Archives/aichat
2
0
Fork 0
mirror of https://github.com/sigoden/aichat synced 2024-11-16 06:15:26 +00:00
Code Issues Packages Projects Releases Wiki Activity
v0.20.0
aichat/models.yaml
sigoden 4384010e5b
refactor: update models.yaml (#772)
2024-08-01 07:39:08 +08:00

1241 lines
35 KiB
YAML
Raw Permalink Blame History

# notes:
# - do not submit pull requests to add new models; this list will be updated in batches with new releases.
- 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-4o
max_input_tokens: 128000
max_output_tokens: 4096
input_price: 5
output_price: 15
supports_vision: true
supports_function_calling: true
- name: gpt-4o-mini
max_input_tokens: 128000
max_output_tokens: 16384
input_price: 0.15
output_price: 0.6
supports_vision: true
supports_function_calling: true
- name: gpt-4-turbo
max_input_tokens: 128000
max_output_tokens: 4096
input_price: 10
output_price: 30
supports_vision: true
supports_function_calling: true
- name: gpt-3.5-turbo
max_input_tokens: 16385
max_output_tokens: 4096
input_price: 0.5
output_price: 1.5
supports_function_calling: true
- name: text-embedding-3-large
type: embedding
max_input_tokens: 8191
input_price: 0.13
output_vector_size: 3072
default_chunk_size: 3000
max_batch_size: 100
- name: text-embedding-3-small
type: embedding
max_input_tokens: 8191
input_price: 0.02
output_vector_size: 1536
default_chunk_size: 3000
max_batch_size: 100
- 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-1.5-pro-latest
max_input_tokens: 2097152
max_output_tokens: 8192
input_price: 3.5
output_price: 10.5
supports_vision: true
supports_function_calling: true
- name: gemini-1.5-flash-latest
max_input_tokens: 1048576
max_output_tokens: 8192
input_price: 0.35
output_price: 1.05
supports_vision: true
supports_function_calling: true
- name: gemini-1.0-pro-latest
max_input_tokens: 30720
max_output_tokens: 2048
input_price: 0.5
output_price: 1.5
supports_function_calling: true
- name: text-embedding-004
type: embedding
max_input_tokens: 2048
default_chunk_size: 1500
max_batch_size: 5
- 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-3-5-sonnet-20240620
max_input_tokens: 200000
max_output_tokens: 4096
require_max_tokens: true
input_price: 3
output_price: 15
supports_vision: true
supports_function_calling: true
- name: claude-3-opus-20240229
max_input_tokens: 200000
max_output_tokens: 4096
require_max_tokens: true
input_price: 15
output_price: 75
supports_vision: true
supports_function_calling: true
- name: claude-3-sonnet-20240229
max_input_tokens: 200000
max_output_tokens: 4096
require_max_tokens: true
input_price: 3
output_price: 15
supports_vision: true
supports_function_calling: true
- name: claude-3-haiku-20240307
max_input_tokens: 200000
max_output_tokens: 4096
require_max_tokens: true
input_price: 0.25
output_price: 1.25
supports_vision: true
supports_function_calling: 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: mistral-large-latest
max_input_tokens: 128000
input_price: 3
output_price: 9
supports_function_calling: true
- name: open-mistral-nemo
max_input_tokens: 128000
input_price: 0.3
output_price: 0.3
supports_function_calling: true
- name: codestral-latest
max_input_tokens: 32000
input_price: 1
output_price: 3
- name: open-codestral-mamba
max_input_tokens: 256000
input_price: 0.25
output_price: 0.25
- name: open-mixtral-8x22b
max_input_tokens: 64000
input_price: 2
output_price: 6
- name: open-mixtral-8x7b
max_input_tokens: 32000
input_price: 0.7
output_price: 0.7
- name: mistral-embed
type: embedding
input_price: 0.1
output_vector_size: 1024
max_input_tokens: 8092
default_chunk_size: 2000
- platform: cohere
