|
|
|
- type: openai
|
|
|
|
# docs:
|
|
|
|
# - https://platform.openai.com/docs/models
|
|
|
|
# - https://openai.com/pricing
|
|
|
|
# - https://platform.openai.com/docs/api-reference/chat
|
|
|
|
# notes
|
|
|
|
# - get max_output_tokens info from api error
|
|
|
|
models:
|
|
|
|
- name: gpt-3.5-turbo
|
|
|
|
max_input_tokens: 16385
|
|
|
|
max_output_tokens?: 4096
|
|
|
|
input_price: 0.5
|
|
|
|
output_price: 1.5
|
|
|
|
- name: gpt-3.5-turbo-1106
|
|
|
|
max_input_tokens: 16385
|
|
|
|
max_output_tokens?: 4096
|
|
|
|
input_price: 1
|
|
|
|
output_price: 2
|
|
|
|
- name: gpt-4-turbo
|
|
|
|
max_input_tokens: 128000
|
|
|
|
max_output_tokens?: 4096
|
|
|
|
input_price: 10
|
|
|
|
output_price: 30
|
|
|
|
supports_vision: true
|
|
|
|
- name: gpt-4-turbo-preview
|
|
|
|
max_input_tokens: 128000
|
|
|
|
max_output_tokens?: 4096
|
|
|
|
input_price: 10
|
|
|
|
output_price: 30
|
|
|
|
- name: gpt-4-1106-preview
|
|
|
|
max_input_tokens: 128000
|
|
|
|
max_output_tokens?: 4096
|
|
|
|
input_price: 10
|
|
|
|
output_price: 30
|
|
|
|
- name: gpt-4-vision-preview
|
|
|
|
max_input_tokens: 128000
|
|
|
|
max_output_tokens: 4096
|
|
|
|
input_price: 10
|
|
|
|
output_price: 30
|
|
|
|
supports_vision: true
|
|
|
|
- name: gpt-4
|
|
|
|
max_input_tokens: 8192
|
|
|
|
max_output_tokens?: 4096
|
|
|
|
input_price: 30
|
|
|
|
output_price: 60
|
|
|
|
- name: gpt-4-32k
|
|
|
|
max_input_tokens: 32768
|
|
|
|
max_output_tokens?: 4096
|
|
|
|
input_price: 60
|
|
|
|
output_price: 120
|
|
|
|
|
|
|
|
- type: gemini
|
|
|
|
# docs:
|
|
|
|
# - https://ai.google.dev/models/gemini
|
|
|
|
# - https://ai.google.dev/pricing
|
|
|
|
# - https://ai.google.dev/api/rest/v1beta/models/streamGenerateContent
|
|
|
|
# notes:
|
|
|
|
# - get max_output_tokens info from list models api
|
|
|
|
models:
|
|
|
|
- name: gemini-1.0-pro-latest
|
|
|
|
max_input_tokens: 30720
|
|
|
|
max_output_tokens?: 2048
|
|
|
|
input_price: 0.5
|
|
|
|
output_price: 1.5
|
|
|
|
- name: gemini-1.0-pro-vision-latest
|
|
|
|
max_input_tokens: 12288
|
|
|
|
max_output_tokens?: 4096
|
|
|
|
input_price: 0.5
|
|
|
|
output_price: 1.5
|
|
|
|
supports_vision: true
|
|
|
|
- name: gemini-1.5-pro-latest
|
|
|
|
max_input_tokens: 1048576
|
|
|
|
max_output_tokens?: 8192
|
|
|
|
input_price: 7
|
|
|
|
output_price: 21
|
|
|
|
supports_vision: true
|
|
|
|
|
|
|
|
- type: claude
|
|
|
|
# docs:
|
|
|
|
# - https://docs.anthropic.com/claude/docs/models-overview
|
|
|
|
# - https://docs.anthropic.com/claude/reference/messages-streaming
|
|
|
|
# notes:
|
|
|
|
# - get max_output_tokens info from models doc
|
|
|
|
models:
|
|
|
|
- name: claude-3-opus-20240229
|
|
|
|
max_input_tokens: 200000
|
|
|
|
max_output_tokens: 4096
|
|
|
|
input_price: 15
|
|
|
|
output_price: 75
|
|
|
|
supports_vision: true
