|
|
|
@ -133,30 +133,14 @@
|
|
|
|
|
# notes:
|
|
|
|
|
# - unable to get max_output_tokens info
|
|
|
|
|
models:
|
|
|
|
|
- name: open-mistral-nemo-2407
|
|
|
|
|
max_input_tokens: 128000
|
|
|
|
|
input_price: 0.3
|
|
|
|
|
output_price: 0.3
|
|
|
|
|
- name: open-mistral-7b
|
|
|
|
|
max_input_tokens: 32000
|
|
|
|
|
input_price: 0.25
|
|
|
|
|
output_price: 0.25
|
|
|
|
|
- name: open-mixtral-8x7b
|
|
|
|
|
- name: mistral-large-latest
|
|
|
|
|
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
|
|
|
|
|
input_price: 4
|
|
|
|
|
output_price: 12
|
|
|
|
|
- name: mistral-small-latest
|
|
|
|
|
max_input_tokens: 32000
|
|
|
|
|
input_price: 1
|
|
|
|
|
output_price: 3
|
|
|
|
|
- name: mistral-large-latest
|
|
|
|
|
max_input_tokens: 32000
|
|
|
|
|
input_price: 4
|
|
|
|
|
output_price: 12
|
|
|
|
|
- name: codestral-latest
|
|
|
|
|
max_input_tokens: 32000
|
|
|
|
|
input_price: 1
|
|
|
|
@ -165,6 +149,19 @@
|
|
|
|
|
max_input_tokens: 256000
|
|
|
|
|
input_price: 0.25
|
|
|
|
|
output_price: 0.25
|
|
|
|
|
- name: open-mistral-nemo
|
|
|
|
|
max_input_tokens: 128000
|
|
|
|
|
input_price: 0.3
|
|
|
|
|
output_price: 0.3
|
|
|
|
|
supports_function_calling: true
|
|
|
|
|
- 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
|
|
|
|
@ -178,16 +175,16 @@
|
|
|
|
|
# - https://cohere.com/pricing
|
|
|
|
|
# - https://docs.cohere.com/reference/chat
|
|
|
|
|
models:
|
|
|
|
|
- name: command-r
|
|
|
|
|
max_input_tokens: 128000
|
|
|
|
|
input_price: 0.5
|
|
|
|
|
output_price: 1.5
|
|
|
|
|
supports_function_calling: true
|
|
|
|
|
- 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
|
|
|
|
@ -215,30 +212,22 @@
|
|
|
|
|
# - https://docs.perplexity.ai/docs/pricing
|
|
|
|
|
# - https://docs.perplexity.ai/reference/post_chat_completions
|
|
|
|
|
models:
|
|
|
|
|
- name: llama-3-sonar-small-32k-chat
|
|
|
|
|
max_input_tokens: 32768
|
|
|
|
|
input_price: 0.2
|
|
|
|
|
output_price: 0.2
|
|
|
|
|
- name: llama-3-sonar-small-32k-online
|
|
|
|
|
max_input_tokens: 28000
|
|
|
|
|
input_price: 0.2
|
|
|
|
|
output_price: 0.2
|
|
|
|
|
- name: llama-3-sonar-large-32k-chat
|
|
|
|
|
max_input_tokens: 32768
|
|
|
|
|
input_price: 1
|
|
|
|
|
output_price: 1
|
|
|
|
|
- name: llama-3-sonar-large-32k-online
|
|
|
|
|
max_input_tokens: 28000
|
|
|
|
|
input_price: 1
|
|
|
|
|
output_price: 1
|
|
|
|
|
- name: llama-3-8b-instruct
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
input_price: 0.2
|
|
|
|
|
output_price: 0.2
|
|
|
|
|
- name: llama-3-70b-instruct
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
input_price: 1
|
|
|
|
|
output_price: 1
|
|
|
|
|
- name: llama-3-8b-instruct
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
input_price: 0.2
|
|
|
|
|
output_price: 0.2
|
|
|
|
|
- name: mixtral-8x7b-instruct
|
|
|
|
|
max_input_tokens: 16384
|
|
|
|
|
input_price: 0.6
|
|
|
|
@ -252,32 +241,41 @@
|
|
|
|
|
# notes:
|
|
|
|
|
# - all models are free with rate limits
|
|
|
|
|
models:
|
|
|
|
|
- name: llama3-8b-8192
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
input_price: 0
|
|
|
|
|
output_price: 0
|
|
|
|
|
- name: llama3-70b-8192
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
input_price: 0
|
|
|
|
|
output_price: 0
|
|
|
|
|
- name: llama3-groq-8b-8192-tool-use-preview
|
|
|
|
|
input_price: 0.59
|
|
|
|
|
output_price: 0.79
|
|
|
|
|
supports_function_calling: true
|
|
|
|
|
- name: llama3-8b-8192
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
input_price: 0
|
|
|
|
|
output_price: 0
|
|
|
|
|