# docs:
# - https://docs.cohere.com/docs/command-r
# - https://cohere.com/pricing
# - https://docs.cohere.com/reference/chat
models:
- name: command-r-plus
max_input_tokens: 128000
input_price: 3
output_price: 15
supports_function_calling: true
- name: command-r
max_input_tokens: 128000
input_price: 0.5
output_price: 1.5
supports_function_calling: true
- name: embed-english-v3.0
type: embedding
max_input_tokens: 512
input_price: 0.1
output_vector_size: 1024
default_chunk_size: 1000
max_batch_size: 96
- name: embed-multilingual-v3.0
type: embedding
max_input_tokens: 512
input_price: 0.1
output_vector_size: 1024
default_chunk_size: 1000
max_batch_size: 96
- name: rerank-english-v3.0
type: reranker
max_input_tokens: 4096
- name: rerank-multilingual-v3.0
type: reranker
max_input_tokens: 4096
- platform: perplexity
# docs:
# - https://docs.perplexity.ai/docs/model-cards
# - https://docs.perplexity.ai/docs/pricing
# - https://docs.perplexity.ai/reference/post_chat_completions
models:
- name: llama-3.1-sonar-large-128k-online
max_input_tokens: 127072
input_price: 1
output_price: 1
- name: llama-3.1-sonar-large-128k-chat
max_input_tokens: 131072
input_price: 1
output_price: 1
- name: llama-3.1-sonar-small-128k-online
max_input_tokens: 127072
input_price: 0.2
output_price: 0.2
- name: llama-3.1-sonar-small-128k-chat
max_input_tokens: 131072
input_price: 0.2
output_price: 0.2
- name: llama-3.1-70b-instruct
max_input_tokens: 131072
input_price: 1
output_price: 1
- name: llama-3.1-8b-instruct
max_input_tokens: 131072
input_price: 0.2
output_price: 0.2
- platform: groq
# docs:
# - https://console.groq.com/docs/models
# - https://wow.groq.com
# - https://console.groq.com/docs/text-chat
# notes:
# - all models are free with rate limits
models:
- name: llama3-70b-8192
max_input_tokens: 8192
input_price: 0.59
output_price: 0.79
supports_function_calling: true
- name: llama3-8b-8192
max_input_tokens: 8192
input_price: 0.05
output_price: 0.08
supports_function_calling: true
- name: llama3-groq-70b-8192-tool-use-preview
max_input_tokens: 8192
input_price: 0.89
output_price: 0.89
supports_function_calling: true
- name: llama3-groq-8b-8192-tool-use-preview
max_input_tokens: 8192
input_price: 0.19
output_price: 0.19
supports_function_calling: true
- name: mixtral-8x7b-32768
max_input_tokens: 32768
input_price: 0.24
output_price: 0.24
- name: gemma2-9b-it
max_input_tokens: 8192
input_price: 0.2
output_price: 0.2
supports_function_calling: true
- name: llama-3.1-405b-reasoning
max_input_tokens: 16384
- name: llama-3.1-70b-versatile
max_input_tokens: 8192
- name: llama-3.1-8b-instant
max_input_tokens: 8192
- platform: vertexai
# docs:
# - https://cloud.google.com/vertex-ai/generative-ai/docs/learn/models
# - https://cloud.google.com/vertex-ai/generative-ai/docs/model-garden/explore-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
models:
- name: gemini-1.5-pro-001
max_input_tokens: 2097152
max_output_tokens: 8192
input_price: 1.25
output_price: 3.75
supports_vision: true
supports_function_calling: true
- name: gemini-1.5-flash-001
max_input_tokens: 1000000
max_output_tokens: 8192
input_price: 0.125
output_price: 0.375
supports_vision: true
supports_function_calling: true
- name: gemini-1.0-pro-002
max_input_tokens: 24568
max_output_tokens: 8192
input_price: 0.125
output_price: 0.375
supports_function_calling: true
- name: claude-3-5-sonnet@20240620
max_input_tokens: 200000
max_output_tokens: 4096
require_max_tokens: true
input_price: 3
output_price: 15
supports_vision: true
supports_function_calling: true
- name: claude-3-opus@20240229
max_input_tokens: 200000
max_output_tokens: 4096
require_max_tokens: true
input_price: 15
