Kimi K2.6
Open-weights agentic MoE (1T total / 32B active) released April 2026; strong on SWE-Bench-style coding tasks. Prices vary by provider — confirm on Moonshot's rate card. Superseded July 2026 by Kimi K3, Moonshot's 2.8-trillion-parameter flagship with a 1M-token context and native video input.
Kimi K2.6 strengths
- Open weights
- Strong agentic coding
- Cost-effective
- Long-horizon task handling
Pricing & context
| Context window | 262K tokens (64K max output) |
| Input price /1M | ≈$0.60 |
| Output price /1M | ≈$2.50 |
| Modalities | text, image |
Cost guide: a typical call of about 10K input + 2K output tokens costs roughly $0.011 at list prices. Worth modelling against cheaper tiers before committing high-volume traffic.
When to choose Kimi K2.6
Kimi K2.6 is best for open-model coding agents and budget-conscious agentic pipelines. If your workload is more cost-sensitive, weigh it against gpt-oss-120b (≈$0.03 input /1M) first.
Kimi K2.6 FAQ
How much does Kimi K2.6 cost?
Kimi K2.6 is priced at ≈$0.60 per 1M input tokens and ≈$2.50 per 1M output tokens (public API list price), with a 262K tokens (64K max output) context window. A typical call of about 10K input and 2K output tokens costs roughly $0.011.
What is Kimi K2.6 best for?
Kimi K2.6 by Moonshot AI is best for open-model coding agents and budget-conscious agentic pipelines.
How does Kimi K2.6 pricing compare to Llama 4 Maverick?
Kimi K2.6 input costs ≈$0.60 per 1M tokens versus ≈$0.15 for Llama 4 Maverick, roughly 4.0x more expensive on input. Output is ≈$2.50 vs ≈$0.60.
Is Kimi K2.6 multimodal?
Kimi K2.6 supports text, image.
Other models
All models →| 01 | Claude Fable 5 | Anthropic | $10.00 | → |
| 02 | Claude Opus 5 | Anthropic | $5.00 | → |
| 03 | GPT-5.6 Sol | OpenAI | $5.00 | → |
| 04 | GPT-5.5 | OpenAI | $5.00 | → |