|
|
|
|
- name: claude-3-sonnet-20240229
|
|
|
|
max_input_tokens: 200000
|
|
|
|
max_output_tokens: 4096
|
|
|
|
input_price: 3
|
|
|
|
output_price: 15
|
|
|
|
supports_vision: true
|
|
|
|
- name: claude-3-haiku-20240307
|
|
|
|
max_input_tokens: 200000
|
|
|
|
max_output_tokens: 4096
|
|
|
|
input_price: 0.25
|
|
|
|
output_price: 1.25
|
|
|
|
supports_vision: true
|
|
|
|
|
|
|
|
- type: mistral
|
|
|
|
# docs:
|
|
|
|
# - https://docs.mistral.ai/getting-started/models/
|
|
|
|
# - https://mistral.ai/technology/#pricing
|
|
|
|
# - https://docs.mistral.ai/api/
|
|
|
|
# notes:
|
|
|
|
# - unable to get max_output_tokens info
|
|
|
|
models:
|
|
|
|
- name: open-mistral-7b
|
|
|
|
max_input_tokens: 32000
|
|
|
|
input_price: 0.25
|
|
|
|
output_price: 0.25
|
|
|
|
- name: open-mixtral-8x7b
|
|
|
|
max_input_tokens: 32000
|
|
|
|
input_price: 0.7
|
|
|
|
output_price: 0.7
|
|
|
|
- name: open-mixtral-8x22b
|
|
|
|
max_input_tokens: 64000
|
|
|
|
input_price: 2
|
|
|
|
output_price: 6
|
|
|
|
- name: mistral-small-latest
|
|
|
|
max_input_tokens: 32000
|
|
|
|
input_price: 2
|
|
|
|
output_price: 6
|
|
|
|
- name: mistral-medium-latest
|
|
|
|
max_input_tokens: 32000
|
|
|
|
input_price: 2.7
|
|
|
|
output_price: 8.1
|
|
|
|
- name: mistral-large-latest
|
|
|
|
max_input_tokens: 32000
|
|
|
|
input_price: 8
|
|
|
|
output_price: 24
|
|
|
|
|
|
|
|
- type: cohere
|
|
|
|
# docs:
|
|
|
|
# - https://docs.cohere.com/docs/command-r
|
|
|
|
# - https://cohere.com/pricing
|
|
|
|
# - https://docs.cohere.com/reference/chat
|
|
|
|
# notes
|
|
|
|
# - get max_output_tokens info from api error
|
|
|
|
models:
|
|
|
|
- name: command-r
|
|
|
|
max_input_tokens: 128000
|
|
|
|
max_output_tokens?: 4000
|
|
|
|
input_price: 0.5
|
|
|
|
output_price: 1.5
|
|
|
|
- name: command-r-plus
|
|
|
|
max_input_tokens: 128000
|
|
|
|
max_output_tokens?: 4000
|
|
|
|
input_price: 3
|
|
|
|
output_price: 15
|
|
|
|
|
|
|
|
- type: perplexity
|
|
|
|
# docs:
|
|
|
|
# - https://docs.perplexity.ai/docs/model-cards
|
|
|
|
# - https://docs.perplexity.ai/docs/pricing
|
|
|
|
# - https://docs.perplexity.ai/reference/post_chat_completions
|
|
|
|
# notes
|
|
|
|
# - get max_output_tokens info from api error
|
|
|
|
models:
|
|
|
|
- name: sonar-small-chat
|
|
|
|
max_input_tokens: 16384
|
|
|
|
max_output_tokens?: 16384
|
|
|
|
- name: sonar-small-online
|
|
|
|
max_input_tokens: 12000
|
|
|
|
max_output_tokens?: 12288
|
|
|
|
- name: sonar-medium-chat
|
|
|
|
max_input_tokens: 16384
|
|
|
|
max_output_tokens?: 16384
|
|
|
|
- name: sonar-medium-online
|
|
|
|
max_input_tokens: 12000
|
|
|
|
max_output_tokens?: 12288
|
|
|
|
|
|
|
|
- name: llama-3-8b-instruct
|
|
|
|
max_input_tokens: 8192
|
|
|
|
max_output_tokens?: 8192
|
|
|
|
input_price: 0.2
|
|
|
|