output_price: 75
supports_vision: true
supports_function_calling: true
- name: claude-3-sonnet@20240229
max_input_tokens: 200000
max_output_tokens: 4096
require_max_tokens: true
input_price: 3
output_price: 15
supports_vision: true
supports_function_calling: true
- name: claude-3-haiku@20240307
max_input_tokens: 200000
max_output_tokens: 4096
require_max_tokens: true
input_price: 0.25
output_price: 1.25
supports_vision: true
supports_function_calling: true
- name: mistral-large@2407
max_input_tokens: 128000
input_price: 3
output_price: 9
supports_function_calling: true
- name: mistral-nemo@2407
max_input_tokens: 128000
input_price: 0.3
output_price: 0.3
supports_function_calling: true
- name: codestral@2405
max_input_tokens: 32000
input_price: 1
output_price: 3
- name: text-embedding-004
type: embedding
max_input_tokens: 3072
input_price: 0.025
output_vector_size: 768
default_chunk_size: 1500
max_batch_size: 5
- name: text-multilingual-embedding-002
type: embedding
max_input_tokens: 3072
input_price: 0.2
output_vector_size: 768
default_chunk_size: 1500
max_batch_size: 5
- platform: bedrock
# docs:
# - https://docs.aws.amazon.com/bedrock/latest/userguide/model-ids.html#model-ids-arns
# - https://aws.amazon.com/bedrock/pricing/
# - https://docs.aws.amazon.com/bedrock/latest/userguide/conversation-inference.html
# notes:
# - except for Claude, other models do not support streaming function calling
models:
- name: anthropic.claude-3-5-sonnet-20240620-v1:0
max_input_tokens: 200000
max_output_tokens: 4096
require_max_tokens: true
input_price: 3
output_price: 15
supports_vision: true
supports_function_calling: true
- name: anthropic.claude-3-opus-20240229-v1:0
max_input_tokens: 200000
max_output_tokens: 4096
require_max_tokens: true
input_price: 15
output_price: 75
supports_vision: true
supports_function_calling: true
- name: anthropic.claude-3-sonnet-20240229-v1:0
max_input_tokens: 200000
max_output_tokens: 4096
require_max_tokens: true
input_price: 3
output_price: 15
supports_vision: true
supports_function_calling: true
- name: anthropic.claude-3-haiku-20240307-v1:0
max_input_tokens: 200000
max_output_tokens: 4096
require_max_tokens: true
input_price: 0.25
output_price: 1.25
supports_vision: true
supports_function_calling: true
- name: meta.llama3-1-405b-instruct-v1:0
max_input_tokens: 128000
input_price: 5.32
output_price: 16
supports_function_calling: true
- name: meta.llama3-1-70b-instruct-v1:0
max_input_tokens: 128000
input_price: 2.65
output_price: 3.5
supports_function_calling: true
- name: meta.llama3-1-8b-instruct-v1:0
max_input_tokens: 128000
input_price: 0.3
output_price: 0.6
supports_function_calling: true
- name: meta.llama3-70b-instruct-v1:0
max_input_tokens: 8192
input_price: 2.65
output_price: 3.5
- name: meta.llama3-8b-instruct-v1:0
max_input_tokens: 8192
input_price: 0.3
output_price: 0.6
- name: mistral.mistral-large-2407-v1:0
max_input_tokens: 128000
input_price: 3
output_price: 9
supports_function_calling: true
- name: cohere.command-r-plus-v1:0
max_input_tokens: 128000
input_price: 3
output_price: 15
supports_function_calling: true
- name: cohere.command-r-v1:0
max_input_tokens: 128000
input_price: 0.5
output_price: 1.5
supports_function_calling: true
- name: cohere.embed-english-v3
type: embedding
max_input_tokens: 512
input_price: 0.1
output_vector_size: 1024
default_chunk_size: 1000
max_batch_size: 96
- name: cohere.embed-multilingual-v3
type: embedding
max_input_tokens: 512
input_price: 0.1
output_vector_size: 1024
default_chunk_size: 1000
max_batch_size: 96
- platform: cloudflare
# docs:
# - https://developers.cloudflare.com/workers-ai/models/
models:
