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
- 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
| Model | Provider | Owner | Context | Cost* |
|---|---|---|---|---|
| o1-preview ID: o1-preview | OpenAI | OpenAI | 128,000 | $15.0 prompt $60.0 completion |
| o1-mini ID: o1-mini | OpenAI | OpenAI | 128,000 | $3.0 prompt $12.0 completion |
| gpt-4o ID: gpt-4o | OpenAI | OpenAI | 128,000 | $2.5 prompt $10.0 completion |
| gpt-4o-2024-08-06 ID: gpt-4o-2024-08-06 | OpenAI | OpenAI | 128,000 | $2.5 prompt $10.0 completion |
| gpt-4o-mini ID: gpt-4o-mini | OpenAI | OpenAI | 128,000 | $0.15 prompt $0.6 completion |
| gpt-4-turbo ID: gpt-4-turbo | OpenAI | OpenAI | 128,000 | $10.0 prompt $30.0 completion |
| gpt-4-turbo-preview ID: gpt-4-turbo-preview | OpenAI | OpenAI | 128,000 | $10.0 prompt $30.0 completion |
| gpt-4-0125-preview ID: gpt-4-0125-preview | OpenAI | OpenAI | 128,000 | $10.0 prompt $30.0 completion |
| gpt-4-1106-preview ID: gpt-4-1106-preview | OpenAI | OpenAI | 128,000 | $10.0 prompt $30.0 completion |
| gpt-4 ID: gpt-4 | OpenAI | OpenAI | 8,192 | $30.0 prompt $60.0 completion |
| gpt-4-0613 ID: gpt-4-0613 | OpenAI | OpenAI | 8,192 | $30.0 prompt $60.0 completion |
| gpt-4-32k ID: gpt-4-32k | OpenAI | OpenAI | 32,768 | $60.0 prompt $120.0 completion |
| gpt-3.5-turbo-0125 ID: gpt-3.5-turbo-0125 | OpenAI | OpenAI | 16,385 | $0.5 prompt $1.5 completion |
| gpt-3.5-turbo-1106 ID: gpt-3.5-turbo-1106 | OpenAI | OpenAI | 16,385 | $1.0 prompt $2.0 completion |
| gpt-3.5-turbo ID: gpt-3.5-turbo | OpenAI | OpenAI | 4,096 | $1.5 prompt $2.0 completion |
| gpt-3.5-turbo-16k ID: gpt-3.5-turbo-16k | OpenAI | OpenAI | 16,385 | $3.0 prompt $4.0 completion |
Together AI
| Model | Provider | Owner | Context | Cost* |
|---|---|---|---|---|
| Llama-3.1-405B-Instruct-Turbo ID: meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | Together | Meta | 4,096 | $5 prompt $5 completion |
| Llama-3.1-70B-Instruct-Turbo ID: meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | Together | Meta | 8,192 | $0.88 prompt $0.88 completion |
| Llama-3.1-8B-Instruct-Turbo ID: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | Together | Meta | 8,192 | $0.18 prompt $0.18 completion |
| Llama-3-70b-chat-hf ID: meta-llama/Llama-3-70b-chat-hf | Together | Meta | 8,192 | $0.9 prompt $0.9 completion |
| Llama-3-8b-chat-hf ID: meta-llama/Llama-3-8b-chat-hf | Together | Meta | 8,192 | $0.2 prompt $0.2 completion |
| Llama-2-13b-chat-hf ID: meta-llama/Llama-2-13b-chat-hf | Together | Meta | 4,096 | $0.225 prompt $0.225 completion |
| gemma-2b-it ID: google/gemma-2b-it | Together | 8,192 | $0.1 prompt $0.1 completion | |
| 7B-Instruct-v0.1 ID: mistralai/Mistral-7B-Instruct-v0.1 | Together | Mistral | 4,096 | $0.2 prompt $0.2 completion |
| 7B-Instruct-v0.2 ID: mistralai/Mistral-7B-Instruct-v0.2 | Together | Mistral | 32,768 | $0.2 prompt $0.2 completion |
| Mixtral-8x7B-Instruct-v0.1 ID: mistralai/Mixtral-8x7B-Instruct-v0.1 | Together | Mistral | 32,768 | $0.6 prompt $0.6 completion |
| Mixtral-8x22B-Instruct-v0.1 ID: mistralai/Mixtral-8x22B-Instruct-v0.1 | Together | Mistral | 64,000 | $1.2 prompt $1.2 completion |
| DBRX-instruct ID: databricks/dbrx-instruct | Together | Databricks | 32,768 | $1.2 prompt $1.2 completion |
Anthropic
| Model | Provider | Owner | Context | Cost* |
|---|---|---|---|---|
| claude-3.5-sonnet-latest ID: claude-3-5-sonnet-latest | Anthropic | Anthropic | 200K | $3 prompt $15 completion |
| claude-3-5-haiku-20241022 ID: claude-3-5-haiku-20241022 | Anthropic | Anthropic | 200K | $1 prompt $5 completion |
| claude-3.5-sonnet-20240620 ID: claude-3-5-sonnet-20240620 | Anthropic | Anthropic | 200K | $3 prompt $15 completion |
| claude-3-opus ID: claude-3-opus-20240229 | Anthropic | Anthropic | 200K | $15 prompt $75 completion |
