One agent session
1M input tokens and 100K output tokens, no caching.
- Input1M x $0.95 = $0.95
- Output0.1M x $4 = $0.40
$1.35per session
Moonshot AI - Open weights
Kimi K2.6 pricing and specs
Kimi K2.6 is an open-weights model from Moonshot AI that costs $0.95 per 1M input tokens and $4 per 1M output tokens on the first-party API, with a 262K-token context window.
Last verified from platform.kimi.ai. All sources
- Input / 1M
- $0.95
- Output / 1M
- $4
- Context
- 262K tokens
- Weights
- Open
Pricing per 1M tokens
| Item | Price / 1M tokens |
|---|---|
| Input | $0.95 |
| Output | $4 |
| Cache read | $0.16 |
| Batch inputBatch requests | $0.57 |
| Batch outputBatch requests | $2.40 |
Note: Previous-generation general model that is still sold and priced. input is the cache-miss price and cache read is the cache-hit price. No separate cache write is billed. Batch prices are 60% of standard. The Batch page also lists a batch cache-hit price of $0.10 per 1M tokens, which has no field in this schema. max output is not stated because the docs give a max_tokens default of 32768 but no maximum. Supports both thinking and non-thinking modes. Takes text, image and video input. The release date is left blank because the changelog says only 'April 2026' and the launch blog gives no explicit date.
Specs
- Context window
- 262,144 tokens
- Provider
- Moonshot AI
- API model id
kimi-k2.6- Vercel AI Gateway id
moonshotai/kimi-k2.6- Weights
- Open weights
- License
- Modified MIT License (Hugging Face license tag: other)
- Weights download
- huggingface.co
What Kimi K2.6 costs in practice
Worked from the standard list rates above, with the math shown so you can swap in your own token counts.
A chat app
10,000 requests a day at 2K input and 500 output tokens each.
- Input20M x $0.95 = $19.00
- Output5M x $4 = $20.00
$39.00per day
$1,170.00 per 30-day month
The same session at a 90% cache hit
90% of the input is read from the prompt cache. The one-time cache write premium is not included.
- Cached input0.9M x $0.16 = $0.144
- Uncached input0.1M x $0.95 = $0.095
- Output0.1M x $4 = $0.40
$0.639per session
Compare with
| Model | Input / 1M | Output / 1M |
|---|---|---|
| Kimi K2.6 (this page) | $0.95 | $4 |
| Kimi K2.7 CodeMoonshot AI | $0.95 | $4 |
| DeepSeek V4 ProDeepSeek | $1.32 | $3.96 |
| Mistral Large 4Mistral AI | $1.36 | $4.18 |
| Gemini 3.6 FlashGoogle | $0.75 | $3.75 |
| Kimi K2.7 Code HighSpeedMoonshot AI | $1.90 | $8 |
| Kimi K3Moonshot AI | $3 | $15 |
Compare
Side-by-side pages with both models' prices, specs, cost examples and like-for-like benchmark rows.
Related reading
- Kimi K3 Is GA in GitHub Copilot: Pricing, Rollout, and What It Means for Model ChoiceKimi K3 is GA in GitHub Copilot at $3/$15 per million tokens, off by default for Business and Enterprise. Rollout details and what it means for model choice.
- Cloudflare Runs Kimi and GLM at Scale: FP8 KV Caches, INT4 Weights, and a Cache Safety NetCloudflare runs Kimi K2.6 and GLM 5.2 on Workers AI with FP8 KV caches, INT4 weights and a KV cache integrity check. What each technique buys on GPU fleets.
- AMD MI355X vs NVIDIA B200 vs B300 for Open-Weight ServingAMD MI355X vs NVIDIA B200 vs B300 for serving Kimi K3's about 1.5TB of open weights: verified specs, the Wafer benchmark, and cost per token for each.
- Kimi Linear: An Attention Architecture That Outperforms Full AttentionKimi Linear explained: Moonshot's KDA hybrid linear attention beat full attention with 75% less KV cache and up to 6x faster decoding at 1M context.
- Kimi K3 Weights Land on HuggingFace: 2.8T Open Frontier Model You Can Actually DownloadKimi K3 open weights are on HuggingFace: 2.8T parameters, 1M context, native MXFP4 and a ~1.63TB download. The specs, license terms and HN reaction.
- Kimi K3 in 10 Minutes: Moonshot AI's 2.8T Open Model, API Setup, Pricing, and BenchmarksKimi K3 from Moonshot AI is a 2.8T open model with a 1M-token context and an OpenAI-compatible API. How to call it, what it costs, and how it benchmarks.
FAQ
How much does Kimi K2.6 cost per million tokens?
Kimi K2.6 costs $0.95 per 1M input tokens and $4 per 1M output tokens on Moonshot AI's first-party API, per platform.kimi.ai on October 17, 2026. Per 1M tokens, cache reads cost $0.16, and the batch rate is $0.57 input and $2.40 output.
What is Kimi K2.6's context window?
Kimi K2.6 has a 262,144-token context window.
Are Kimi K2.6's weights open?
Yes. Kimi K2.6's weights are published at https://huggingface.co/moonshotai/Kimi-K2.6 under the Modified MIT License (Hugging Face license tag: other).
Sources
Last verified from platform.kimi.ai.
- https://platform.kimi.ai/docs/pricing/chat
- https://platform.kimi.ai/docs/guide/kimi-k2-6-quickstart
- https://platform.kimi.ai/docs/models.md
- https://platform.kimi.ai/docs/pricing/batch.md
- https://platform.kimi.ai/docs/platform-changelog.md
- https://www.kimi.ai/blog/kimi-k2-6
- https://huggingface.co/moonshotai/Kimi-K2.6
Newsletter
Get model price changes as they ship
One email per week. New model releases, price cuts and what they mean for your bill.