# Grok 4.20 Multi-Agent - Core.Today AI API

> Grok 4.20 Multi-Agent beta (0309 snapshot) - deep-research style multi-agent orchestration with a 1M-token context window. Served through the Responses API only.

- **Provider**: xAI
- **Model ID**: grok-4.20-multi-agent-0309
- **Category**: LLM
- **Credits**: 3 per 1K tokens (avg) - min ≈ 4K tokens per turn
- **Speed**: Slow
- **Quality**: Ultra

## Model Specifications
- **Context Window**: 1M tokens
- **Max Output**: 33K tokens
- **Training Cutoff**: 2025-11
- **Supported Formats**: text, json, markdown
- **Compatible SDK**: OpenAI

### Capabilities
- Function Calling
- Streaming
- JSON Mode
- System Prompt

### Token Pricing (per 1M tokens)
- **Input Tokens**: 2,322.5 credits ($1.55)
- **Output Tokens**: 4,645 credits ($3.10)
- **Cached Tokens**: 371.6 credits ($0.25)

## Features
- Multi-agent deep research (beta) - sub-agent tokens are billed
- 1M context window
- Responses API only (/v1/responses) - Chat Completions is rejected with 400
- Prompt caching with discounted cache reads
- Long-context tier: prompts reaching 200K tokens bill the whole request at 2x rates

## Use Cases
- Deep research over long documents with multi-step synthesis
- Complex analysis where parallel sub-tasks pay off
- Agentic workflows that need a 1M shared context

## API Endpoint

Base URL: https://api.core.today
Endpoint: POST /llm/grok/v1/responses

## Authentication
Header: Authorization: Bearer YOUR_API_KEY

Note: LLM endpoints use OpenAI-compatible format with Authorization Bearer token.

## Input Parameters

### Required
- **model**: string - Model ID, e.g. "grok-4.20-multi-agent-0309".
- **input**: string | array - Responses API input - a plain string or an array of role/content messages (replaces `messages`).

### Optional
- **instructions**: string - System-level instructions (replaces the `system` message).
- **max_output_tokens**: integer (default: 4096) - Cap on the visible answer. Sub-agent and reasoning tokens are billed separately and are not limited by this value.
- **stream**: boolean (default: false) - Stream the response as server-sent events.

## Examples

### Deep research (Responses API)
Responses API request - the only endpoint this model accepts. A research-grade question amortizes the per-turn token floor.
```json
{
  "model": "grok-4.20-multi-agent-0309",
  "instructions": "You are a research analyst. Cite the evidence you rely on.",
  "input": "Compare the three leading approaches to long-context retrieval in 2026 and recommend one for a legal-document pipeline.",
  "max_output_tokens": 4096
}
```

## Response Format
```json
{
  "id": "chatcmpl-abc123",
  "object": "chat.completion",
  "choices": [
    {
      "index": 0,
      "message": {
        "role": "assistant",
        "content": "Response text here"
      },
      "finish_reason": "stop"
    }
  ],
  "usage": {
    "prompt_tokens": 100,
    "completion_tokens": 50,
    "total_tokens": 150
  }
}
```

## Tips
- Call POST /llm/grok/v1/responses - Chat Completions returns 400 for this model. With the OpenAI SDK use client.responses.create(...) with base_url https://api.core.today/llm/grok/v1
- Budget for a per-turn floor of roughly 4K tokens (≈9 credits): the orchestrator's cached system context and sub-agent reasoning are billed even when your prompt is one line. Pick a single-agent Grok for short Q&A
- max_output_tokens caps only the visible answer - it does not cap sub-agent or reasoning tokens
- Keep prompts under 200K tokens to stay on the standard rate (2x above that)

## Documentation
https://docs.x.ai/docs/models