output_price: 0.2
|
|
|
|
- name: llama-3-70b-instruct
|
|
|
|
max_input_tokens: 8192
|
|
|
|
max_output_tokens?: 8192
|
|
|
|
input_price: 1
|
|
|
|
output_price: 1
|
|
|
|
- name: codellama-70b-instruct
|
|
|
|
max_input_tokens: 16384
|
|
|
|
max_output_tokens?: 16384
|
|
|
|
input_price: 1
|
|
|
|
output_price: 1
|
|
|
|
- name: mistral-7b-instruct
|
|
|
|
max_input_tokens: 16384
|
|
|
|
max_output_tokens?: 16384
|
|
|
|
input_price: 0.2
|
|
|
|
output_price: 0.2
|
|
|
|
- name: mixtral-8x7b-instruct
|
|
|
|
max_input_tokens: 16384
|
|
|
|
max_output_tokens?: 16384
|
|
|
|
input_price: 0.6
|
|
|
|
output_price: 0.6
|
|
|
|
- name: mixtral-8x22b-instruct
|
|
|
|
max_input_tokens: 16384
|
|
|
|
max_output_tokens?: 16384
|
|
|
|
input_price: 1
|
|
|
|
output_price: 1
|
|
|
|
|
|
|
|
- type: groq
|
|
|
|
# docs:
|
|
|
|
# - https://console.groq.com/docs/models
|
|
|
|
# - https://console.groq.com/docs/text-chat
|
|
|
|
# notes:
|
|
|
|
# - unable to get max_output_tokens info
|
|
|
|
# - all models are free with rate limits
|
|
|
|
models:
|
|
|
|
- name: llama3-8b-8192
|
|
|
|
max_input_tokens: 8192
|
|
|
|
- name: llama3-70b-8192
|
|
|
|
max_input_tokens: 8192
|
|
|
|
- name: llama2-70b-4096
|
|
|
|
max_input_tokens: 4096
|
|
|
|
- name: mixtral-8x7b-32768
|
|
|
|
max_input_tokens: 32768
|
|
|
|
- name: gemma-7b-it
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
|
|
|
- type: vertexai
|
|
|
|
# docs:
|
|
|
|
# - https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models
|
|
|
|
# - https://cloud.google.com/vertex-ai/generative-ai/pricing
|
|
|
|
# - https://cloud.google.com/vertex-ai/generative-ai/docs/model-reference/gemini
|
|
|
|
# notes:
|
|
|
|
# - get max_output_tokens info from models doc
|
|
|
|
# - claude models have not been tested
|
|
|
|
models:
|
|
|
|
- name: gemini-1.0-pro
|
|
|
|
max_input_tokens: 24568
|
|
|
|
max_output_tokens?: 8192
|
|
|
|
input_price: 0.125
|
|
|
|
output_price: 0.375
|
|
|
|
- name: gemini-1.0-pro-vision
|
|
|
|
max_input_tokens: 14336
|
|
|
|
max_output_tokens?: 2048
|
|
|
|
input_price: 0.125
|
|
|
|
output_price: 0.375
|
|
|
|
supports_vision: true
|
|
|
|
- name: gemini-1.5-pro-preview-0409
|
|
|
|
max_input_tokens: 1000000
|
|
|
|
max_output_tokens?: 8192
|
|
|
|
input_price: 2.5
|
|
|
|
output_price: 7.5
|
|
|
|
supports_vision: true
|
|
|
|
- name: claude-3-opus@20240229
|
|
|
|
max_input_tokens: 200000
|
|
|
|
max_output_tokens: 4096
|
|
|
|
input_price: 15
|
|
|
|
output_price: 75
|
|
|
|
supports_vision: true
|
|
|
|
- name: claude-3-sonnet@20240229
|
|
|
|
max_input_tokens: 200000
|
|
|
|
max_output_tokens: 4096
|
|
|
|
input_price: 3
|
|
|
|
output_price: 15
|
|
|
|
supports_vision: true
|
|
|
|
- name: claude-3-haiku@20240307
|
|
|
|
max_input_tokens: 200000
|
|
|
|
max_output_tokens: 4096