- name: '@cf/meta/llama-3.1-8b-instruct'
max_input_tokens: 6144
max_output_tokens: 2048
require_max_tokens: true
input_price: 0
output_price: 0
- name: '@cf/meta/llama-3-8b-instruct'
max_input_tokens: 6144
max_output_tokens: 2048
require_max_tokens: true
input_price: 0
output_price: 0
- name: '@cf/baai/bge-large-en-v1.5'
type: embedding
max_input_tokens: 512
input_price: 0
output_vector_size: 1024
default_chunk_size: 1000
max_batch_size: 100
- platform: replicate
# docs:
# - https://replicate.com/explore
# - https://replicate.com/pricing
# - https://replicate.com/docs/reference/http
models:
- name: meta/meta-llama-3.1-405b-instruct
max_input_tokens: 128000
max_output_tokens: 4096
input_price: 9.5
output_price: 9.5
- name: meta/meta-llama-3-70b-instruct
max_input_tokens: 8192
max_output_tokens: 4096
require_max_tokens: true
input_price: 0.65
output_price: 2.75
- name: meta/meta-llama-3-8b-instruct
max_input_tokens: 8192
max_output_tokens: 4096
require_max_tokens: true
input_price: 0.05
output_price: 0.25
- name: mistralai/mixtral-8x7b-instruct-v0.1
max_input_tokens: 32000
max_output_tokens: 8192
require_max_tokens: true
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
models:
- name: ernie-4.0-turbo-8k-preview
max_input_tokens: 8192
input_price: 4.2
output_price: 8.4
supports_function_calling: true
- name: ernie-4.0-8k-preview
max_input_tokens: 8192
input_price: 16.8
output_price: 16.8
supports_function_calling: true
- name: ernie-3.5-8k-preview
max_input_tokens: 8192
input_price: 1.68
output_price: 1.68
supports_function_calling: true
- name: ernie-speed-128k
max_input_tokens: 128000
input_price: 0
output_price: 0
- name: bge_large_zh
type: embedding
max_input_tokens: 512
input_price: 0.28
output_vector_size: 1024
default_chunk_size: 1000
max_batch_size: 16
- name: bge_large_en
type: embedding
max_input_tokens: 512
input_price: 0.28
output_vector_size: 1024
default_chunk_size: 1000
max_batch_size: 16
- name: bce_reranker_base
type: reranker
max_input_tokens: 1024
input_price: 0.28
- platform: qianwen
# docs:
# - https://help.aliyun.com/zh/dashscope/developer-reference/model-introduction
# - https://help.aliyun.com/zh/dashscope/developer-reference/tongyi-thousand-questions-metering-and-billing
# - https://help.aliyun.com/zh/dashscope/developer-reference/use-qwen-by-api
models:
- name: qwen-max
max_input_tokens: 8000
input_price: 5.6
output_price: 16.8
supports_function_calling: true
- name: qwen-max-longcontext
input_price: 5.6
output_price: 16.8
max_input_tokens: 30000
supports_function_calling: true
- name: qwen-plus
max_input_tokens: 32000
input_price: 0.56
output_price: 1.68
supports_function_calling: true
- name: qwen-turbo
max_input_tokens: 8000
input_price: 0.28
output_price: 0.84
supports_function_calling: true
- name: qwen-long
max_input_tokens: 1000000
input_price: 0.07
output_price: 0.28
- name: qwen-vl-max
input_price: 2.8
output_price: 2.8
supports_vision: true
- name: qwen-vl-plus
input_price: 1.12
output_price: 1.12
supports_vision: true
- name: text-embedding-v2
type: embedding
max_input_tokens: 2048
input_price: 0.1
output_vector_size: 1536
default_chunk_size: 1500
max_batch_size: 25
- platform: moonshot
# docs:
# - https://platform.moonshot.cn/docs/intro
# - https://platform.moonshot.cn/docs/pricing
# - https://platform.moonshot.cn/docs/api-reference
models:
- name: moonshot-v1-8k
max_input_tokens: 8000
input_price: 1.68
output_price: 1.68
supports_function_calling: true
- name: moonshot-v1-32k
max_input_tokens: 32000
input_price: 3.36
output_price: 3.36
supports_function_calling: true
- name: moonshot-v1-128k
max_input_tokens: 128000
input_price: 8.4