| claude-3-sonnet ID: claude-3-sonnet-20240229 | Anthropic | Anthropic | 200K | $3 prompt $15 completion |
| claude-3-haiku ID: claude-3-haiku-20240307 | Anthropic | Anthropic | 200K | $0.25 prompt $1.25 completion |
Google AI
| Model | Provider | Owner | Context | Cost* |
|---|---|---|---|---|
| gemini-1.5-pro ID: gemini-1.5-pro-latest | upto 1M | $7 prompt $21 completion | ||
| gemini-1.5-flash ID: gemini-1.5-flash-latest | upto 1M | $0.075 prompt $0.3 completion | ||
| gemini-1.5-flash-8b ID: gemini-1.5-flash-8b-latest | upto 1M | $0.0375 prompt $0.15 completion | ||
| gemini-1.0-pro ID: gemini-pro | 30,720 | $0.5 prompt $1.5 completion |
Groq
| Model | Provider | Owner | Context | Cost* |
|---|---|---|---|---|
| Llama-3.1-70b-versatile ID: llama-3.1-70b-versatile | Groq | Meta | 131,072 | $0.59 prompt $0.79 completion |
| Llama-3.1-8b-instant ID: llama-3.1-8b-instant | Groq | Meta | 131,072 | $0.59 prompt $0.79 completion |
| Llama-3-70b ID: llama3-70b-8192 | Groq | Meta | 8,192 | $0.59 prompt $0.79 completion |
| Llama-3-8b ID: llama3-8b-8192 | Groq | Meta | 8,192 | $0.05 prompt $0.1 completion |
| Mixtral-8x7B ID: mixtral-8x7b-32768 | Groq | Mistral | 32,768 | $0.27 prompt $0.27 completion |
| gemma2-9b-it ID: gemma2-9b-it | Groq | 8,192 | $0.2 prompt $0.2 completion | |
| gemma-7b-it ID: gemma-7b-it | Groq | 8,192 | $0.07 prompt $0.07 completion |
Fireworks AI
| Model | Provider | Owner | Context | Cost* |
|---|---|---|---|---|
| Llama-3.2-3b ID: llama-v3p2-3b-instruct | Fireworks AI | Meta | 131,072 | $0.1 prompt $0.1 completion |
| Llama-3.2-1b ID: llama-v3p2-1b-instruct | Fireworks AI | Meta | 131,072 | $0.1 prompt $0.1 completion |
| Llama-3.1-405b ID: llama-v3p1-405b-instruct | Fireworks AI | Meta | 131,072 | $3 prompt $3 completion |
| Llama-3.1-70b ID: llama-v3p1-70b-instruct | Fireworks AI | Meta | 131,072 | $0.9 prompt $0.9 completion |
| Llama-3.1-8b ID: llama-v3p1-8b-instruct | Fireworks AI | Meta | 131,072 | $0.2 prompt $0.2 completion |
| yi-large ID: yi-large | Fireworks AI | 01.AI | 32,768 | $3 prompt $3 completion |
| Llama-3-70b ID: llama-v3-70b-instruct | Fireworks AI | Meta | 8,192 | $0.9 prompt $0.9 completion |
Perplexity
| Model | Provider | Owner | Context | Cost* |
|---|---|---|---|---|
| llama-3.1-sonar-huge-128k-online ID: llama-3.1-sonar-huge-128k-online | Perplexity | Meta | 127,072 | $5 prompt $5 completion |
| llama-3.1-sonar-large-128k-online ID: llama-3.1-sonar-large-128k-online | Perplexity | Meta | 127,072 | $1 prompt $1 completion |
| llama-3.1-sonar-small-128k-online ID: llama-3.1-sonar-small-128k-online | Perplexity | Meta | 127,072 | $0.2 prompt $0.2 completion |
| llama-3.1-sonar-large-128k-chat ID: llama-3.1-sonar-large-128k-chat | Perplexity | Meta | 131,072 | $1 prompt $1 completion |
| llama-3.1-sonar-small-128k-chat ID: llama-3.1-sonar-small-128k-chat | Perplexity | Meta | 131,072 | $0.2 prompt $0.2 completion |
Mistral AI
| Model | Provider | Owner | Context | Cost* |
|---|---|---|---|---|
| Mistral Large 2 ID: mistral-large-latest | Mistral AI | Mistral AI | 128K | $3 prompt $9 completion |
| Mistral Nemo ID: open-mistral-nemo | Mistral AI | Mistral AI | 128K | $0.3 prompt $0.3 completion |
| Codestral ID: codestral-latest | Mistral AI | Mistral AI | 32,768 | $1 prompt $3 completion |
Cohere
| Model | Provider | Owner | Context | Cost* |
|---|---|---|---|---|
| command-r ID: command-r | Cohere | Cohere | 128K | $0.5 prompt $1.5 completion |
| command-r-plus ID: command-r-plus | Cohere | Cohere | 128K | $3 prompt $15 completion |
xAI
| Model | Provider | Owner | Context | Cost* |
|---|---|---|---|---|
| grok-beta ID: grok-beta | xAI | xAI | 131,072 | $5 prompt $15 completion |
JSON Mode Support
See the list of models that support JSON mode and how to use it in your Pipe.
