
en_US: "Sao10k L3 8B Lunaris"
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.0005'
|
||||
output: '0.0005'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: sao10k/l31-70b-euryale-v2.2
|
||||
label:
|
||||
zh_Hans: L31 70B Euryale V2.2
|
||||
en_US: L31 70B Euryale V2.2
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 16000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.0148'
|
||||
output: '0.0148'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: meta-llama/llama-3.1-8b-instruct-bf16
|
||||
label:
|
||||
zh_Hans: Llama 3.1 8B Instruct BF16
|
||||
en_US: Llama 3.1 8B Instruct BF16
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 8192
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.0006'
|
||||
output: '0.0006'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: meta-llama/llama-3.1-8b-instruct-max
|
||||
label:
|
||||
zh_Hans: "Llama3.1 8B Instruct Max\t"
|
||||
en_US: "Llama3.1 8B Instruct Max\t"
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 16384
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.0005'
|
||||
output: '0.0005'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
+41
@@ -0,0 +1,41 @@
|
||||
model: meta-llama/llama-3.2-11b-vision-instruct
|
||||
label:
|
||||
zh_Hans: "Llama 3.2 11B Vision Instruct\t"
|
||||
en_US: "Llama 3.2 11B Vision Instruct\t"
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32768
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.0006'
|
||||
output: '0.0006'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: meta-llama/llama-3.2-1b-instruct
|
||||
label:
|
||||
zh_Hans: "Llama 3.2 1B Instruct\t"
|
||||
en_US: "Llama 3.2 1B Instruct\t"
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.0002'
|
||||
output: '0.0002'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: meta-llama/llama-3.2-3b-instruct
|
||||
label:
|
||||
zh_Hans: Llama 3.2 3B Instruct
|
||||
en_US: Llama 3.2 3B Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32768
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.0003'
|
||||
output: '0.0005'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: meta-llama/llama-3.3-70b-instruct
|
||||
label:
|
||||
zh_Hans: Llama 3.3 70B Instruct
|
||||
en_US: Llama 3.3 70B Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.0039'
|
||||
output: '0.0039'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
@@ -1,69 +0,0 @@
|
||||
from collections.abc import Generator
|
||||
from typing import Optional, Union
|
||||
|
||||
from core.model_runtime.entities.llm_entities import LLMResult
|
||||
from core.model_runtime.entities.message_entities import PromptMessage, PromptMessageTool
|
||||
from core.model_runtime.entities.model_entities import AIModelEntity
|
||||
from core.model_runtime.model_providers.openai_api_compatible.llm.llm import OAIAPICompatLargeLanguageModel
|
||||
|
||||
|
||||
class NovitaLargeLanguageModel(OAIAPICompatLargeLanguageModel):
|
||||
def _update_endpoint_url(self, credentials: dict):
|
||||
credentials["endpoint_url"] = "https://api.novita.ai/v3/openai"
|
||||
credentials["extra_headers"] = {"X-Novita-Source": "dify.ai"}
|
||||
return credentials
|
||||
|
||||
def _invoke(
|
||||
self,
|
||||
model: str,
|
||||
credentials: dict,
|
||||
prompt_messages: list[PromptMessage],
|
||||
model_parameters: dict,
|
||||
tools: Optional[list[PromptMessageTool]] = None,
|
||||
stop: Optional[list[str]] = None,
|
||||
stream: bool = True,
|
||||
user: Optional[str] = None,
|
||||
) -> Union[LLMResult, Generator]:
|
||||
cred_with_endpoint = self._update_endpoint_url(credentials=credentials)
|
||||
return super()._invoke(model, cred_with_endpoint, prompt_messages, model_parameters, tools, stop, stream, user)
|
||||
|
||||
def validate_credentials(self, model: str, credentials: dict) -> None:
|
||||
cred_with_endpoint = self._update_endpoint_url(credentials=credentials)
|
||||
self._add_custom_parameters(credentials, model)
|
||||
return super().validate_credentials(model, cred_with_endpoint)
|
||||
|
||||
@classmethod
|
||||
def _add_custom_parameters(cls, credentials: dict, model: str) -> None:
|
||||
credentials["mode"] = "chat"
|
||||
|
||||
def _generate(
|
||||
self,
|
||||
model: str,
|
||||
credentials: dict,
|
||||
prompt_messages: list[PromptMessage],
|
||||
model_parameters: dict,
|
||||
tools: Optional[list[PromptMessageTool]] = None,
|
||||
stop: Optional[list[str]] = None,
|
||||
stream: bool = True,
|
||||
user: Optional[str] = None,
|
||||
) -> Union[LLMResult, Generator]:
|
||||
cred_with_endpoint = self._update_endpoint_url(credentials=credentials)
|
||||
return super()._generate(
|
||||
model, cred_with_endpoint, prompt_messages, model_parameters, tools, stop, stream, user
|
