← Model list
Grok 4.20 Multi-Agent
xai·xai/grok-4.20-multi-agent·GA·Closed·grok series·NEW
Grok model for agentic tool use, reasoning, coding, and live assistance
At a glance
Official price$1.25 / $2.50 per 1M
Cache read $0.20 · xAI
Lowest paid$1.25 / $2.50
OpenRouter Gateway · 1.6× spread
Context1,000,000
⚠ Providers report 128,000–2,000,000; the table below is authoritative
Output limit30,000
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF
Knowledge cutoff2025-09-01
Released / updated2026-03-31 / 2026-06-11
Quality & performance
Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.
Available at 6 providers6 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| OpenRouter | Gateway | $1.25 tiered >200K: $2.50 | $2.50 | $0.20 | — | 2,000,000 ⚠ | 2,000,000 | |
| xAIOfficial grok-4.20-multi-agent-0309 | First-party | $1.25 tiered >200K: $2.50 | $2.50 | $0.20 | — | 1,000,000 | 30,000 | |
| Vercel AI Gateway | Cloud | $1.25 | $2.50 | $0.20 | — | 2,000,000 ⚠ | 2,000,000 | |
| Venice AI grok-4-20-multi-agent | Gateway | $1.42 tiered >200K: $2.83 | $2.83 | $0.23 | — | 2,000,000 ⚠ | 128,000 | |
| NanoGPT | Gateway | $2.00 | $6.00 | $1.00 | — | 2,000,000 ⚠ | 131,072 | |
| Poe | Gateway | $2.00 | $6.00 | $0.20 | — | 128,000 ⚠ | 0 |
Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.
Your usage cost
1OpenRouter$249.00
2xAI · Official$249.00
3Vercel AI Gateway$249.00
4Venice AI$282.70
5Poe$484.00
6NanoGPT$580.00
Switch to OpenRouter to save $0.00/mo (0%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.
Benchmark
No upstream benchmark data for this model. For quality, see the Artificial Analysis intelligence score above.
Reasoning control
effort = loweffort = mediumeffort = higheffort = xhigh
2 / 6 providers expose no reasoning control (reasoning_options: []).
Related models
Grok 4.6same series$2.00 / $6.00Grok 4.6 (xAI)same series$2.00 / $6.00Grok 4.6 (AWS Bedrock)same series$2.00 / $6.00DeepSeek V4 Procheaper alternative$0.435 / $0.87DeepSeek V4 Flashcheaper alternative$0.14 / $0.28DeepSeek V4 Flash 0731cheaper alternative$0.479 / $1.44MiniMax-M3cheaper alternative$0.30 / $1.20
Price historyone sample accumulated per data sync
Input listOutput listMin blended