aichat/models.yaml

- platform: 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

- platform: 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

- platform: 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

- platform: 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-large-latest
      max_input_tokens: 32000
      input_price: 8
      output_price: 24

- platform: 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

- platform: 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

- platform: groq
  # docs:
  #   - https://console.groq.com/docs/models
  #   - https://wow.groq.com
  #   - https://console.groq.com/docs/text-chat
  # notes:
  #   - get max_output_tokens info from playgourd
  #   - all models are free with rate limits
  models:
    - name: llama3-8b-8192
      max_input_tokens: 8192
      max_output_tokens?: 8192
      input_price: 0.05
      output_price: 0.10
    - name: llama3-70b-8192
      max_input_tokens: 8192
      max_output_tokens?: 8192
      input_price: 0.59
      output_price: 0.79
    - name: mixtral-8x7b-32768
      max_input_tokens: 32768
      max_output_tokens?: 32768
      input_price: 0.27
      output_price: 0.27
    - name: gemma-7b-it
      max_input_tokens: 8192
      max_output_tokens?: 8192
      input_price: 0.10
      output_price: 0.10

- platform: 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

- platform: 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.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

- platform: cloudflare
  # docs:
  #   - https://developers.cloudflare.com/workers-ai/models/
  #   - https://developers.cloudflare.com/workers-ai/platform/pricing/
  # notes:
  #   - unable to get max_output_tokens info
  models:
    - name: '@cf/meta/llama-3-8b-instruct'
      max_input_tokens: 4096
      max_output_tokens: 4096
    - name: '@cf/mistral/mistral-7b-instruct-v0.2-lora'
      max_input_tokens: 4096
      max_output_tokens: 4096
    - name: '@cf/google/gemma-7b-it-lora'
      max_input_tokens: 4096
      max_output_tokens: 4096
    - name: '@cf/qwen/qwen1.5-14b-chat-awq'
      max_input_tokens: 4096
      max_output_tokens: 4096
    - name: '@hf/nexusflow/starling-lm-7b-beta'
      max_input_tokens: 4096
      max_output_tokens: 4096

- platform: replicate
  # docs:
  #   - https://replicate.com/docs
  #   - https://replicate.com/pricing
  # notes:
  #   - max_output_tokens is required but unknown
  models:
    - name: meta/meta-llama-3-70b-instruct
      max_input_tokens: 8192
      max_output_tokens: 4096
      input_price: 0.65
      output_price: 2.75
    - name: meta/meta-llama-3-8b-instruct
      max_input_tokens: 8192
      max_output_tokens: 4096
      input_price: 0.05
      output_price: 0.25
    - name: mistralai/mistral-7b-instruct-v0.2
      max_input_tokens: 32000
      max_output_tokens: 8192
      input_price: 0.05
      output_price: 0.25
    - name: mistralai/mixtral-8x7b-instruct-v0.1
      max_input_tokens: 32000
      max_output_tokens: 8192
      input_price: 0.3
      output_price: 1

- platform: 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

- platform: 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

- platform: 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

- platform: anyscale
  # docs:
  #   - https://docs.endpoints.anyscale.com/text-generation/query-a-model/#select-a-model
  #   - https://docs.endpoints.anyscale.com/pricing
  models:
    - name: meta-llama/Meta-Llama-3-8B-Instruct
      max_input_tokens: 8192
      input_price: 0.15
      output_price: 0.15
    - name: meta-llama/Meta-Llama-3-70B-Instruct
      max_input_tokens: 8192
      input_price: 1.0
      output_price: 1.0
    - name: codellama/CodeLlama-70b-Instruct-hf
      max_input_tokens: 4096
      input_price: 1.0
      output_price: 1.0
    - name: mistralai/Mistral-7B-Instruct-v0.1
      max_input_tokens: 16384
      input_price: 0.15
      output_price: 0.15
    - name: mistralai/Mixtral-8x7B-Instruct-v0.1
      max_input_tokens: 32768
      input_price: 0.50
      output_price: 0.50
    - name: mistralai/Mixtral-8x22B-Instruct-v0.1
      max_input_tokens: 65536
      input_price: 0.90
      output_price: 0.90
    - name: google/gemma-7b-it
      max_input_tokens: 8192
      input_price: 0.15
      output_price: 0.15