||||
)
|
||||
|
||||
def get_customizable_model_schema(self, model: str, credentials: dict) -> AIModelEntity:
|
||||
cred_with_endpoint = self._update_endpoint_url(credentials=credentials)
|
||||
|
||||
return super().get_customizable_model_schema(model, cred_with_endpoint)
|
||||
|
||||
def get_num_tokens(
|
||||
self,
|
||||
model: str,
|
||||
credentials: dict,
|
||||
prompt_messages: list[PromptMessage],
|
||||
tools: Optional[list[PromptMessageTool]] = None,
|
||||
) -> int:
|
||||
cred_with_endpoint = self._update_endpoint_url(credentials=credentials)
|
||||
|
||||
return super().get_num_tokens(model, cred_with_endpoint, prompt_messages, tools)
|
||||
@@ -0,0 +1,41 @@
|
||||
model: mistralai/mistral-nemo
|
||||
label:
|
||||
zh_Hans: Mistral Nemo
|
||||
en_US: Mistral Nemo
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.0017'
|
||||
output: '0.0017'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: openchat/openchat-7b
|
||||
label:
|
||||
zh_Hans: OpenChat 7B
|
||||
en_US: OpenChat 7B
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 4096
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.0006'
|
||||
output: '0.0006'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: qwen/qwen-2-72b-instruct
|
||||
label:
|
||||
zh_Hans: Qwen2 72B Instruct
|
||||
en_US: Qwen2 72B Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32768
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.0034'
|
||||
output: '0.0039'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: qwen/qwen-2-7b-instruct
|
||||
label:
|
||||
zh_Hans: Qwen 2 7B Instruct
|
||||
en_US: Qwen 2 7B Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32768
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.00054'
|
||||
output: '0.00054'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: qwen/qwen-2-vl-72b-instruct
|
||||
label:
|
||||
zh_Hans: Qwen 2 VL 72B Instruct
|
||||
en_US: Qwen 2 VL 72B Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32768
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.0045'
|
||||
output: '0.0045'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,41 @@
|
||||
model: qwen/qwen-2.5-72b-instruct
|
||||
label:
|
||||
zh_Hans: Qwen 2.5 72B Instruct
|
||||
en_US: Qwen 2.5 72B Instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 32000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 2
|
||||
default: 1
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 2048
|
||||
default: 512
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
pricing:
|
||||
input: '0.0038'
|
||||
output: '0.004'
|
||||
unit: '0.0001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,35 @@
|
||||
model: deepseek-ai/deepseek-r1
|
||||
label:
|
||||
en_US: deepseek-ai/deepseek-r1
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
min: 0
|
||||
max: 1
|
||||
default: 0.5
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
min: 0
|
||||
max: 1
|
||||
default: 1
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
min: 1
|
||||
max: 1024
|
||||
default: 1024
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
min: -2
|
||||
max: 2
|
||||
default: 0
|
||||
@@ -0,0 +1,47 @@
|
||||
model: gpt-4o-2024-11-20
|
||||
label:
|
||||
zh_Hans: gpt-4o-2024-11-20
|
||||
en_US: gpt-4o-2024-11-20
|
||||
model_type: llm
|
||||
features:
|
||||
- multi-tool-call
|
||||
- agent-thought
|
||||
- stream-tool-call
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 16384
|
||||
min: 1
|
||||
max: 16384
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: Response Format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
- json_schema
|
||||
- name: json_schema
|
||||
use_template: json_schema
|
||||
pricing:
|
||||
input: '2.50'
|
||||
output: '10.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,44 @@
|
||||
model: gpt-4o-audio-preview
|
||||
label:
|
||||
zh_Hans: gpt-4o-audio-preview
|
||||
en_US: gpt-4o-audio-preview
|
||||
model_type: llm
|
||||
features:
|
||||
- multi-tool-call
|
||||
- agent-thought
|
||||
- stream-tool-call
|
||||
- audio
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 128000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 16384
|
||||
min: 1
|
||||
max: 16384
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: Response Format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '5.00'
|
||||
output: '15.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,48 @@
|
||||
model: o1-2024-12-17
|
||||
label:
|
||||
en_US: o1-2024-12-17
|
||||
model_type: llm
|
||||
features:
|
||||
- multi-tool-call
|
||||
- agent-thought
|
||||
- stream-tool-call
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
parameter_rules:
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 50000
|
||||
min: 1