|
|
|
|
input_price: 0.25
|
|
|
|
output_price: 1.25
|
|
|
|
supports_vision: true
|
|
|
|
|
|
|
|
- type: bedrock
|
|
|
|
# docs:
|
|
|
|
# - https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns
|
|
|
|
# - https://aws.amazon.com/bedrock/pricing/
|
|
|
|
# notes:
|
|
|
|
# - get max_output_tokens info from playground
|
|
|
|
# - claude/llama models have not been tested
|
|
|
|
models:
|
|
|
|
- name: anthropic.claude-3-opus-20240229-v1:0
|
|
|
|
max_input_tokens: 200000
|
|
|
|
max_output_tokens: 4096
|
|
|
|
input_price: 15
|
|
|
|
output_price: 75
|
|
|
|
supports_vision: true
|
|
|
|
- name: anthropic.claude-3-sonnet-20240229-v1:0
|
|
|
|
max_input_tokens: 200000
|
|
|
|
max_output_tokens: 4096
|
|
|
|
input_price: 3
|
|
|
|
output_price: 15
|
|
|
|
supports_vision: true
|
|
|
|
- name: anthropic.claude-3-haiku-20240307-v1:0
|
|
|
|
max_input_tokens: 200000
|
|
|
|
max_output_tokens: 4096
|
|
|
|
input_price: 0.25
|
|
|
|
output_price: 1.25
|
|
|
|
supports_vision: true
|
|
|
|
- name: meta.llama2-13b-chat-v1
|
|
|
|
max_input_tokens: 4096
|
|
|
|
max_output_tokens: 2048
|
|
|
|
input_price: 0.75
|
|
|
|
output_price: 1
|
|
|
|
- name: meta.llama2-70b-chat-v1
|
|
|
|
max_input_tokens: 4096
|
|
|
|
max_output_tokens: 2048
|
|
|
|
input_price: 1.95
|
|
|
|
output_price: 2.56
|
|
|
|
- name: meta.llama3-8b-instruct-v1:0
|
|
|
|
max_input_tokens: 8192
|
|
|
|
max_output_tokens: 4096
|
|
|
|
input_price: 0.4
|
|
|
|
output_price: 0.6
|
|
|
|
- name: meta.llama3-70b-instruct-v1:0
|
|
|
|
max_input_tokens: 8192
|
|
|
|
max_output_tokens: 4096
|
|
|
|
input_price: 2.65
|
|
|
|
output_price: 3.5
|
|
|
|
- name: mistral.mistral-7b-instruct-v0:2
|
|
|
|
max_input_tokens: 32000
|
|
|
|
max_output_tokens: 8192
|
|
|
|
input_price: 0.15
|
|
|
|
output_price: 0.2
|
|
|
|
- name: mistral.mixtral-8x7b-instruct-v0:1
|
|
|
|
max_input_tokens: 32000
|
|
|
|
max_output_tokens: 8192
|
|
|
|
input_price: 0.45
|
|
|
|
output_price: 0.7
|
|
|
|
- name: mistral.mistral-large-2402-v1:0
|
|
|
|
max_input_tokens: 32000
|
|
|
|
max_output_tokens: 8192
|
|
|
|
input_price: 8
|
|
|
|
output_price: 2.4
|
|
|
|
|
|
|
|
- type: cloudflare
|
|
|
|
# docs:
|
|
|
|
# - https://developers.cloudflare.com/workers-ai/models/
|
|
|
|
# - https://developers.cloudflare.com/workers-ai/platform/pricing/
|
|
|
|
# notes:
|
|
|
|
# - get max_output_tokens info from models doc
|
|
|
|
models:
|
|
|
|
- name: '@cf/meta/llama-2-7b-chat-fp16'
|
|
|
|
max_input_tokens: 3072
|
|
|
|
max_output_tokens: 2500
|
|
|
|
input_price: 0.56
|
|
|
|
output_price: 6.6
|
|
|
|
- name: '@cf/meta/llama-2-7b-chat-int8'
|
|
|
|
max_input_tokens: 2048
|
|
|
|
max_output_tokens: 1800
|
|
|
|
input_price: 0.16
|
|
|
|
output_price: 0.24
|
|
|
|
- name: '@cf/mistral/mistral-7b-instruct-v0.1'
|