Tool Support
The following models support tool calls in BaseAI.
OpenAI
| Model | Parallel Tool Call Support | Tool Choice Support |
|---|---|---|
| o1-preview ID: openai:o1-preview | true | true |
| o1-mini ID: openai:o1-mini | true | true |
| gpt-4o ID: openai:gpt-4o | true | true |
| gpt-4o-2024-08-06 ID: openai:gpt-4o-2024-08-06 | true | true |
| gpt-4o-mini ID: openai:gpt-4o-mini | true | true |
| gpt-4-turbo ID: openai:gpt-4-turbo | true | true |
| gpt-4-turbo-preview ID: openai:gpt-4-turbo-preview | true | true |
| gpt-4-0125-preview ID: openai:gpt-4-0125-preview | true | true |
| gpt-4-1106-preview ID: openai:gpt-4-1106-preview | true | true |
| gpt-4 ID: openai:gpt-4 | true | true |
| gpt-4-0613 ID: openai:gpt-4-0613 | true | true |
| gpt-4-32k ID: openai:gpt-4-32k | true | true |
| gpt-3.5-turbo-0125 ID: openai:gpt-3.5-turbo-0125 | true | true |
| gpt-3.5-turbo-1106 ID: openai:gpt-3.5-turbo-1106 | true | true |
| gpt-3.5-turbo ID: openai:gpt-3.5-turbo | true | true |
| gpt-3.5-turbo-16k ID: openai:gpt-3.5-turbo-16k | true | true |
| Model | Parallel Tool Call Support | Tool Choice Support |
|---|---|---|
| gemini-1.5-pro ID: google:gemini-1.5-pro-latest | true | true |
| gemini-1.5-flash ID: google:gemini-1.5-flash-latest | true | true |
| gemini-1.5-flash-8b ID: gemini-1.5-flash-8b-latest | true | true |
| gemini-1.0-pro ID: google:gemini-pro | false | false |
Anthropic
| Model | Parallel Tool Call Support | Tool Choice Support |
|---|---|---|
| claude-3.5-sonnet-latest ID: anthropic:claude-3-5-sonnet-latest | true | true |
| claude-3.5-sonnet-20240620 ID: anthropic:claude-3-5-sonnet-20240620 | true | true |
| claude-3-opus ID: anthropic:claude-3-opus-20240229 | true | true |
| claude-3-sonnet ID: anthropic:claude-3-sonnet-20240229 | true | true |
| claude-3-haiku ID: anthropic:claude-3-haiku-20240307 | true | true |
Together AI
| Model | Parallel Tool Call Support | Tool Choice Support |
|---|---|---|
| Llama-3.1-405B-Instruct-Turbo ID: together:meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo | false | true |
| Llama-3.1-70B-Instruct-Turbo ID: together:meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo | false | true |
| Llama-3.1-8B-Instruct-Turbo ID: together:meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo | false | true |
| 7B-Instruct-v0.1 ID: together:mistralai/Mistral-7B-Instruct-v0.1 | false | true |
| Mixtral-8x7B-Instruct-v0.1 ID: together:mistralai/Mixtral-8x7B-Instruct-v0.1 | false | true |
Deprecated Models
The following models are deprecated and no longer available for use in pipes. It is recommended to switch to a supported model.
| Model | Provider | Owner | Deprecated on | Reason |
|---|---|---|---|---|
| qwen2-72b | Fireworks AI | QwenLM | 13-08-2024 | Discontinued by Fireworks AI |
| Llama-3-70b-chat-hf | Together AI | Meta | 15-09-2024 | Discontinued by Together AI |
| Llama-2-7B-32K-Instruct | Together AI | Meta | 15-09-2024 | Discontinued by Together AI |
| gemma-7b-it | Together AI | Meta | 15-09-2024 | Discontinued by Together AI |