|
||||
max: 50000
|
||||
- name: reasoning_effort
|
||||
label:
|
||||
zh_Hans: 推理工作
|
||||
en_US: reasoning_effort
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 限制推理模型的推理工作
|
||||
en_US: constrains effort on reasoning for reasoning models
|
||||
required: false
|
||||
options:
|
||||
- low
|
||||
- medium
|
||||
- high
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: response_format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '15.00'
|
||||
output: '60.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,49 @@
|
||||
model: o1
|
||||
label:
|
||||
zh_Hans: o1
|
||||
en_US: o1
|
||||
model_type: llm
|
||||
features:
|
||||
- multi-tool-call
|
||||
- agent-thought
|
||||
- stream-tool-call
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
parameter_rules:
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 50000
|
||||
min: 1
|
||||
max: 50000
|
||||
- name: reasoning_effort
|
||||
label:
|
||||
zh_Hans: 推理工作
|
||||
en_US: reasoning_effort
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 限制推理模型的推理工作
|
||||
en_US: constrains effort on reasoning for reasoning models
|
||||
required: false
|
||||
options:
|
||||
- low
|
||||
- medium
|
||||
- high
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: response_format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '15.00'
|
||||
output: '60.00'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,46 @@
|
||||
model: o3-mini-2025-01-31
|
||||
label:
|
||||
zh_Hans: o3-mini-2025-01-31
|
||||
en_US: o3-mini-2025-01-31
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
parameter_rules:
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 100000
|
||||
min: 1
|
||||
max: 100000
|
||||
- name: reasoning_effort
|
||||
label:
|
||||
zh_Hans: 推理工作
|
||||
en_US: reasoning_effort
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 限制推理模型的推理工作
|
||||
en_US: constrains effort on reasoning for reasoning models
|
||||
required: false
|
||||
options:
|
||||
- low
|
||||
- medium
|
||||
- high
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: response_format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '1.10'
|
||||
output: '4.40'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,46 @@
|
||||
model: o3-mini
|
||||
label:
|
||||
zh_Hans: o3-mini
|
||||
en_US: o3-mini
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
parameter_rules:
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 100000
|
||||
min: 1
|
||||
max: 100000
|
||||
- name: reasoning_effort
|
||||
label:
|
||||
zh_Hans: 推理工作
|
||||
en_US: reasoning_effort
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 限制推理模型的推理工作
|
||||
en_US: constrains effort on reasoning for reasoning models
|
||||
required: false
|
||||
options:
|
||||
- low
|
||||
- medium
|
||||
- high
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: response_format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: '1.10'
|
||||
output: '4.40'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,38 @@
|
||||
model: anthropic/claude-3-5-haiku
|
||||
label:
|
||||
en_US: claude-3-5-haiku
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- tool-call
|
||||
- stream-tool-call
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
required: true
|
||||
default: 8192
|
||||
min: 1
|
||||
max: 8192
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: "1"
|
||||
output: "5"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
@@ -0,0 +1,59 @@
|
||||
model: deepseek/deepseek-r1
|
||||
label:
|
||||
en_US: deepseek-r1
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 163840
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
type: float
|
||||
default: 1
|
||||
min: 0.0
|
||||
max: 2.0
|
||||
help:
|
||||
zh_Hans: 控制生成结果的多样性和随机性。数值越小，越严谨；数值越大，越发散。
|
||||
en_US: Control the diversity and randomness of generated results. The smaller the value, the more rigorous it is; the larger the value, the more divergent it is.
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
type: int
|
||||
default: 4096
|
||||
min: 1
|
||||
max: 4096
|
||||
help:
|
||||
zh_Hans: 指定生成结果长度的上限。如果生成结果截断，可以调大该参数。
|
||||
en_US: Specifies the upper limit on the length of generated results. If the generated results are truncated, you can increase this parameter.
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
type: float
|
||||
default: 1
|
||||
min: 0.01
|
||||
max: 1.00
|
||||
help:
|
||||
zh_Hans: 控制生成结果的随机性。数值越小，随机性越弱；数值越大，随机性越强。一般而言，top_p 和 temperature 两个参数选择一个进行调整即可。
|
||||
en_US: Control the randomness of generated results. The smaller the value, the weaker the randomness; the larger the value, the stronger the randomness. Generally speaking, you can adjust one of the two parameters top_p and temperature.
