Supported LLM models and providers

Langbase supports a wide range of latest Large Language Models (LLMs) and providers. We are continuously adding support for the latest models as they are released. Here are some of the models and providers supported by Langbase.

Supported LLM Providers

We currently support the following LLM providers.

  • OpenAI
  • Together
  • Anthropic
  • Groq
  • Google
  • Cohere
  • Fireworks AI
  • Perplexity
  • Mistral AI
  • xAI

You can use any of these providers to build your Pipe, by adding your provider's key. Please feel free to request any specific provider you would like to use.


Supported LLM Models

We support the following LLM models from the above providers. Please feel free to request any specific model you would like to use.

OpenAI

ModelProviderOwnerContextCost*
o1-preview
ID: openai:o1-preview
OpenAIOpenAI128,000$15.0 prompt
$60.0 completion
o1-mini
ID: openai:o1-mini
OpenAIOpenAI128,000$3.0 prompt
$12.0 completion
gpt-4o
ID: openai:gpt-4o
OpenAIOpenAI128,000$2.5 prompt
$10.0 completion
gpt-4o-2024-08-06
ID: openai:gpt-4o-2024-08-06
OpenAIOpenAI128,000$2.5 prompt
$10.0 completion
gpt-4o-mini
ID: openai:gpt-4o-mini
OpenAIOpenAI128,000$0.15 prompt
$0.6 completion
gpt-4-turbo
ID: openai:gpt-4-turbo
OpenAIOpenAI128,000$10.0 prompt
$30.0 completion
gpt-4-turbo-preview
ID: openai:gpt-4-turbo-preview
OpenAIOpenAI128,000$10.0 prompt
$30.0 completion
gpt-4-0125-preview
ID: openai:gpt-4-0125-preview
OpenAIOpenAI128,000$10.0 prompt
$30.0 completion
gpt-4-1106-preview
ID: openai:gpt-4-1106-preview
OpenAIOpenAI128,000$10.0 prompt
$30.0 completion
gpt-4
ID: openai:gpt-4
OpenAIOpenAI8,192$30.0 prompt
$60.0 completion
gpt-4-0613
ID: openai:gpt-4-0613
OpenAIOpenAI8,192$30.0 prompt
$60.0 completion
gpt-4-32k
ID: openai:gpt-4-32k
OpenAIOpenAI32,768$60.0 prompt
$120.0 completion
gpt-3.5-turbo-0125
ID: openai:gpt-3.5-turbo-0125
OpenAIOpenAI16,385$0.5 prompt
$1.5 completion
gpt-3.5-turbo-1106
ID: openai:gpt-3.5-turbo-1106
OpenAIOpenAI16,385$1.0 prompt
$2.0 completion
gpt-3.5-turbo
ID: openai:gpt-3.5-turbo
OpenAIOpenAI4,096$1.5 prompt
$2.0 completion
gpt-3.5-turbo-16k
ID: openai:gpt-3.5-turbo-16k
OpenAIOpenAI16,385$3.0 prompt
$4.0 completion
* USD per Million tokens

