Kimi K3 Fast
by AbliteratedLLM · family kimi-k3 · listed Jul 2026RTVW
Multimodal Kimi model with 1M context and toggleable max-effort thinking for long-horizon agent work
Current rates USD per 1M tokens
Input$4.05
Output$20.25
Cache read$0.405
Cache write—
Against the market
On the record
- Model id
kimi-k3-fast- Context window
- 1.0M tokens
- Max output
- 1.0M tokens
- Input modalities
- text, image
- Output modalities
- text
- Reasoning
- yes
- Tool calls
- yes
- Open weights
- yes
- Knowledge cutoff
- —
- Released
- 2026-07-16
- Last updated
- 2026-07-16
- Provider docs
- abliteratedllm.dev/docs/models
Back of the envelope
≈
Also listed at
- DevPass (LLM Gateway)$4.50 in · $22.50 out
- Fireworks AI$4.50 in · $22.50 out
- LLM Gateway$4.50 in · $22.50 out
- Pioneer$4.50 in · $22.50 out
- Vercel AI Gateway$6.00 in · $22.50 out
- Kilo Gateway$6.00 in · $22.50 out