Kimi K2.6
Summary
Kimi K2.6 is an open-weight language model from Moonshot AI, released on 20 Apr 2026. It accepts text, images and video and generates text, with a 262K-token context window and up to 262K output tokens per response. As of 18 Nov 2026, the lowest listed API price is $0.65 per million input tokens and $3.41 per million output tokens (OpenRouter), across 8 providers we track.
Multimodal Kimi workhorse for agent loops, coding tasks, and visual context
Last verified 18 Nov 2026. Every figure on this page links to its source.
Specifications
| Developer | Moonshot AI |
|---|---|
| Release date | 20 Apr 2026 [models.dev] |
| Status | Generally available [models.dev] |
| Weights | Open weights [Hugging Face] |
| License | modified-mit [Hugging Face] |
| Parameters | 1T [Hugging Face] |
| Context window | 262K (262,144 tokens) [models.dev] |
| Max output | 262K tokens [models.dev] |
| Knowledge cutoff | Jan 2025 [models.dev] |
| Input | Text, images and video [models.dev] |
| Output | Text [models.dev] |
| Reasoning mode | Yes [models.dev] |
| Tool calling | Yes [models.dev] |
| Structured output | Yes [models.dev] |
| Hugging Face | moonshotai/Kimi-K2.6 [Hugging Face] |
Kimi K2.6 API pricing by provider
USD per million tokens. Sorted by input price.
| Provider | Input | Output | Cached input | Context | Source |
|---|---|---|---|---|---|
| OpenRouter moonshotai/kimi-k2.6 | $0.65 | $3.41 | $0.15 | 262K | OpenRouter, 18 Nov 2026 |
| DeepInfra moonshotai/Kimi-K2.6 | $0.75 | $3.50 | $0.15 | 262K | models.dev, 18 Nov 2026 |
| SiliconFlow moonshotai/Kimi-K2.6 | $0.77 | $3.40 | $0.14 | 262K | models.dev, 18 Nov 2026 |
| Novita AI moonshotai/kimi-k2.6 | $0.80 | $3.40 | $0.16 | 262K | models.dev, 18 Nov 2026 |
| Moonshot AI API kimi-k2.6 | $0.95 | $4 | $0.16 | 262K | models.dev, 18 Nov 2026 |
| Azure AI Foundry kimi-k2.6 | $0.95 | $4 | – | 262K | models.dev, 18 Nov 2026 |
| Hugging Face Inference Providers moonshotai/Kimi-K2.6 | $0.95 | $4 | $0.16 | 262K | models.dev, 18 Nov 2026 |
| Vercel AI Gateway moonshotai/kimi-k2.6 | $0.95 | $4 | $0.16 | 262K | models.dev, 18 Nov 2026 |
Running Kimi K2.6 locally
Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.
| Quantization | Weights | Total, 8K context | Total, 32K context |
|---|---|---|---|
| Q4_K_M (4-bit) | 623 GB | 624 GB | 626 GB |
| Q8_0 (8-bit) | 1091 GB | 1092 GB | 1094 GB |
| FP16 / BF16 (16-bit) | 2054 GB | 2055 GB | 2057 GB |
At 4-bit with an 8K conversation, Kimi K2.6 needs about 624 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.
Frequently asked questions
What is the context window of Kimi K2.6?
Kimi K2.6 has a context window of 262,144 tokens (262K) and can generate up to 262,144 tokens in a single response, according to models.dev.
How much does the Kimi K2.6 API cost?
Through Moonshot AI API, Kimi K2.6 costs $0.95 per million input tokens and $4 per million output tokens. The lowest listed price is $0.65 input / $3.41 output through OpenRouter. Prices last verified 18 Nov 2026.
Is Kimi K2.6 open source?
Kimi K2.6 is an open-weight model: its weights are published on Hugging Face as moonshotai/Kimi-K2.6 under the modified-mit license. Check the license terms before commercial use.
When was Kimi K2.6 released?
Moonshot AI released Kimi K2.6 on 20 Apr 2026, according to models.dev.
Which providers offer Kimi K2.6?
We track Kimi K2.6 on 8 providers: OpenRouter, DeepInfra, SiliconFlow, Novita AI, Moonshot AI API, Azure AI Foundry, Hugging Face Inference Providers, Vercel AI Gateway.
How much VRAM does Kimi K2.6 need?
About 624 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 1092 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.
Similar models from other labs
Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.
| Model | Lab | Released | Context | Input $/1M | Output $/1M | Weights |
|---|---|---|---|---|---|---|
| Qwen3.6 27B | Alibaba (Qwen) | 22 Apr 2026 | 262K | $0.30 | $3.19 | Open |
| GLM-5.1 | Zhipu AI (Z.ai) | 7 Apr 2026 | 200K | $1 | $3.20 | Open |
| Qwen3.5 397B-A17B | Alibaba (Qwen) | 15 Feb 2026 | 262K | $0.45 | $3 | Open |
| Inkling | Thinkingmachines | 15 Jul 2026 | 256K | $1 | $4.05 | Open |
| GLM-5 | Zhipu AI (Z.ai) | 12 Feb 2026 | 205K | $0.95 | $2.55 | Open |
| Mistral Medium 3.5 | Mistral AI | 29 Apr 2026 | 262K | $1.50 | $7.50 | Open |
Change history
- No longer listed on cloudflare-workers-ai
- No longer listed on baseten
- Release date changed from 21 Apr 2026 to 20 Apr 2026
- OpenRouter price changed: input $0.47 → $0.65, output $2.45 → $3.41 per 1M tokens
- OpenRouter price changed: input $0.45 → $0.47, output $2.45 → $2.45 per 1M tokens
- OpenRouter price changed: input $0.44 → $0.45, output $2.45 → $2.45 per 1M tokens
- OpenRouter price changed: input $0.47 → $0.44, output $2.45 → $2.45 per 1M tokens
- OpenRouter price changed: input $0.95 → $0.47, output $4 → $2.45 per 1M tokens
Sources
- https://openrouter.ai/moonshotai/kimi-k2.6
- https://github.com/sst/models.dev/blob/dev/providers/moonshotai/models/kimi-k2.6.toml
- https://huggingface.co/moonshotai/Kimi-K2.6
- https://github.com/sst/models.dev/blob/dev/providers/deepinfra/models/moonshotai/Kimi-K2.6.toml
- https://github.com/sst/models.dev/blob/dev/providers/siliconflow/models/moonshotai/Kimi-K2.6.toml
- https://github.com/sst/models.dev/blob/dev/providers/novita-ai/models/moonshotai/kimi-k2.6.toml
- https://github.com/sst/models.dev/blob/dev/providers/azure/models/kimi-k2.6.toml
- https://github.com/sst/models.dev/blob/dev/providers/huggingface/models/moonshotai/Kimi-K2.6.toml
- https://github.com/sst/models.dev/blob/dev/providers/vercel/models/moonshotai/kimi-k2.6.toml