Together AI

ModelProviderOwnerContextCost*
Llama-3.3-70B-Instruct-Turbo
ID: together:meta-llama/Llama-3.3-70B-Instruct-Turbo
TogetherMeta131,072$0.88 prompt
$0.88 completion
Llama-3.1-405B-Instruct-Turbo
ID: together:meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
TogetherMeta4,096$5 prompt
$5 completion
Llama-3.1-70B-Instruct-Turbo
ID: together:meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
TogetherMeta8,192$0.88 prompt
$0.88 completion
Llama-3.1-8B-Instruct-Turbo
ID: together:meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
TogetherMeta8,192$0.18 prompt
$0.18 completion
Llama-3-70b-chat-hf
ID: together:meta-llama/Llama-3-70b-chat-hf
TogetherMeta8,192$0.9 prompt
$0.9 completion
Llama-3-8b-chat-hf
ID: together:meta-llama/Llama-3-8b-chat-hf
TogetherMeta8,192$0.2 prompt
$0.2 completion
Llama-2-13b-chat-hf
ID: together:meta-llama/Llama-2-13b-chat-hf
TogetherMeta4,096$0.225 prompt
$0.225 completion
gemma-2b-it
ID: together:google/gemma-2b-it
TogetherGoogle8,192$0.1 prompt
$0.1 completion
7B-Instruct-v0.1
ID: together:mistralai/Mistral-7B-Instruct-v0.1
TogetherMistral4,096$0.2 prompt
$0.2 completion
7B-Instruct-v0.2
ID: together:mistralai/Mistral-7B-Instruct-v0.2
TogetherMistral32,768$0.2 prompt
$0.2 completion
Mixtral-8x7B-Instruct-v0.1
ID: together:mistralai/Mixtral-8x7B-Instruct-v0.1
TogetherMistral32,768$0.6 prompt
$0.6 completion
Mixtral-8x22B-Instruct-v0.1
ID: together:mistralai/Mixtral-8x22B-Instruct-v0.1
TogetherMistral64,000$1.2 prompt
$1.2 completion
DBRX-instruct
ID: together:databricks/dbrx-instruct
TogetherDatabricks32,768$1.2 prompt
$1.2 completion
* USD per Million tokens

Anthropic

ModelProviderOwnerContextCost*
claude-3.5-sonnet-latest
ID: anthropic:claude-3-5-sonnet-latest
AnthropicAnthropic200K$3 prompt
$15 completion
claude-3-5-haiku-20241022
ID: anthropic:claude-3-5-haiku-20241022
AnthropicAnthropic200K$1 prompt
$5 completion
claude-3.5-sonnet-20240620
ID: anthropic:claude-3-5-sonnet-20240620
AnthropicAnthropic200K$3 prompt
$15 completion
claude-3-opus
ID: anthropic:claude-3-opus-20240229
AnthropicAnthropic200K$15 prompt
$75 completion
claude-3-sonnet
ID: anthropic:claude-3-sonnet-20240229
AnthropicAnthropic200K$3 prompt
$15 completion
claude-3-haiku
ID: anthropic:claude-3-haiku-20240307
AnthropicAnthropic200K$0.25 prompt
$1.25 completion
* USD per Million tokens

Google AI

ModelProviderOwnerContextCost*
gemini-1.5-pro
ID: google:gemini-1.5-pro-latest
GoogleGoogleupto 1M$7 prompt
$21 completion
gemini-2.0-flash-exp
ID: google:gemini-2.0-flash-exp
GoogleGoogleupto 1M$0.075 prompt
$0.3 completion
gemini-1.5-flash
ID: google:gemini-1.5-flash-latest
GoogleGoogleupto 1M$0.075 prompt
$0.3 completion
gemini-1.5-flash-8b
ID: google:gemini-1.5-flash-8b-latest
GoogleGoogleupto 1M$0.0375 prompt
$0.15 completion
gemini-1.0-pro
ID: google:gemini-pro
GoogleGoogle30,720$0.5 prompt
$1.5 completion
* USD per Million tokens

Groq

ModelProviderOwnerContextCost*
Llama-3.3-70b-versatile
ID: groq:llama-3.3-70b-versatile
GroqMeta128,000$0.59 prompt
$0.79 completion
Llama-3.1-70b-versatile
ID: groq:llama-3.1-70b-versatile
GroqMeta131,072$0.59 prompt
$0.79 completion
Llama-3.1-8b-instant
ID: groq:llama-3.1-8b-instant
GroqMeta131,072$0.59 prompt
$0.79 completion
Llama-3-70b
ID: groq:llama3-70b-8192
GroqMeta8,192$0.59 prompt
$0.79 completion
Llama-3-8b
ID: groq:llama3-8b-8192
GroqMeta8,192$0.05 prompt
$0.1 completion
Mixtral-8x7B
ID: groq:mixtral-8x7b-32768
GroqMistral32,768$0.27 prompt
$0.27 completion
gemma2-9b-it
ID: groq:gemma2-9b-it
GroqGoogle8,192$0.2 prompt
$0.2 completion
gemma-7b-it
ID: groq:gemma-7b-it
GroqGoogle8,192$0.07 prompt
$0.07 completion
* USD per Million tokens

