API Reference

Complete reference for the AltLLM API. Fully compatible with OpenAI SDK.

Base URL

https://api.altllm.ai/v1

Authentication

All API requests require a Bearer token in the Authorization header.

Authorization: Bearer YOUR_API_KEY

Get your API key from the API Keys page.

Chat Completions

POST/v1/chat/completions

Create a chat completion with optional streaming and tool use.

Request Body

Parameter	Type	Required	Description
`model`	string	Yes	Model ID (e.g., `altllm-basic`)
`messages`	array	Yes	Array of message objects
`stream`	boolean	No	Enable streaming (default: false)
`max_tokens`	integer	No	Maximum tokens to generate
`temperature`	number	No	Sampling temperature (0-2, default: 1)
`top_p`	number	No	Nucleus sampling (0-1)
`stop`	string \| array	No	Stop sequences
`tools`	array	No	Custom tools for function calling
`tool_choice`	string \| object	No	Tool selection mode
`response_format`	object	No	Output format (e.g., JSON mode)

Message Object

{
  "role": "user" | "assistant" | "system" | "tool",
  "content": "string or array",
  "name": "optional tool name",
  "tool_call_id": "optional tool call ID"
}

Example Request

curl https://api.altllm.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "altllm-basic",
    "messages": [
      {"role": "system", "content": "You are a helpful crypto assistant."},
      {"role": "user", "content": "What is the price of Bitcoin?"}
    ],
    "max_tokens": 500
  }'

Example Response

{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "created": 1704067200,
  "model": "altllm-basic",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "The current price of Bitcoin is $95,051 USD..."
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 50,
    "total_tokens": 75
  }
}

Video Generation

POST/v1/contents/generations/tasksBusiness FlexAsync

Create a Seedance video-generation task. Seedance is an async video model, not a chat-completions model, so the create response returns analtllm_status_tokenthat you poll until the provider finishes the video.

Create Task

curl -X POST https://api.altllm.ai/v1/contents/generations/tasks \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "altllm-flex-seedance-2.0",
    "prompt": "A cinematic 6-second product reveal of a crypto analytics dashboard, smooth camera push-in, crisp UI reflections",
    "duration": 6,
    "resolution": "720p"
  }'

Parameter	Type	Required	Description
`model`	string	Yes	`altllm-flex-seedance-2.0` or `altllm-flex-seedance-2.0-fast`
`prompt`	string	Yes	Video prompt passed to Seedance through OpenRouter.
`duration`	number	No	Requested video duration in seconds. Used for credit estimation.
`resolution`	string	No	Resolution bucket such as `480p`, `720p`, or `1080p`.

Poll Task Status

GET/v1/contents/generations/tasks/{status_token}

STATUS_TOKEN="<altllm_status_token from create response>"

curl https://api.altllm.ai/v1/contents/generations/tasks/$STATUS_TOKEN \
  -H "Authorization: Bearer YOUR_API_KEY"

The status token is signed and bound to the creating user or API key. Store it until the video completes; Portal task history is not persisted yet.

Streaming

Enable real-time streaming by setting stream: true.

Stream Request

curl https://api.altllm.ai/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "altllm-basic",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": true
  }'

Stream Response Format

data: {"id":"chatcmpl-abc123","choices":[{"delta":{"role":"assistant"}}]}

data: {"id":"chatcmpl-abc123","choices":[{"delta":{"content":"Hello"}}]}

data: {"id":"chatcmpl-abc123","choices":[{"delta":{"content":"!"}}]}

data: {"id":"chatcmpl-abc123","choices":[{"delta":{},"finish_reason":"stop"}]}

data: [DONE]

Tool Use / Function Calling

Define custom tools for the model to use. Built-in crypto tools are automatically available.

Custom Tool Definition

{
  "model": "altllm-basic",
  "messages": [{"role": "user", "content": "Get my portfolio for 0x123..."}],
  "tools": [{
    "type": "function",
    "function": {
      "name": "get_portfolio",
      "description": "Get user's crypto portfolio",
      "parameters": {
        "type": "object",
        "properties": {
          "wallet_address": {"type": "string"}
        },
        "required": ["wallet_address"]
      }
    }
  }],
  "tool_choice": "auto"
}

Tool Call Response

{
  "choices": [{
    "message": {
      "role": "assistant",
      "content": null,
      "tool_calls": [{
        "id": "call_abc123",
        "type": "function",
        "function": {
          "name": "get_portfolio",
          "arguments": "{\"wallet_address\": \"0x123...\"}"
        }
      }]
    },
    "finish_reason": "tool_calls"
  }]
}

List Models

GET/v1/modelsPublic

List all available models with full metadata. No authentication required.

curl https://api.altllm.ai/v1/models

Response

{
  "object": "list",
  "data": [{
    "id": "altllm-basic",
    "name": "AltLLM Standard",
    "created": 1704067200,
    "description": "AltLLM's balanced tier for daily tasks...",
    "pricing": {
      "prompt": "0.0000006",
      "completion": "0.0000024"
    },
    "context_length": 256000,
    "max_output_length": 32768,
    "input_modalities": ["text"],
    "output_modalities": ["text"],
    "supported_sampling_parameters": ["temperature", "top_p", ...],
    "supported_features": ["tools", "json_mode", "streaming"]
  }]
}

Get Model

GET/v1/models/{model_id}Public

Get details for a specific model. No authentication required.

curl https://api.altllm.ai/v1/models/altllm-basic

Provider Info

GET/v1/providerPublic

Get AltLLM provider metadata and capabilities.

curl https://api.altllm.ai/v1/provider

Health Check

GET/health

Check API gateway health status.

curl https://api.altllm.ai/health

{
  "status": "healthy",
  "service": "altllm-gateway",
  "version": "1.0.0"
}

Rate Limits

Rate limits are applied per API key. Check response headers for current usage.

Header	Description
`X-RateLimit-Limit`	Maximum requests per minute
`X-RateLimit-Remaining`	Remaining requests in current window
`X-RateLimit-Reset`	Time until rate limit resets (Unix timestamp)