Grok 4.20 (Reasoning / Non-reasoning / Multi-Agent)
Snapshot ids dated 0309. xAI docs list 1M context; OpenRouter lists 2M. Superseded by Grok 4.5-4.7; logprobs unsupported.
- Context window
- 1,000,000 tokens
- Input
- text, image
- Output
- text
- License
- proprietary
- Pricing
- input: $1.25 · cached input: $0.2 · output: $2.5 · input over 200k: $2.5 · output over 200k: $5 (per 1M tokens (USD)) source
- Verified
- 2026-09-29
How to call it
| Provider | Model id | Endpoint / URL | Docs |
|---|---|---|---|
| xAI API | grok-4.20-0309-reasoning | https://api.x.ai/v1/chat/completions | docs |
| xAI API (non-reasoning) | grok-4.20-0309-non-reasoning | https://api.x.ai/v1/chat/completions | — |
| xAI API (multi-agent) | grok-4.20-multi-agent-0309 | — | docs |
| OpenRouter | x-ai/grok-4.20 | openrouter.ai/x-ai/grok-4.20 | — |
| OpenRouter (multi-agent) | x-ai/grok-4.20-multi-agent | openrouter.ai/x-ai/grok-4.20-multi-agent | — |
Notable capabilities (2)
- Multi-agent model variant: Dedicated API id that runs parallel collaborating agents (4 at low/medium effort, 16 at high/xhigh) that search and cross-check before synthesizing an answer. source
- Reasoning and non-reasoning twin ids: Same snapshot (0309) offered as separate reasoning and non-reasoning model ids. source
Previous-generation Grok, notable for its multi-agent variant for deep research.
curl https://api.x.ai/v1/chat/completions -H "Authorization: Bearer $XAI_API_KEY" -H "Content-Type: application/json" \
-d '{"model":"grok-4.20-0309-reasoning","messages":[{"role":"user","content":"Hello"}]}'
Sources: https://docs.x.ai/docs/models , https://docs.x.ai/developers/model-capabilities/text/multi-agent
Other xAI models
Grok 4.7 · Grok Voice Transcribe 2.0 · Grok Imagine Image 2.0 · Grok Voice Think Fast 2.0 · Grok Imagine Video 1.5 · Grok Build 0.1 · Grok Text to Speech (Grok TTS API) · Grok 4.3