- platform: deepinfra
  # docs:
  #   - https://deepinfra.com/models
  #   - https://deepinfra.com/pricing
  models:
    - name: meta-llama/Meta-Llama-3-8B-Instruct
      max_input_tokens: 8192
      input_price: 0.08
      output_price: 0.08
    - name: meta-llama/Meta-Llama-3-70B-Instruct
      max_input_tokens: 8192
      input_price: 0.59
      output_price: 0.79
    - name: mistralai/Mistral-7B-Instruct-v0.2
      max_input_tokens: 32768
      input_price: 0.07
      output_price: 0.07
    - name: mistralai/Mixtral-8x7B-Instruct-v0.1
      max_input_tokens: 32768
      input_price: 0.24
      output_price: 0.24
    - name: mistralai/Mixtral-8x22B-Instruct-v0.1
      max_input_tokens: 65536
      input_price: 0.65
      output_price: 0.65
    - name: google/gemma-1.1-7b-it
      max_input_tokens: 8192
      input_price: 0.07
      output_price: 0.07
    - name: databricks/dbrx-instruct
      max_input_tokens: 32768
      input_price: 0.6
      output_price: 0.6
    - name: 01-ai/Yi-34B-Chat
      max_input_tokens: 4096
      input_price: 0.6
      output_price: 0.6

- platform: fireworks
  # docs:
  #   - https://fireworks.ai/models
  #   - https://fireworks.ai/pricing
  models:
    - name: accounts/fireworks/models/llama-v3-8b-instruct
      max_input_tokens: 8192
      input_price: 0.2
      output_price: 0.2
    - name: accounts/fireworks/models/llama-v3-70b-instruct
      max_input_tokens: 8192
      input_price: 0.9
      output_price: 0.9
    - name: accounts/fireworks/models/mistral-7b-instruct-v0p2
      max_input_tokens: 32768
      input_price: 0.2
      output_price: 0.2
    - name: accounts/fireworks/models/mixtral-8x7b-instruct
      max_input_tokens: 32768
      input_price: 0.5
      output_price: 0.5
    - name: accounts/fireworks/models/mixtral-8x22b-instruct
      max_input_tokens: 65536
      input_price: 0.9
      output_price: 0.9
    - name: accounts/fireworks/models/qwen-72b-chat
      max_input_tokens: 4096
      input_price: 0.9
      output_price: 0.9
    - name: accounts/fireworks/models/gemma-7b-it
      max_input_tokens: 8192
      input_price: 0.2
      output_price: 0.2
    - name: accounts/fireworks/models/dbrx-instruct
      max_input_tokens: 32768
      input_price: 1.6
      output_price: 1.6