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
|
|
|
|
|
output_price: 0
|
|
|
|
|
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
|
|
|
|
|
output_price: 0
|
|
|
|
|
input_price: 0.24
|
|
|
|
|
output_price: 0.24
|
|
|
|
|
- name: gemma2-9b-it
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
input_price: 0
|
|
|
|
|
output_price: 0
|
|
|
|
|
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:
|
|
|
|
@ -307,13 +305,6 @@
|
|
|
|
|
input_price: 0.125
|
|
|
|
|
output_price: 0.375
|
|
|
|
|
supports_function_calling: true
|
|
|
|
|
- name: textembedding-gecko@003
|
|
|
|
|
type: embedding
|
|
|
|
|
max_input_tokens: 3072
|
|
|
|
|
input_price: 0.025
|
|
|
|
|
output_vector_size: 2048
|
|
|
|
|
default_chunk_size: 3000
|
|
|
|
|
max_batch_size: 5
|
|
|
|
|
- name: text-embedding-004
|
|
|
|
|
type: embedding
|
|
|
|
|
max_input_tokens: 3072
|
|
|
|
@ -407,11 +398,21 @@
|
|
|
|
|
output_price: 1.25
|
|
|
|
|
supports_vision: true
|
|
|
|
|
supports_function_calling: true
|
|
|
|
|
- name: meta.llama3-8b-instruct-v1:0
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
- name: meta.llama3-1-405b-instruct-v1:0
|
|
|
|
|
max_input_tokens: 128000
|
|
|
|
|
max_output_tokens: 2048
|
|
|
|
|
require_max_tokens: true
|
|
|
|
|
- name: meta.llama3-1-70b-instruct-v1:0
|
|
|
|
|
max_input_tokens: 128000
|
|
|
|
|
max_output_tokens: 2048
|
|
|
|
|
require_max_tokens: true
|
|
|
|
|
input_price: 0.4
|
|
|
|
|
input_price: 2.65
|
|
|
|
|
output_price: 3.5
|
|
|
|
|
- name: meta.llama3-1-8b-instruct-v1:0
|
|
|
|
|
max_input_tokens: 128000
|
|
|
|
|
max_output_tokens: 2048
|
|
|
|
|
require_max_tokens: true
|
|
|
|
|
input_price: 0.3
|
|
|
|
|
output_price: 0.6
|
|
|
|
|
- name: meta.llama3-70b-instruct-v1:0
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
@ -419,49 +420,36 @@
|
|
|
|
|
require_max_tokens: true
|
|
|
|
|
input_price: 2.65
|
|
|
|
|
output_price: 3.5
|
|
|
|
|
- name: mistral.mistral-7b-instruct-v0:2
|
|
|
|
|
- name: meta.llama3-8b-instruct-v1:0
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
max_output_tokens: 2048
|
|
|
|
|
require_max_tokens: true
|
|
|
|
|
input_price: 0.3
|
|
|
|
|
output_price: 0.6
|
|
|
|
|
- name: mistral.mistral-large-2402-v1:0
|
|
|
|
|
max_input_tokens: 32000
|
|
|
|
|
max_output_tokens: 8192
|
|
|
|
|
require_max_tokens: true
|
|
|
|
|
input_price: 0.15
|
|
|
|
|
output_price: 0.2
|
|
|
|
|
input_price: 8
|
|
|
|
|
output_price: 2.4
|
|
|
|
|
- name: mistral.mixtral-8x7b-instruct-v0:1
|
|
|
|
|
max_input_tokens: 32000
|
|
|
|
|
max_output_tokens: 8192
|
|
|
|
|
require_max_tokens: true
|
|
|
|
|
input_price: 0.45
|
|
|
|
|
output_price: 0.7
|
|
|
|
|
- name: mistral.mistral-large-2402-v1:0
|
|
|
|
|
max_input_tokens: 32000
|
|
|
|
|
max_output_tokens: 8192
|
|
|
|
|
require_max_tokens: true
|
|
|
|
|
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/
|
|
|
|
|
models:
|
|
|
|
|
- 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: '@hf/mistral/mistral-7b-instruct-v0.2'
|
|
|
|
|
max_input_tokens: 6144
|
|
|
|
|
max_output_tokens: 2048
|
|
|
|
|
require_max_tokens: true
|
|
|
|
|
input_price: 0
|
|
|
|
|
output_price: 0
|
|
|
|
|
- name: '@cf/qwen/qwen1.5-14b-chat-awq'
|
|
|
|
|
- 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/google/gemma-7b-it'
|
|
|
|
|
- name: '@cf/meta/llama-3-8b-instruct'
|
|
|
|
|
max_input_tokens: 6144
|
|
|
|
|
max_output_tokens: 2048
|
|
|
|
|
require_max_tokens: true
|
|
|
|
@ -481,6 +469,11 @@
|
|
|
|
|
# - 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
|
|
|
|
@ -493,12 +486,6 @@
