Skip to main content

​
SpaceXAI: Grok 4.20

Use this guide when you are moving traffic onto Grok 4.20 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 requirement

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 changed

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: 
{
  "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: 
{
  "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

Last modified on July 9, 2026