output_price: 8.4
supports_function_calling: true
- platform: deepseek
# docs:
# - https://platform.deepseek.com/api-docs/
# - https://platform.deepseek.com/api-docs/pricing
models:
- name: deepseek-chat
max_input_tokens: 32768
input_price: 0.14
output_price: 0.28
supports_function_calling: true
- name: deepseek-coder
max_input_tokens: 32768
input_price: 0.14
output_price: 0.28
supports_function_calling: true
- platform: zhipuai
# docs:
# - https://open.bigmodel.cn/dev/howuse/model
# - https://open.bigmodel.cn/pricing
models:
- name: glm-4-0520
max_input_tokens: 128000
input_price: 14
output_price: 14
supports_function_calling: true
- name: glm-4-alltools
max_input_tokens: 2048
input_price: 14
output_price: 14
supports_function_calling: true
- name: glm-4-airx
max_input_tokens: 8092
input_price: 1.4
output_price: 1.4
supports_function_calling: true
- name: glm-4-air
max_input_tokens: 128000
input_price: 0.14
output_price: 0.14
supports_function_calling: true
- name: glm-4-flash
max_input_tokens: 128000
input_price: 0.014
output_price: 0.014
supports_function_calling: true
- name: glm-4v
max_input_tokens: 2048
input_price: 7
output_price: 7
supports_vision: true
- name: embedding-2
type: embedding
max_input_tokens: 512
input_price: 0.07
output_vector_size: 1024
default_chunk_size: 1000
- platform: lingyiwanwu
# docs:
# - https://platform.lingyiwanwu.com/docs#%E6%A8%A1%E5%9E%8B
# - https://platform.lingyiwanwu.com/docs#%E8%AE%A1%E8%B4%B9%E5%8D%95%E5%85%83
models:
- name: yi-large
max_input_tokens: 32768
input_price: 2.8
output_price: 2.8
- name: yi-large-fc
max_input_tokens: 32768
input_price: 2.8
output_price: 2.8
supports_function_calling: true
- name: yi-large-rag
max_input_tokens: 16384
input_price: 3.5
output_price: 3.5
- name: yi-large-turbo
max_input_tokens: 16384
input_price: 1.68
output_price: 1.68
- name: yi-medium-200k
max_input_tokens: 200000
input_price: 1.68
output_price: 1.68
- name: yi-vision
max_input_tokens: 4096
input_price: 0.84
output_price: 0.84
supports_vision: true
- name: yi-medium
max_input_tokens: 16384
input_price: 0.35
output_price: 0.35
- name: yi-spark
max_input_tokens: 16384
input_price: 0.14
output_price: 0.14
- platform: deepinfra
# docs:
# - https://deepinfra.com/models
# - https://deepinfra.com/pricing
models:
- name: meta-llama/Meta-Llama-3.1-70B-Instruct
max_input_tokens: 128000
input_price: 0.52
output_price: 0.75
- name: meta-llama/Meta-Llama-3.1-8B-Instruct
max_input_tokens: 128000
input_price: 0.09
output_price: 0.09
- name: meta-llama/Meta-Llama-3-70B-Instruct
max_input_tokens: 8192
input_price: 0.59
output_price: 0.79
supports_function_calling: true
- name: meta-llama/Meta-Llama-3-8B-Instruct
max_input_tokens: 8192
input_price: 0.08
output_price: 0.08
supports_function_calling: true
- name: mistralai/Mixtral-8x22B-Instruct-v0.1
max_input_tokens: 65536
input_price: 0.65
output_price: 0.65
supports_function_calling: true
- name: mistralai/Mixtral-8x7B-Instruct-v0.1
max_input_tokens: 32768
input_price: 0.24
output_price: 0.24
supports_function_calling: true
- name: google/gemma-2-27b-it
max_input_tokens: 8192
input_price: 0.27
output_price: 0.27
- name: google/gemma-2-9b-it
max_input_tokens: 8192
input_price: 0.09
output_price: 0.09
- name: Qwen/Qwen2-72B-Instruct
max_input_tokens: 32768
input_price: 0.59
output_price: 0.79
supports_function_calling: true
- name: BAAI/bge-large-en-v1.5
type: embedding
max_input_tokens: 512
input_price: 0.01
output_vector_size: 1024
default_chunk_size: 1000
max_batch_size: 100
- name: BAAI/bge-m3
type: embedding
max_input_tokens: 8192
input_price: 0.01
output_vector_size: 1024
default_chunk_size: 2000
