xAIGrok 4.20 Multi Agent
Not yet ranked: too few independent results so far. Released 9 Mar 2026.
- Blended price
- $1.56/M
- $1.25 in · $2.50 out
- Output speed
- 329 tok/s
- First answer
- 6.71 s
- Context
- 1M
- Reasoning66
- Coding65
- Human preference67
- Multimodal61
Benchmark results
One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.
Reasoning
| Benchmark | default | Source |
|---|---|---|
| LMArena Hard Prompts | 1484#49 | LMArena |
Coding
| Benchmark | default | Source |
|---|---|---|
| LMArena Coding | 1508#50 | LMArena |
Human preference
| Benchmark | default | Source |
|---|---|---|
| LMArena Text | 1471#39 | LMArena |
Multimodal
| Benchmark | default | Source |
|---|---|---|
| LMArena Vision | 1260#42 | LMArena |
Where to run it
Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.
| Provider | Speed | First token | Input $/M | Output $/M | Context | Quantisation |
|---|---|---|---|---|---|---|
| SpaceXAI | 329 tok/s | 6.71 s | $1.25 | $2.50 | 2M | – |
What a task costs
Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.200 per 1M. Reasoning tokens are not modelled.
| Workload | Tokens in / out | Cost | With caching | Time |
|---|---|---|---|---|
| Chat reply | 400 / 300 | $0.0013 | $0.0009 | 7.6 s |
| Summarise a 30-page report | 12,000 / 600 | $0.017 | $0.0071 | 8.5 s |
| Code edit | 6,000 / 1,500 | $0.011 | $0.0065 | 11.3 s |
| Agentic coding session | 60,000 / 4,000 | $0.085 | $0.038 | 18.9 s |
| Structured extraction | 2,000 / 200 | $0.0030 | $0.0014 | 7.3 s |
See also
Data as of 9 Sept 2026. Compare with another model.