|
|
|
|
|
require_max_tokens: true
|
|
|
|
|
input_price: 0.05
|
|
|
|
|
output_price: 0.25
|
|
|
|
|
- name: mistralai/mistral-7b-instruct-v0.2
|
|
|
|
|
max_input_tokens: 32000
|
|
|
|
|
max_output_tokens: 8192
|
|
|
|
|
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
|
|
|
|
@ -711,42 +698,47 @@
|
|
|
|
|
# - 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
|
|
|
|
|
supports_function_calling: true
|
|
|
|
|
- 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: mistralai/Mistral-7B-Instruct-v0.3
|
|
|
|
|
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: 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: google/gemma-1.1-7b-it
|
|
|
|
|
- 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: 0.07
|
|
|
|
|
output_price: 0.07
|
|
|
|
|
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
|
|
|
|
|
- name: microsoft/Phi-3-medium-4k-instruct
|
|
|
|
|
max_input_tokens: 4096
|
|
|
|
|
input_price: 0.14
|
|
|
|
|
output_price: 0.14
|
|
|
|
|
supports_function_calling: true
|
|
|
|
|
- name: BAAI/bge-large-en-v1.5
|
|
|
|
|
type: embedding
|
|
|
|
|
max_input_tokens: 512
|
|
|
|
@ -788,53 +780,57 @@
|
|
|
|
|
# - https://fireworks.ai/models
|
|
|
|
|
# - https://fireworks.ai/pricing
|
|
|
|
|
models:
|
|
|
|
|
- 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: accounts/fireworks/models/llama-v3-8b-instruct
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
- 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/mistral-7b-instruct-v3
|
|
|
|
|
max_input_tokens: 32768
|
|
|
|
|
- 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/mixtral-8x22b-instruct
|
|
|
|
|
max_input_tokens: 65536
|
|
|
|
|
- name: accounts/fireworks/models/qwen2-72b-instruct
|
|
|
|
|
max_input_tokens: 32768
|
|
|
|
|
input_price: 0.9
|
|
|
|
|
output_price: 0.9
|
|
|
|
|
- name: accounts/fireworks/models/gemma2-9b-it
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
input_price: 0.2
|
|
|
|
|
output_price: 0.2
|
|
|
|
|
- name: accounts/fireworks/models/qwen2-72b-instruct
|
|
|
|
|
max_input_tokens: 32768
|
|
|
|
|
input_price: 0.9
|
|
|
|
|
output_price: 0.9
|
|
|
|
|
- name: accounts/fireworks/models/phi-3-mini-128k-instruct
|
|
|
|
|
- name: accounts/fireworks/models/phi-3-vision-128k-instruct
|
|
|
|
|
max_input_tokens: 131072
|
|
|
|
|
input_price: 0.2
|
|
|
|
|
output_price: 0.2
|
|
|
|
|
- name: accounts/fireworks/models/phi-3-vision-128k-instruct
|
|
|
|
|
max_input_tokens: 131072
|
|
|
|
|
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
|
|
|
|
@ -861,26 +857,34 @@
|
|
|
|
|
# docs:
|
|
|
|
|
# - https://openrouter.ai/docs#models
|
|
|
|
|
models:
|
|
|
|
|
- name: meta-llama/llama-3-8b-instruct
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
input_price: 0.07
|
|
|
|
|
output_price: 0.07
|
|
|
|
|
- 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: microsoft/phi-3-mini-128k-instruct
|
|
|
|
|
max_input_tokens: 128000
|
|
|
|
|
input_price: 0.1
|
|
|
|
|
output_price: 0.1
|
|
|
|
|
- name: microsoft/phi-3-medium-4k-instruct
|
|
|
|
|
max_input_tokens: 4000
|
|
|
|
|
input_price: 0.14
|
|
|
|
|
output_price: 0.14
|
|
|
|
|
- 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
|
|
|
|
@ -961,36 +965,41 @@
|
|
|
|
|
output_price: 1.25
|
|
|
|
|
supports_vision: true
|
|
|
|
|
supports_function_calling: true
|
|
|
|
|
- name: mistralai/mistral-7b-instruct-v0.3
|
|
|
|
|
max_input_tokens: 32768
|
|
|
|
|
input_price: 0.07
|
|
|
|
|
output_price: 0.07
|
|
|
|
|
- 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: cohere/command-r