- platform: openrouter
  # docs:
  #   - https://openrouter.ai/docs#models
  models:
    - name: meta-llama/llama-3-8b-instruct
      max_input_tokens: 8192
      input_price: 0.1
      output_price: 0.1
    - name: meta-llama/llama-3-8b-instruct:nitro
      max_input_tokens: 8192
      input_price: 0.2
      output_price: 0.2
    - name: meta-llama/llama-3-8b-instruct:extended
      max_input_tokens: 16384
      input_price: 0.275
      output_price: 0.283
    - name: meta-llama/llama-3-70b-instruct
      max_input_tokens: 8192
      input_price: 0.81
      output_price: 0.81
    - name: meta-llama/llama-3-70b-instruct:nitro
      max_input_tokens: 8192
      input_price: 0.9
      output_price: 0.9
    - name: mistralai/mistral-7b-instruct:free
      max_input_tokens: 32768
      input_price: 0.0
      output_price: 0.0
    - name: codellama/codellama-70b-instruct
      max_input_tokens: 2048
      input_price: 0.81
      output_price: 0.81
    - name: google/gemma-7b-it:free
      max_input_tokens: 8192
      input_price: 0.0
      output_price: 0.0
    - name: 01-ai/yi-34b-chat
      max_input_tokens: 4096
      input_price: 0.72
      output_price: 0.72
    - name: openai/gpt-3.5-turbo
      max_input_tokens: 16385
      input_price: 0.5
      output_price: 1.5
    - name: openai/gpt-4-turbo
      max_input_tokens: 128000
      input_price: 10
      output_price: 30
      supports_vision: true
    - name: openai/gpt-4-turbo-preview
      max_input_tokens: 128000
      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: openai/gpt-4
      max_input_tokens: 8192
      input_price: 30
      output_price: 60
    - name: openai/gpt-4-32k
      max_input_tokens: 32768
      input_price: 60
      output_price: 120
    - name: google/gemini-pro
      max_input_tokens: 91728
      input_price: 0.125
      output_price: 0.375
    - name: google/gemini-pro-vision
      max_input_tokens: 45875
      input_price: 0.125
      output_price: 0.375
      supports_vision: true
    - name: google/gemini-pro-1.5
      max_input_tokens: 2800000
      input_price: 2.5
      output_price: 7.5
      supports_vision: true
    - name: anthropic/claude-3-opus
      max_input_tokens: 200000
      input_price: 15
      output_price: 75
      supports_vision: true
    - name: anthropic/claude-3-sonnet
      max_input_tokens: 200000
      input_price: 3
      output_price: 15
      supports_vision: true
    - name: anthropic/claude-3-haiku
      max_input_tokens: 200000
      input_price: 0.25
      output_price: 1.25
      supports_vision: true
    - name: mistralai/mixtral-8x7b-instruct
      max_input_tokens: 32768
      input_price: 0.24
      output_price: 0.24
    - name: mistralai/mixtral-8x22b-instruct
      max_input_tokens: 65536
      input_price: 0.65
      output_price: 0.65
    - name: mistralai/mistral-small
      max_input_tokens: 32000
      input_price: 2
      output_price: 6
    - name: mistralai/mistral-large
      max_input_tokens: 32000
      input_price: 8
      output_price: 24
    - name: databricks/dbrx-instruct
      max_input_tokens: 32768
      input_price: 0.6
      output_price: 0.6
    - name: cohere/command-r
      max_input_tokens: 128000
      input_price: 0.5
      output_price: 1.5
    - name: cohere/command-r-plus
      max_input_tokens: 128000
      input_price: 3
      output_price: 15

- platform: octoai
  # docs:
  #   - https://octo.ai/docs/getting-started/inference-models
  #   - https://octo.ai/pricing/text-gen-solution/
  models:
    - name: meta-llama-3-8b-instruct
      max_input_tokens: 8192
      input_price: 0.13
      output_price: 0.13
    - name: meta-llama-3-70b-instruct
      max_input_tokens: 8192
      input_price: 0.86
      output_price: 0.86
    - name: mistral-7b-instruct
      max_input_tokens: 32768
      input_price: 0.13
      output_price: 0.13
    - name: mixtral-8x7b-instruct
      max_input_tokens: 32768
      input_price: 0.34
      output_price: 0.34
    - name: mixtral-8x22b-instruct
      max_input_tokens: 65536
      input_price: 0.86
      output_price: 0.86

- platform: together
  # docs:
  #   - https://docs.together.ai/docs/inference-models
  #   - https://www.together.ai/pricing
  models:
    - name: meta-llama/Llama-3-8b-chat-hf
      max_input_tokens: 8000
      input_price: 0.2
      output_price: 0.2
    - name: meta-llama/Llama-3-70b-chat-hf
      max_input_tokens: 8000
      input_price: 0.9
      output_price: 0.9
    - name: mistralai/Mistral-7B-Instruct-v0.2
      max_input_tokens: 32768
      input_price: 0.2
      output_price: 0.2
    - name: mistralai/Mixtral-8x7B-Instruct-v0.1
      max_input_tokens: 32768
      input_price: 0.9
      output_price: 0.9
    - name: mistralai/Mixtral-8x22B-Instruct-v0.1
      max_input_tokens: 65536
      input_price: 1.2
      output_price: 1.2
    - name: google/gemma-7b-it
      max_input_tokens: 8192
      input_price: 0.2
      output_price: 0.2
    - name: Qwen/Qwen1.5-72B-Chat
      max_input_tokens: 32768
      input_price: 0.9
      output_price: 0.9
    - name: databricks/dbrx-instruct
      max_input_tokens: 32768
      input_price: 1.2
      output_price: 1.2
    - name: zero-one-ai/Yi-34B-Chat
      max_input_tokens: 4096
      input_price: 0.8
      output_price: 0.8
    - name: allenai/OLMo-7B-Instruct
      max_input_tokens: 2048
      input_price: 0.2
      output_price: 0.2