Fireworks AI

ModelProviderOwnerContextCost*
Llama 3.3 70B Instruct
ID: fireworks:llama-v3p3-70b-instruct
Fireworks AIMeta131,072$0.9 prompt
$0.9 completion
Llama-3.2-3b
ID: fireworks:llama-v3p2-3b-instruct
Fireworks AIMeta131,072$0.1 prompt
$0.1 completion
Llama-3.2-1b
ID: fireworks:llama-v3p2-1b-instruct
Fireworks AIMeta131,072$0.1 prompt
$0.1 completion
Llama-3.1-405b
ID: fireworks:llama-v3p1-405b-instruct
Fireworks AIMeta131,072$3 prompt
$3 completion
Llama-3.1-70b
ID: fireworks:llama-v3p1-70b-instruct
Fireworks AIMeta131,072$0.9 prompt
$0.9 completion
Llama-3.1-8b
ID: fireworks:llama-v3p1-8b-instruct
Fireworks AIMeta131,072$0.2 prompt
$0.2 completion
yi-large
ID: fireworks:yi-large
Fireworks AI01.AI32,768$3 prompt
$3 completion
Llama-3-70b
ID: fireworks:llama-v3-70b-instruct
Fireworks AIMeta8,192$0.9 prompt
$0.9 completion
* USD per Million tokens

Perplexity

ModelProviderOwnerContextCost*
llama-3.1-sonar-huge-128k-online
ID: perplexity:llama-3.1-sonar-huge-128k-online
PerplexityMeta127,072$5 prompt
$5 completion
llama-3.1-sonar-large-128k-online
ID: perplexity:llama-3.1-sonar-large-128k-online
PerplexityMeta127,072$1 prompt
$1 completion
llama-3.1-sonar-small-128k-online
ID: perplexity:llama-3.1-sonar-small-128k-online
PerplexityMeta127,072$0.2 prompt
$0.2 completion
llama-3.1-sonar-large-128k-chat
ID: perplexity:llama-3.1-sonar-large-128k-chat
PerplexityMeta131,072$1 prompt
$1 completion
llama-3.1-sonar-small-128k-chat
ID: perplexity:llama-3.1-sonar-small-128k-chat
PerplexityMeta131,072$0.2 prompt
$0.2 completion
* USD per Million tokens. Perplexity charges additional $5 per each request on its online models.

Mistral AI

ModelProviderOwnerContextCost*
Mistral Large 2
ID: mistral:mistral-large-latest
Mistral AIMistral AI128K$3 prompt
$9 completion
Mistral Nemo
ID: mistral:open-mistral-nemo
Mistral AIMistral AI128K$0.3 prompt
$0.3 completion
Codestral
ID: mistral:codestral-latest
Mistral AIMistral AI32,768$1 prompt
$3 completion
* USD per Million tokens

Cohere

ModelProviderOwnerContextCost*
command-r
ID: cohere:command-r
CohereCohere128K$0.5 prompt
$1.5 completion
command-r-plus
ID: cohere:command-r-plus
CohereCohere128K$3 prompt
$15 completion
* USD per Million tokens

xAI

ModelProviderOwnerContextCost*
grok-2-1212
ID: xai:grok-2-1212
xAIxAI131,072$2 prompt
$10 completion
grok-2-vision-1212
ID: xai:grok-2-vision-1212
xAIxAI32K$2 prompt
$10 completion
grok-beta
ID: xai:grok-beta
xAIxAI131,072$5 prompt
$15 completion
* USD per Million tokens

JSON Mode Support

See the list of models that support JSON mode and how to use it in your Pipe.

