Moonshot AI · Released Apr 21, 2026Kimi K2.6
Multimodal Kimi workhorse for agent loops, coding tasks, and visual context.
- Capability
- 151.1ECI · #45 of 148
- Input
- $0.95per 1M tokens
- Output
- $4.00per 1M tokens
- Context
- 262K262K max output
What it costs
- Input
- $0.95per million tokens
- Output
- $4.00per million tokens
- Cached input
- $0.16per million tokens
- Blended (3:1)
- $1.71pricier than 66% of priced models
Typical monthly bills
| Monthly usage | Estimated cost |
|---|---|
| Side project2M input + 0.5M output tokens | $3.90 |
| Team assistant25M input + 5M output tokens | $43.75 |
| Production app250M input + 50M output tokens | $437.50 |
Official Moonshot AI API price, as listed on models.dev.
Independent benchmarks
#45 of 148 scored models
The shaded band is Epoch AI’s confidence range (149.1–152.8); the tick marks the median scored model.
Scores from Epoch AI, run independently of Moonshot AI.
The details
- Lab
- Moonshot AI
- Released
- Apr 21, 2026
- Knowledge cutoff
- Jan 2025
- Context window
- 262,144 tokens
- Max output
- 262,144 tokens
- Inputs
- Text, Images, Video
- Output
- Text
- Reasoning
- Can be switched on or off
- Tool calling
- Yes
- Structured output
- Yes
- Weights
- Open weights
- API model ID
kimi-k2.6on Moonshot AI- Availability
- 46 API providerslisted on models.dev
What Moonshot AI claims
Published by the lab at launch. Settings vary, so compare these only with care.
More from Moonshot AI
About Kimi K2.6
How much does Kimi K2.6 cost?
Kimi K2.6 costs $0.95 input / $4.00 output per million tokens (official Moonshot AI API price). Cached input is $0.16 per million tokens. At a 3:1 input-to-output mix that is $1.71 per million tokens, more expensive than 66% of the 360 priced models we track.
What is the context window of Kimi K2.6?
Kimi K2.6 accepts up to 262,144 tokens per request and can write up to 262,144 tokens in one response.
How good is Kimi K2.6?
Epoch AI gives Kimi K2.6 a Capabilities Index score of 151.1 (likely range 149.1–152.8), ranking it #45 of 148 models Epoch has scored. Epoch AI benchmark results: GPQA Diamond 90.8%, FrontierMath Tiers 1–3 57.2%, OTIS Mock AIME 2024–2025 96.1%, SWE-bench Verified 76.7%, SimpleQA Verified 34.9%.
Is Kimi K2.6 open source?
Yes. Moonshot AI publishes the weights, so it can be downloaded and self-hosted.
What inputs does Kimi K2.6 support?
Kimi K2.6 accepts text, images and video and replies in text. It is a reasoning model, supports tool calling and can return structured JSON output.
When was Kimi K2.6 released?
Moonshot AI released Kimi K2.6 on Apr 21, 2026. Its training data runs to Jan 2025.
What are the best alternatives to Kimi K2.6?
The closest current models from other labs on capability, price and release date are Grok 4.20 (Reasoning) (xAI, ECI 152.0, $1.25 / $2.50), GLM-5.1 (Z.ai (Zhipu), ECI 149.9, $1.40 / $4.40), GPT-5.4 mini (OpenAI, ECI 148.8, $0.75 / $4.50) and Qwen3.6 Max Preview (Alibaba (Qwen), ECI 149.2, $1.30 / $7.80).