max_batch_size: 100
- name: intfloat/e5-large-v2
type: embedding
max_input_tokens: 512
input_price: 0.01
output_vector_size: 1024
default_chunk_size: 1000
max_batch_size: 100
- name: intfloat/multilingual-e5-large
type: embedding
max_input_tokens: 512
input_price: 0.01
output_vector_size: 1024
default_chunk_size: 1000
max_batch_size: 100
- name: thenlper/gte-large
type: embedding
max_input_tokens: 512
input_price: 0.01
output_vector_size: 1024
default_chunk_size: 1000
max_batch_size: 100
- platform: fireworks
# docs:
# - https://fireworks.ai/models
# - https://fireworks.ai/pricing
models:
- name: accounts/fireworks/models/llama-v3p1-405b-instruct
max_input_tokens: 131072
input_price: 3
output_price: 3
- name: accounts/fireworks/models/llama-v3p1-70b-instruct
max_input_tokens: 131072
input_price: 0.9
output_price: 0.9
- name: accounts/fireworks/models/llama-v3p1-8b-instruct
max_input_tokens: 131072
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/llama-v3-8b-instruct
max_input_tokens: 8192
input_price: 0.2
output_price: 0.2
- name: accounts/fireworks/models/mixtral-8x22b-instruct
max_input_tokens: 65536
input_price: 0.9
output_price: 0.9
- name: accounts/fireworks/models/mixtral-8x7b-instruct
max_input_tokens: 32768
input_price: 0.5
output_price: 0.5
- name: accounts/fireworks/models/gemma2-9b-it
max_input_tokens: 8192
input_price: 0.2
output_price: 0.2
- name: accounts/fireworks/models/deepseek-coder-v2-instruct
max_input_tokens: 131072
input_price: 2.7
output_price: 2.7
- name: accounts/fireworks/models/deepseek-coder-v2-lite-instruct
max_input_tokens: 163840
input_price: 0.2
output_price: 0.2
- name: accounts/fireworks/models/phi-3-vision-128k-instruct
max_input_tokens: 131072
input_price: 0.2
output_price: 0.2
supports_vision: true
- name: accounts/fireworks/models/firellava-13b
max_input_tokens: 4096
input_price: 0.2
output_price: 0.2
supports_vision: true
- name: accounts/fireworks/models/firefunction-v2
max_input_tokens: 32768
input_price: 0.2
output_price: 0.2
supports_function_calling: true
- name: nomic-ai/nomic-embed-text-v1.5
type: embedding
max_input_tokens: 8192
input_price: 0.008
output_vector_size: 768
default_chunk_size: 1500
max_batch_size: 100
- name: WhereIsAI/UAE-Large-V1
type: embedding
max_input_tokens: 512
input_price: 0.016
output_vector_size: 1024
default_chunk_size: 1000
max_batch_size: 100
- name: thenlper/gte-large
type: embedding
max_input_tokens: 512
input_price: 0.016
output_vector_size: 1024
default_chunk_size: 1000
max_batch_size: 100
- platform: openrouter
# docs:
# - https://openrouter.ai/docs#models
models:
- name: meta-llama/llama-3.1-405b-instruct
max_input_tokens: 131072
input_price: 3
output_price: 3
- name: meta-llama/llama-3.1-70b-instruct
max_input_tokens: 131072
input_price: 0.75
output_price: 0.75
- name: meta-llama/llama-3.1-8b-instruct
max_input_tokens: 131072
input_price: 0.09
output_price: 0.09
- name: meta-llama/llama-3-70b-instruct
max_input_tokens: 8192
input_price: 0.59
output_price: 0.79
- name: meta-llama/llama-3-8b-instruct
max_input_tokens: 8192
input_price: 0.07
output_price: 0.07
- name: microsoft/phi-3-medium-128k-instruct
max_input_tokens: 128000
input_price: 1
output_price: 1
- name: microsoft/phi-3-mini-128k-instruct
max_input_tokens: 128000
input_price: 0.1
output_price: 0.1
- name: qwen/qwen-2-72b-instruct
max_input_tokens: 32768
input_price: 0.9
output_price: 0.9
- name: openai/gpt-4o
max_input_tokens: 128000
input_price: 5
output_price: 15
supports_vision: true
supports_function_calling: true
- name: openai/gpt-4o-mini
max_input_tokens: 128000
input_price: 0.15
output_price: 0.6
supports_vision: true