Note

Completion and Prompt costs are based on the provider's pricing. Langbase does not charge on top of the provider's costs.


Tool Support

The following models support tool calls on Langbase.

OpenAI

ModelParallel Tool Call SupportTool Choice Support
o1-preview
ID: openai:o1-preview
truetrue
o1-mini
ID: openai:o1-mini
truetrue
gpt-4o
ID: openai:gpt-4o
truetrue
gpt-4o-2024-08-06
ID: openai:gpt-4o-2024-08-06
truetrue
gpt-4o-mini
ID: openai:gpt-4o-mini
truetrue
gpt-4-turbo
ID: openai:gpt-4-turbo
truetrue
gpt-4-turbo-preview
ID: openai:gpt-4-turbo-preview
truetrue
gpt-4-0125-preview
ID: openai:gpt-4-0125-preview
truetrue
gpt-4-1106-preview
ID: openai:gpt-4-1106-preview
truetrue
gpt-4
ID: openai:gpt-4
truetrue
gpt-4-0613
ID: openai:gpt-4-0613
truetrue
gpt-4-32k
ID: openai:gpt-4-32k
truetrue
gpt-3.5-turbo-0125
ID: openai:gpt-3.5-turbo-0125
truetrue
gpt-3.5-turbo-1106
ID: openai:gpt-3.5-turbo-1106
truetrue
gpt-3.5-turbo
ID: openai:gpt-3.5-turbo
truetrue
gpt-3.5-turbo-16k
ID: openai:gpt-3.5-turbo-16k
truetrue

Google

ModelParallel Tool Call SupportTool Choice Support
gemini-1.5-pro
ID: google:gemini-1.5-pro-latest
truetrue
gemini-2.0-flash-exp
ID: google:gemini-2.0-flash-exp
GoogleGoogle
gemini-1.5-flash
ID: google:gemini-1.5-flash-latest
truetrue
gemini-1.5-flash-8b
ID: gemini-1.5-flash-8b-latest
truetrue
gemini-1.0-pro
ID: google:gemini-pro
falsefalse

Anthropic

ModelParallel Tool Call SupportTool Choice Support
claude-3.5-sonnet-latest
ID: anthropic:claude-3-5-sonnet-latest
truetrue
claude-3.5-sonnet-20240620
ID: anthropic:claude-3-5-sonnet-20240620
truetrue
claude-3-opus
ID: anthropic:claude-3-opus-20240229
truetrue
claude-3-sonnet
ID: anthropic:claude-3-sonnet-20240229
truetrue
claude-3-haiku
ID: anthropic:claude-3-haiku-20240307
truetrue

Together AI

ModelParallel Tool Call SupportTool Choice Support
Llama-3.1-405B-Instruct-Turbo
ID: together:meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
falsetrue
Llama-3.1-70B-Instruct-Turbo
ID: together:meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
falsetrue
Llama-3.1-8B-Instruct-Turbo
ID: together:meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
falsetrue
7B-Instruct-v0.1
ID: together:mistralai/Mistral-7B-Instruct-v0.1
falsetrue
Mixtral-8x7B-Instruct-v0.1
ID: together:mistralai/Mixtral-8x7B-Instruct-v0.1
falsetrue

Deprecated Models

The following models are deprecated and no longer available for use in pipes. It is recommended to switch to a supported model.

ModelProviderOwnerDeprecated onReason
qwen2-72bFireworks AIQwenLM13-08-2024Discontinued by Fireworks AI
Llama-3-70b-chat-hfTogether AIMeta15-09-2024Discontinued by Together AI
Llama-2-7B-32K-InstructTogether AIMeta15-09-2024Discontinued by Together AI
gemma-7b-itTogether AIMeta15-09-2024Discontinued by Together AI