# Grok 4.1 Fast (Non-Reasoning) API prices

Grok 4.1 Fast (Non-Reasoning) (grok) — 2.0M context, 2.0M max output.
9 metered per-token offers from 11 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Jiekou.AI | $0.18 | $0.45 | — | 2.0M |
| Abacus | $0.2 | $0.5 | — | 2.0M |
| Azure | $0.2 | $0.5 | $0.05 | 128k |
| FrogBot | $0.2 | $0.5 | $0.05 | 2.0M |
| Helicone | $0.2 | $0.5 | $0.05 | 2.0M |
| DevPass (LLM Gateway) | $0.2 | $0.5 | $0.05 | 2.0M |
| LLM Gateway | $0.2 | $0.5 | — | 2.0M |
| Perplexity Agent | $0.2 | $0.5 | $0.05 | 2.0M |
| Vercel AI Gateway | $0.2 | $0.5 | $0.05 | 1.0M |

## Summary

- Cheapest input: $0.18 per 1M tokens (Jiekou.AI)
- Cheapest output: $0.45 per 1M tokens (Jiekou.AI)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2025-11-19
- Inputs: audio, image, pdf, text, video

HTML page: https://llmprice.gitlab.io/models/grok-4-1-fast-non-reasoning/
Full dataset: https://llmprice.gitlab.io/data/catalog.json