supports_function_calling: true
- name: openai/gpt-4-turbo
max_input_tokens: 128000
input_price: 10
output_price: 30
supports_vision: true
supports_function_calling: true
- name: openai/gpt-3.5-turbo
max_input_tokens: 16385
input_price: 0.5
output_price: 1.5
supports_function_calling: true
- name: google/gemini-pro-1.5
max_input_tokens: 2800000
input_price: 2.5
output_price: 7.5
supports_vision: true
supports_function_calling: true
- name: google/gemini-flash-1.5
max_input_tokens: 2800000
input_price: 0.25
output_price: 0.75
supports_vision: true
supports_function_calling: true
- name: google/gemini-pro
max_input_tokens: 91728
input_price: 0.125
output_price: 0.375
supports_function_calling: true
- name: google/gemma-2-9b-it
max_input_tokens: 2800000
input_price: 0.2
output_price: 0.2
- name: anthropic/claude-3.5-sonnet
max_input_tokens: 200000
max_output_tokens: 4096
require_max_tokens: true
input_price: 3
output_price: 15
supports_vision: true
supports_function_calling: true
- name: anthropic/claude-3-opus
max_input_tokens: 200000
max_output_tokens: 4096
require_max_tokens: true
input_price: 15
output_price: 75
supports_vision: true
supports_function_calling: true
- name: anthropic/claude-3-sonnet
max_input_tokens: 200000
max_output_tokens: 4096
require_max_tokens: true
input_price: 3
output_price: 15
supports_vision: true
supports_function_calling: true
- name: anthropic/claude-3-haiku
max_input_tokens: 200000
max_output_tokens: 4096
require_max_tokens: true
input_price: 0.25
output_price: 1.25
supports_vision: true
supports_function_calling: true
- name: mistralai/mistral-large
max_input_tokens: 128000
input_price: 3
output_price: 9
supports_function_calling: true
- name: mistralai/mistral-nemo
max_input_tokens: 128000
input_price: 0.18
output_price: 0.18
supports_function_calling: true
- name: mistralai/codestral-mamba
max_input_tokens: 256000
input_price: 0.25
output_price: 0.25
- name: mistralai/mixtral-8x22b-instruct
max_input_tokens: 65536
input_price: 0.65
output_price: 0.65
- name: mistralai/mixtral-8x7b-instruct
max_input_tokens: 32768
input_price: 0.24
output_price: 0.24
- name: cohere/command-r-plus
max_input_tokens: 128000
input_price: 3
output_price: 15
supports_function_calling: true
- name: cohere/command-r
max_input_tokens: 128000
input_price: 0.5
output_price: 1.5
supports_function_calling: true
- name: deepseek/deepseek-chat
max_input_tokens: 32768
input_price: 0.14
output_price: 0.28
- name: deepseek/deepseek-coder
max_input_tokens: 32768
input_price: 0.14
output_price: 0.28
- name: perplexity/llama-3.1-sonar-large-128k-online
max_input_tokens: 131072
input_price: 1
output_price: 1
- name: perplexity/llama-3.1-sonar-large-128k-chat
max_input_tokens: 131072
input_price: 1
output_price: 1
- name: perplexity/llama-3.1-sonar-small-128k-online
max_input_tokens: 131072
input_price: 0.2
output_price: 0.2
- name: perplexity/llama-3.1-sonar-small-128k-chat
max_input_tokens: 131072
input_price: 0.2
output_price: 0.2
- name: 01-ai/yi-large
max_input_tokens: 32768
input_price: 3
output_price: 3
- platform: octoai
# docs:
# - https://octo.ai/docs/getting-started/inference-models
# - https://octo.ai/docs/getting-started/pricing-and-billing
models:
- name: meta-llama-3.1-405b-instruct
max_input_tokens: 131072
input_price: 3
output_price: 9
- name: meta-llama-3.1-70b-instruct
max_input_tokens: 131072
input_price: 0.9
output_price: 0.9
- name: meta-llama-3.1-8b-instruct
max_input_tokens: 131072
input_price: 0.15
output_price: 0.15
- name: meta-llama-3-70b-instruct
max_input_tokens: 8192
input_price: 0.9
output_price: 0.9
- name: meta-llama-3-8b-instruct
max_input_tokens: 8192
