xAI / xai/grok-4.20-multi-agent
Grok 4.20 Multi-Agent - access through LLMTR
Positioned for teams that want parallel sub-agents and broader research output. It shines more in deep scans, synthesis, and briefings than in short-form answers.
Technical specifications
| Canonical ID | xai/grok-4.20-multi-agent |
|---|---|
| Provider | xAI |
| Context window | 2,000,000 tokens |
| Operations | RESPONSES |
| Modalities | text |
Pricing
An 8% platform margin applies to credit top-ups; model usage prices are not separately marked up.
| Operation | Metric | Unit | Price |
|---|---|---|---|
| RESPONSES | INPUT_TEXT | PER_1M_TOKENS | $1.25 |
| RESPONSES | OUTPUT_TEXT | PER_1M_TOKENS | $2.50 |
Example usage
With existing OpenAI SDK flows, change only the base URL and model identifier.
curl https://llmtr.com/v1/chat/completions -H "Authorization: Bearer llmtr-your_key" -H "Content-Type: application/json" -d '{"model":"xai/grok-4.20-multi-agent","messages":[{"role":"user","content":"Hello"}]}'Guides about this model
- Grok 4.20 Multi-Agent: the name says 'agent,' but the model doesn't support function calling - Even though the model's name includes 'multi-agent,' the catalog page shows this row has no function-calling capability. This article covers that unexpected detail and the deep research/synthesis tasks the model is actually strong at.
Related models
- Grok 4.7 xai/grok-4.7
- Grok 4.6 xai/grok-4.6
- Grok 4.5 xai/grok-4.5
- Grok 4.3 xai/grok-4.3
- Grok Imagine Video 1.5 xai/grok-imagine-video-1.5
- Grok 4.20 Reasoning 0309 xai/grok-4.20-0309-reasoning
- Grok 4.20 Non-Reasoning 0309 xai/grok-4.20-0309-non-reasoning
- Grok Imagine Image xai/grok-imagine-image