Grok 4.1 Fast (Non-Reasoning)
by Azure · family grok · listed Jun 2025TV
Fast Grok model for responsive chat, reasoning, and tool-assisted work
Current rates USD per 1M tokens
Input$0.20
Output$0.50
Cache read$0.05
Cache write—
Against the market
On the record
- Model id
grok-4-1-fast-non-reasoning- Context window
- 128K tokens
- Max output
- 8K tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- no
- Tool calls
- yes
- Open weights
- no
- Knowledge cutoff
- —
- Released
- 2025-06-27
- Last updated
- 2025-06-27
Back of the envelope
≈
Also listed at
- Jiekou.AI$0.18 in · $0.45 out
- Helicone$0.20 in · $0.50 out
- LLM Gateway$0.20 in · $0.50 out
- Perplexity Agent$0.20 in · $0.50 out
- 302.AI$0.20 in · $0.50 out
- FrogBot$0.20 in · $0.50 out
- DevPass (LLM Gateway)$0.20 in · $0.50 out
- Abacus$0.20 in · $0.50 out