input_price: 0.15
output_price: 0.15
- name: mixtral-8x22b-instruct
max_input_tokens: 65536
input_price: 1.2
output_price: 1.2
- name: mixtral-8x7b-instruct
max_input_tokens: 32768
input_price: 0.45
output_price: 0.45
- name: thenlper/gte-large
type: embedding
max_input_tokens: 512
input_price: 0.05
output_vector_size: 1024
default_chunk_size: 1000
max_batch_size: 100
- platform: together
# docs:
# - https://docs.together.ai/docs/inference-models
# - https://docs.together.ai/docs/embedding-models
# - https://www.together.ai/pricing
models:
- name: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
max_input_tokens: 32768
input_price: 5
output_price: 5
- name: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
max_input_tokens: 8192
input_price: 0.88
output_price: 0.88
- name: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
max_input_tokens: 8192
input_price: 0.18
output_price: 0.18
- name: meta-llama/Meta-Llama-3-70B-Instruct-Turbo
max_input_tokens: 8192
input_price: 0.88
output_price: 0.88
- name: meta-llama/Meta-Llama-3-8B-Instruct-Turbo
max_input_tokens: 8192
input_price: 0.18
output_price: 0.18
- name: mistralai/Mixtral-8x22B-Instruct-v0.1
max_input_tokens: 65536
input_price: 1.2
output_price: 1.2
- name: mistralai/Mixtral-8x7B-Instruct-v0.1
max_input_tokens: 32768
input_price: 0.9
output_price: 0.9
- name: Qwen/Qwen2-72B-Instruct
max_input_tokens: 32768
input_price: 0.9
output_price: 0.9
- name: WhereIsAI/UAE-Large-V1
type: embedding
max_input_tokens: 512
input_price: 0.016
output_vector_size: 1024
default_chunk_size: 1000
max_batch_size: 100
- name: BAAI/bge-large-en-v1.5
type: embedding
max_input_tokens: 512
input_price: 0.016
output_vector_size: 1024
default_chunk_size: 1000
max_batch_size: 100
- platform: jina
# docs:
# - https://jina.ai/
# - https://api.jina.ai/redoc
models:
- name: jina-clip-v1
type: embedding
max_input_tokens: 8192
input_price: 0.02
output_vector_size: 768
default_chunk_size: 1500
max_batch_size: 100
- name: jina-embeddings-v2-base-en
type: embedding
max_input_tokens: 8192
input_price: 0.02
output_vector_size: 768
default_chunk_size: 1500
max_batch_size: 100
- name: jina-embeddings-v2-base-zh
type: embedding
max_input_tokens: 8192
input_price: 0.02
output_vector_size: 768
default_chunk_size: 1500
max_batch_size: 100
- name: jina-colbert-v1-en
type: embedding
max_input_tokens: 8192
input_price: 0.02
output_vector_size: 768
default_chunk_size: 1500
max_batch_size: 100
- name: jina-reranker-v2-base-multilingual
type: reranker
max_input_tokens: 1024
input_price: 0.02
- name: jina-reranker-v1-base-en
type: reranker
max_input_tokens: 8192
input_price: 0.02
- name: jina-colbert-v1-en
type: reranker
max_input_tokens: 8192
input_price: 0.02
- platform: voyageai
# docs:
# - https://docs.voyageai.com/docs/embeddings
# - https://docs.voyageai.com/docs/pricing
# - https://docs.voyageai.com/reference/embeddings-api
models:
- name: voyage-large-2-instruct
type: embedding
max_input_tokens: 16000
input_price: 0.12
output_vector_size: 1024
default_chunk_size: 2000
max_batch_size: 128
- name: voyage-large-2
type: embedding
max_input_tokens: 16000
input_price: 0.12
output_vector_size: 1536
default_chunk_size: 3000
max_batch_size: 128
- name: voyage-multilingual-2
type: embedding
max_input_tokens: 32000
input_price: 0.12
output_vector_size: 1024
default_chunk_size: 2000
max_batch_size: 128
- name: voyage-code-2
type: embedding
max_input_tokens: 16000
input_price: 0.12
output_vector_size: 1536
default_chunk_size: 3000
max_batch_size: 128
- name: rerank-1
type: reranker
max_input_tokens: 8000
input_price: 0.05
Reference in New Issue View Git Blame Copy Permalink