|
|
|
|
|
- name: mistralai/mistral-small
|
|
|
|
|
max_input_tokens: 32000
|
|
|
|
|
input_price: 2
|
|
|
|
|
output_price: 6
|
|
|
|
|
- name: mistralai/codestral-mamba
|
|
|
|
|
max_input_tokens: 256000
|
|
|
|
|
input_price: 0.25
|
|
|
|
|
output_price: 0.25
|
|
|
|
|
- name: mistralai/mistral-nemo
|
|
|
|
|
max_input_tokens: 128000
|
|
|
|
|
input_price: 0.5
|
|
|
|
|
output_price: 1.5
|
|
|
|
|
input_price: 0.18
|
|
|
|
|
output_price: 0.18
|
|
|
|
|
supports_function_calling: true
|
|
|
|
|
- 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
|
|
|
|
@ -999,18 +1008,10 @@
|
|
|
|
|
max_input_tokens: 32768
|
|
|
|
|
input_price: 0.14
|
|
|
|
|
output_price: 0.28
|
|
|
|
|
- name: perplexity/llama-3-sonar-small-32k-chat
|
|
|
|
|
max_input_tokens: 32768
|
|
|
|
|
input_price: 0.2
|
|
|
|
|
output_price: 0.2
|
|
|
|
|
- name: perplexity/llama-3-sonar-small-32k-online
|
|
|
|
|
max_input_tokens: 28000
|
|
|
|
|
input_price: 0.2
|
|
|
|
|
output_price: 0.2
|
|
|
|
|
- name: perplexity/llama-3-sonar-large-32k-chat
|
|
|
|
|
max_input_tokens: 32768
|
|
|
|
|
input_price: 1
|
|
|
|
|
output_price: 1
|
|
|
|
|
- name: perplexity/llama-3-sonar-large-32k-online
|
|
|
|
|
max_input_tokens: 28000
|
|
|
|
|
input_price: 1
|
|
|
|
@ -1023,28 +1024,36 @@
|
|
|
|
|
- platform: octoai
|
|
|
|
|
# docs:
|
|
|
|
|
# - https://octo.ai/docs/getting-started/inference-models
|
|
|
|
|
# - https://octo.ai/pricing/text-gen-solution/
|
|
|
|
|
# - https://octo.ai/docs/getting-started/pricing-and-billing
|
|
|
|
|
models:
|
|
|
|
|
- name: meta-llama-3-8b-instruct
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
input_price: 0.13
|
|
|
|
|
output_price: 0.13
|
|
|
|
|
- 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: 0.86
|
|
|
|
|
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
|
|
|
|
|
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: 0.86
|
|
|
|
|
output_price: 0.86
|
|
|
|
|
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
|
|
|
|
@ -1059,35 +1068,38 @@
|
|
|
|
|
# - https://docs.together.ai/docs/embedding-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-v0.3
|
|
|
|
|
max_input_tokens: 32768
|
|
|
|
|
input_price: 0.2
|
|
|
|
|
output_price: 0.2
|
|
|
|
|
- name: mistralai/Mixtral-8x7B-Instruct-v0.1
|
|
|
|
|
- name: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
|
|
|
|
|
max_input_tokens: 32768
|
|
|
|
|
input_price: 0.9
|
|
|
|
|
output_price: 0.9
|
|
|
|
|
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: google/gemma-7b-it
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
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: Qwen/Qwen2-72B-Instruct
|
|
|
|
|
max_input_tokens: 32768
|
|
|
|
|
input_price: 0.9
|
|
|
|
|
output_price: 0.9
|
|
|
|
|
max_batch_size: 100
|
|
|
|
|
- name: WhereIsAI/UAE-Large-V1
|
|
|
|
|
type: embedding
|
|
|
|
|
max_input_tokens: 512
|
|
|
|
@ -1129,13 +1141,6 @@
|
|
|
|
|
output_vector_size: 768
|
|
|
|
|
default_chunk_size: 1500
|
|
|
|
|
max_batch_size: 100
|
|
|
|
|
- name: jina-embeddings-v2-base-code
|
|
|
|
|
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
|
|
|
|
@ -1143,9 +1148,9 @@
|
|
|
|
|
output_vector_size: 768
|
|
|
|
|
default_chunk_size: 1500
|
|
|
|
|
max_batch_size: 100
|
|
|
|
|
- name: jina-reranker-v1-base-multilingual
|
|
|
|
|
- name: jina-reranker-v2-base-multilingual
|
|
|
|
|
type: reranker
|
|
|
|
|
max_input_tokens: 8192
|
|
|
|
|
max_input_tokens: 1024
|
|
|
|
|
input_price: 0.02
|
|
|
|
|
- name: jina-reranker-v1-base-en
|
|
|
|
|
type: reranker
|
|
|
|
|