# Kimi K3 Fast API prices

Kimi K3 Fast (kimi-k3) — 1.0M context, 1.0M max output.
5 metered per-token offers from 5 provider(s), in USD per 1M tokens.

| Provider | Input $/1M | Output $/1M | Cache read $/1M | Context |
| --- | --- | --- | --- | --- |
| Neuralwatt | $3 | $15 | $0.3 | 1.0M |
| Fireworks AI | $4.5 | $22.5 | $0.45 | 1.0M |
| LLM Gateway | $4.5 | $22.5 | $0.45 | 1.0M |
| Venice AI | $4.5 | $22.5 | $0.45 | 1.0M |
| Vercel AI Gateway | $4.5 | $22.5 | $0.45 | 1.0M |

## Summary

- Cheapest input: $3 per 1M tokens (Neuralwatt)
- Cheapest output: $15 per 1M tokens (Neuralwatt)
- First-party: not listed separately
- Free offers: none
- Subscription plans (not per-token): none
- Released: 2026-07-16
- Inputs: image, pdf, text, video

HTML page: https://llmprice.gitlab.io/models/kimi-k3-fast/
Full dataset: https://llmprice.gitlab.io/data/catalog.json