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
default: 0
|
||||
min: -2.0
|
||||
max: 2.0
|
||||
help:
|
||||
zh_Hans: 介于 -2.0 和 2.0 之间的数字。如果该值为正，那么新 token 会根据其在已有文本中的出现频率受到相应的惩罚，降低模型重复相同内容的可能性。
|
||||
en_US: A number between -2.0 and 2.0. If the value is positive, new tokens are penalized based on their frequency of occurrence in existing text, reducing the likelihood that the model will repeat the same content.
|
||||
pricing:
|
||||
input: "3"
|
||||
output: "8"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
+46
@@ -0,0 +1,46 @@
|
||||
model: meta-llama/llama-3.2-11b-vision-instruct
|
||||
label:
|
||||
zh_Hans: llama-3.2-11b-vision-instruct
|
||||
en_US: llama-3.2-11b-vision-instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
- name: context_length_exceeded_behavior
|
||||
default: None
|
||||
label:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
help:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
type: string
|
||||
options:
|
||||
- None
|
||||
- truncate
|
||||
- error
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: '0.055'
|
||||
output: '0.055'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,45 @@
|
||||
model: meta-llama/llama-3.2-1b-instruct
|
||||
label:
|
||||
zh_Hans: llama-3.2-1b-instruct
|
||||
en_US: llama-3.2-1b-instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
- name: context_length_exceeded_behavior
|
||||
default: None
|
||||
label:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
help:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
type: string
|
||||
options:
|
||||
- None
|
||||
- truncate
|
||||
- error
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: '0.01'
|
||||
output: '0.02'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,45 @@
|
||||
model: meta-llama/llama-3.2-3b-instruct
|
||||
label:
|
||||
zh_Hans: llama-3.2-3b-instruct
|
||||
en_US: llama-3.2-3b-instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
- name: context_length_exceeded_behavior
|
||||
default: None
|
||||
label:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
help:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
type: string
|
||||
options:
|
||||
- None
|
||||
- truncate
|
||||
- error
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: '0.03'
|
||||
output: '0.05'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
+46
@@ -0,0 +1,46 @@
|
||||
model: meta-llama/llama-3.2-90b-vision-instruct
|
||||
label:
|
||||
zh_Hans: llama-3.2-90b-vision-instruct
|
||||
en_US: llama-3.2-90b-vision-instruct
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
- vision
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 131072
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
- name: context_length_exceeded_behavior
|
||||
default: None
|
||||
label:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
help:
|
||||
zh_Hans: 上下文长度超出行为
|
||||
en_US: Context Length Exceeded Behavior
|
||||
type: string
|
||||
options:
|
||||
- None
|
||||
- truncate
|
||||
- error
|
||||
- name: response_format
|
||||
use_template: response_format
|
||||
pricing:
|
||||
input: '0.35'
|
||||
output: '0.4'
|
||||
unit: '0.000001'
|
||||
currency: USD
|
||||
@@ -0,0 +1,49 @@
|
||||
model: openai/o3-mini-2025-01-31
|
||||
label:
|
||||
en_US: o3-mini-2025-01-31
|
||||
model_type: llm
|
||||
features:
|
||||
- agent-thought
|
||||
model_properties:
|
||||
mode: chat
|
||||
context_size: 200000
|
||||
parameter_rules:
|
||||
- name: temperature
|
||||
use_template: temperature
|
||||
- name: top_p
|
||||
use_template: top_p
|
||||
- name: top_k
|
||||
label:
|
||||
zh_Hans: 取样数量
|
||||
en_US: Top k
|
||||
type: int
|
||||
help:
|
||||
zh_Hans: 仅从每个后续标记的前 K 个选项中采样。
|
||||
en_US: Only sample from the top K options for each subsequent token.
|
||||
required: false
|
||||
- name: presence_penalty
|
||||
use_template: presence_penalty
|
||||
- name: frequency_penalty
|
||||
use_template: frequency_penalty
|
||||
- name: max_tokens
|
||||
use_template: max_tokens
|
||||
default: 512
|
||||
min: 1
|
||||
max: 100000
|
||||
- name: response_format
|
||||
label:
|
||||
zh_Hans: 回复格式
|
||||
en_US: response_format
|
||||
type: string
|
||||
help:
|
||||
zh_Hans: 指定模型必须输出的格式
|
||||
en_US: specifying the format that the model must output
|
||||
required: false
|
||||
options:
|
||||
- text
|
||||
- json_object
|
||||
pricing:
|
||||
input: "1.10"
|
||||
output: "4.40"
|
||||
unit: "0.000001"
|
||||
currency: USD
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user