- Context
- 2M
- Released
- 7mo ago
- Input / 1M tokens
- $1.25
- Output / 1M tokens
- $2.50
- Cached input / 1M tokens
- $0.20
Sources:OpenRouter
Benchmarks
DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.
Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.
No benchmark results have been matched to this model yet.
Specifications
- Developer
- xAI
- Model family
- Grok
- Type
- Language model
- Predecessor
- —
- Successor
- —
- Released
- March 10, 2026
- Model ID
x-ai/grok-4.20-multi-agent- Openness
- Closed
- License
- —
- Input modalities
- text, image, file
- Output modalities
- text
- Modality
- text+image+file->text
- Tokenizer
- Grok
- Max output tokens
- 1.8M
- Knowledge cutoff
- 2025-09-01
- Hugging Face
- —
- Source freshness
- Endpoints synced Oct 15, 2026, 11:18 AM UTC
Infrastructure
Provider availability
| Provider | Endpoint | Context | Input /M tokens | Output /M tokens | Cached input /M tokens | Cache write /M tokens | Uptime 1d | Data handling |
|---|---|---|---|---|---|---|---|---|
| xai/zdr | 2M | $1.25 | $2.50 | $0.20 | — | 95.65% | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| xai | 2M | $1.25 | $2.50 | $0.20 | — | 7.45% | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| xai/zdr/priority | 2M | $2.50 | $5.00 | $0.40 | — | — | ZDR: YesTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 | |
| xai/priority | 2M | $2.50 | $5.00 | $0.40 | — | — | ZDR: NoTraining: Unknown Prompt logging: Unknown Retention: Unknown Checked 2026-10-15 |
Provider data:OpenRouter