Kimi K2.6 logo
Chat & reasoning

Kimi K2.6

Moonshot's K2.6 — open-weights, 80%+ SWE-bench Verified, top-tier agentic reasoning.

Try Kimi K2.6
Context
262K
Type
Chat & reasoning
Reasoning
Model-set
Streaming
Yes

Capabilities

StreamingReasoningTool use

Pricing

Input$0.95 / 1M tokens
Cached input$0.16 / 1M tokens
Output$4 / 1M tokens

Provider-equivalent rates used for credits. Higher reasoning effort can consume more output tokens; it has no separate fixed multiplier. One credit equals 1¢, with a one-credit minimum per completed run and the aggregate rounded up once.

Provider pricing source · verified 2026-07-20

Kimi K2.6: frequently asked questions

What is Kimi K2.6?
Moonshot's K2.6 — open-weights, 80%+ SWE-bench Verified, top-tier agentic reasoning. You can try Kimi K2.6 on TryAI without a separate provider account.
How much does Kimi K2.6 cost on TryAI?
Kimi K2.6 uses these provider-equivalent rates: Input: $0.95 / 1M tokens, Cached input: $0.16 / 1M tokens, Output: $4 / 1M tokens. One TryAI credit equals one cent of usage; completed runs have a one-credit minimum and the aggregate cost is rounded up once.
What can Kimi K2.6 do?
Kimi K2.6 supports Streaming, Reasoning, Tool use with a context window of about 262K tokens.
How do I try Kimi K2.6?
Create a free TryAI account, pick Kimi K2.6 from the model selector, and start generating in seconds.

Related models