|
|
|
input_price: 0.11
|
|
|
|
output_price: 0.19
|
|
|
|
|
|
|
|
- type: ernie
|
|
|
|
# docs:
|
|
|
|
# - https://cloud.baidu.com/doc/WENXINWORKSHOP/s/Nlks5zkzu
|
|
|
|
# - https://cloud.baidu.com/doc/WENXINWORKSHOP/s/hlrk4akp7
|
|
|
|
# notes:
|
|
|
|
# - get max_output_tokens info from models doc
|
|
|
|
models:
|
|
|
|
- name: ernie-4.0-8k-preview
|
|
|
|
max_input_tokens: 5120
|
|
|
|
max_output_tokens: 2048
|
|
|
|
input_price: 16.8
|
|
|
|
output_price: 16.8
|
|
|
|
- name: ernie-3.5-8k-preview
|
|
|
|
max_input_tokens: 5120
|
|
|
|
max_output_tokens: 2048
|
|
|
|
input_price: 1.68
|
|
|
|
output_price: 1.68
|
|
|
|
- name: ernie-speed-128k
|
|
|
|
max_input_tokens: 124000
|
|
|
|
max_output_tokens: 4096
|
|
|
|
input_price: 0.56
|
|
|
|
output_price: 1.12
|
|
|
|
- name: ernie-lite-8k
|
|
|
|
max_input_tokens: 7168
|
|
|
|
max_output_tokens: 2048
|
|
|
|
input_price: 0.42
|
|
|
|
output_price: 0.84
|
|
|
|
- name: ernie-tiny-8k
|
|
|
|
max_input_tokens: 7168
|
|
|
|
max_output_tokens: 2048
|
|
|
|
input_price: 0.14
|
|
|
|
output_price: 0.14
|
|
|
|
|
|
|
|
- type: qianwen
|
|
|
|
# docs:
|
|
|
|
# - https://help.aliyun.com/zh/dashscope/developer-reference/tongyiqianwen-large-language-models/
|
|
|
|
# - https://help.aliyun.com/zh/dashscope/developer-reference/qwen-vl-plus/
|
|
|
|
# notes:
|
|
|
|
# - get max_output_tokens info from models doc
|
|
|
|
models:
|
|
|
|
- name: qwen-turbo
|
|
|
|
max_input_tokens: 6000
|
|
|
|
max_output_tokens?: 1500
|
|
|
|
input_price: 1.12
|
|
|
|
output_price: 1.12
|
|
|
|
- name: qwen-plus
|
|
|
|
max_input_tokens: 30000
|
|
|
|
max_output_tokens?: 2000
|
|
|
|
input_price: 2.8
|
|
|
|
output_price: 2.8
|
|
|
|
- name: qwen-max
|
|
|
|
max_input_tokens: 6000
|
|
|
|
max_output_tokens?: 2000
|
|
|
|
input_price: 16.8
|
|
|
|
output_price: 16.8
|
|
|
|
- name: qwen-max-longcontext
|
|
|
|
max_input_tokens: 28000
|
|
|
|
max_output_tokens?: 2000
|
|
|
|
- name: qwen-vl-plus
|
|
|
|
input_price: 1.12
|
|
|
|
output_price: 1.12
|
|
|
|
supports_vision: true
|
|
|
|
- name: qwen-vl-max
|
|
|
|
input_price: 2.8
|
|
|
|
output_price: 2.8
|
|
|
|
supports_vision: true
|
|
|
|
|
|
|
|
- type: moonshot
|
|
|
|
# docs:
|
|
|
|
# - https://platform.moonshot.cn/docs/intro
|
|
|
|
# - https://platform.moonshot.cn/docs/pricing
|
|
|
|
# - https://platform.moonshot.cn/docs/api-reference
|
|
|
|
# notes:
|
|
|
|
# - unable to get max_output_tokens info
|
|
|
|
models:
|
|
|
|
- name: moonshot-v1-8k
|
|
|
|
max_input_tokens: 8000
|
|
|
|
input_price: 1.68
|
|
|
|
output_price: 1.68
|
|
|
|
- name: moonshot-v1-32k
|
|
|
|
max_input_tokens: 32000
|
|
|
|
input_price: 3.36
|
|
|
|
output_price: 3.36
|
|
|
|
- name: moonshot-v1-128k
|
|
|
|
max_input_tokens: 128000
|
|
|
|
input_price: 8.4
|
|
|
|
output_price: 8.4
|