Skip to content

Documentation

Getting Started

CallStack AI Gateway is fully compatible with the OpenAI API specification. Integration requires only a base URL change — no code modifications needed.

Endpoint Configuration

Each model provider has a dedicated gateway endpoint:

Anthropic Claude
claude.callaiapi.com
OpenAI
openai.callaiapi.com
Google Gemini
gemini.callaiapi.com
DeepSeek
deepseek.callaiapi.com

Authentication

All requests require an API key in the Authorization header:

Authorization: Bearer csk-your-api-key

API keys can be managed through the admin dashboard or via the management API.

Compatibility

The gateway accepts requests in standard OpenAI API format. Any SDK, framework, or tool that supports OpenAI can be used directly:

FrameworkConfiguration
OpenAI Python SDKSet base_url parameter
OpenAI Node.js SDKSet baseURL option
LangChainSet base_url on ChatOpenAI
Vercel AI SDKSet baseURL on createOpenAI
LlamaIndexSet api_base on OpenAI LLM
cURL / HTTPReplace the request URL

Available Models

ModelIdentifierEndpoint
Claude Opus 4claude-opus-4-20250514claude.callaiapi.com
Claude Sonnet 4claude-sonnet-4-20250514claude.callaiapi.com
GPT-4ogpt-4oopenai.callaiapi.com
GPT-4o Minigpt-4o-miniopenai.callaiapi.com
o3o3openai.callaiapi.com
Gemini 2.5 Progemini-2.5-progemini.callaiapi.com
DeepSeek V3deepseek-chatdeepseek.callaiapi.com
DeepSeek R1deepseek-reasonerdeepseek.callaiapi.com

For the full model catalog, see Supported Models.

API Reference

Chat Completions

POST /v1/chat/completions

Standard OpenAI Chat Completions format. Supports streaming, function calling, and multimodal inputs (model-dependent).

Models

GET /v1/models

Returns the list of models available on the specified gateway endpoint.

Embeddings

POST /v1/embeddings

Generate vector embeddings using supported embedding models.

Rate Limits

PlanRequests/minTokens/min
Starter60100,000
Professional300500,000
EnterpriseCustomCustom

Error Codes

CodeDescriptionResolution
401Authentication failedVerify API key
403Insufficient permissionsCheck key scope and model access
429Rate limit exceededReduce request frequency or upgrade plan
500Internal server errorRetry or contact support
503Upstream unavailableUpstream model temporarily unavailable

Support

For technical assistance, contact our engineering team: