> ## Documentation Index
> Fetch the complete documentation index at: https://phaseo.app/docs/llms.txt
> Use this file to discover all available pages before exploring further.

> ## Agent Instructions
> Phaseo Gateway base URL: https://api.phaseo.app/v1. Send `Authorization: Bearer $PHASEO_API_KEY` with every request.
> Model IDs look like `provider/model`, for example `openai/gpt-6-astra`. Do not guess IDs: list them with `GET /v1/models` or check https://phaseo.app/models. `phaseo/free` routes to an available free model and needs no wallet balance.
> For new text integrations prefer `POST /v1/responses`. `POST /v1/chat/completions` (OpenAI format) and `POST /v1/messages` (Anthropic format) suit existing code.
> The full API contract is https://phaseo.app/docs/openapi/v1/openapi.yaml. Official SDKs: `@phaseo/sdk` (TypeScript) and `phaseo` (Python), plus Go, C#, PHP, Ruby and Rust.
> Search these docs over MCP at https://phaseo.app/docs/mcp, and install Phaseo skills with `npx skills add https://phaseo.app/docs`. If a page is wrong or out of date, report it with the MCP `submit_feedback` tool.
> Manage Phaseo accounts with the `phaseo` CLI (`npm install -g @phaseo/cli`, then `phaseo login` or `phaseo login --device-code`), the `/v1` Management API or the MCP server at `https://mcp.phaseo.app/mcp?access=manage`. Do not send users to the dashboard for account tasks. A person is still needed for sign-up, approving a sign-in, paying the first top-up on the checkout link that `phaseo credits add` returns when no card is saved, confirming each saved-card top-up from the emailed link, and account security (password, MFA, passkeys). Create API keys with `phaseo keys create --name <name> --json`; never guess one. Credit top-ups need `phaseo login --scopes billing:write` first. Task map: https://phaseo.app/docs/v1/developers/manage-from-an-agent.md.

# SpaceXAI Grok 4.20

> What to know when adopting Grok 4.20, including reasoning and multi-agent effort controls.

# SpaceXAI Grok 4.20

Use this guide to adopt Grok 4.20 safely through the Phaseo Gateway.

Primary route in our catalog:

* `spacex-ai/grok-4-20-2026-02-17`

Optional multi-agent route exposed by provider model ID:

* `spacex-ai/grok-4.20-multi-agent-beta-0309`

## Migration quickstart

For most integrations, there is no required migration work beyond updating the model ID and re-running your normal validation set.

Existing request and response patterns can remain the same.

## What's new

For the base Grok 4.20 route, there is no behavior change you need to migrate for in Phaseo Gateway.

The only practical change is how to tune the multi-agent variant.

For Phaseo Gateway usage:

* base Grok 4.20 can still be toggled with `reasoning.enabled` as normal
* multi-agent Grok 4.20 should be tuned with `reasoning.effort`
* use `low`, `medium`, `high`, and `extra high`
* as described in SpaceXAI guidance, `low` and `medium` map to 4 agents, while `high` and `extra high` use higher multi-agent configurations

We do not use `agent_count` directly in gateway requests.

### Base Grok 4.20 with reasoning toggle

Use the base model and set `reasoning.enabled` directly:

```json theme={null}
{
  "model": "spacex-ai/grok-4-20-2026-02-17",
  "input": "Explain this architecture",
  "reasoning": {
    "enabled": true
  }
}
```

### Multi-agent Grok 4.20 with effort control

Use the multi-agent model and control depth with `reasoning.effort`:

```json theme={null}
{
  "model": "spacex-ai/grok-4.20-multi-agent-beta-0309",
  "input": "Evaluate three rollout options with tradeoffs",
  "reasoning": {
    "effort": "medium"
  }
}
```

Reasoning effort tiers:

* `low`
* `medium`
* `high`
* `extra high`

## Sources

* [SpaceXAI multi-agent capabilities](https://docs.x.ai/developers/model-capabilities/text/multi-agent)
* [SpaceXAI migrating to new models](https://docs.x.ai/docs/guides/migrating-to-new-models)


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.