X Ai
Grok 4 Fast
Grok 4 Fast is xAI's latest multimodal model with SOTA cost-efficiency and a 2M token context window. It comes in two flavors: non-reasoning and reasoning. Read more about the model on xAI's [news post](http://x.ai/news/grok-4-fast). Reasoning can be enabled/disabled using the `reasoning` `enabled` parameter in the API. [Learn more in our docs](https://openrouter.ai/docs/use-cases/reasoning-tokens#controlling-reasoning-tokens)
- Input / 1M tokens
- $0.200
- Output / 1M tokens
- $0.500
- Context window
- 2M tokens
- Provider
- X Ai
- Cached input / 1M
- $0.050
- Knowledge cutoff
- 2025-09-30
Performance
Median streaming throughput and first-token latency measured by Artificial Analysis.
- Output tokens / sec
- 196 t/s
- Time to first token
- 0.35s
Benchmarks
Intelligence, coding, and math indexes plus the underlying evaluation scores.
- Intelligence Index
- 23
- Coding Index
- 19
- Math Index
- 41
- MMLU-Pro
- 73.0%
- GPQA
- 60.6%
- HLE
- 5.0%
- LiveCodeBench
- 40.1%
- SciCode
- 32.9%
- MATH-500
- —
- AIME
- —
Benchmarks via Artificial Analysis