Kimi K2.6 API pricing
As of October 21, 2026, MoonshotAI Kimi K2.6 costs $0.65 per million input tokens and $3.41 per million output tokens through OpenRouter, with cached input at $0.15 per million.
Kimi K2.6 benchmarks and specs · Every Moonshot AI model's price
- Input, per million tokens$0.65
- Output, per million tokens$3.41
- Cached input, per million$0.15
- Context window262K tokens
- Max output236K tokens
- Output speedNot measured
What a request costs
Three fixed token mixes at the list price, without cache or batch discounts. For a whole month, use the calculator.
| Workload | Tokens | One request | 1,000 requests | Fits the context window |
|---|---|---|---|---|
| Chat turn | 1K input + 500 output tokens | $0.0024 | $2.35 | Yes |
| Repository review | 50K input + 3K output tokens | $0.043 | $42.73 | Yes |
| Agent loop | 200K input + 10K output tokens | $0.164 | $164.10 | Yes |
| Solved coding task | One SWE-bench Verified attempt, divided by the share that succeed | $0.35 | $350.00 |
Price history
We read this price every day and have since October 15, 2026. It has not changed yet; any change will be listed here with its date.
- October 15, 2026 First recorded: $0.65 input, $3.41 output
Cheaper models as good as Kimi K2.6
Models within two points of Kimi K2.6 or above it on the Artificial Analysis Intelligence Index, with a lower output price. Cheapest first.
- Ling 3.1 Flash$0.225 Overall 41.1 against 27.0 · 93% cheaper output
- MiMo-V2.6-Flash$0.28 Overall 37.9 against 27.0 · 92% cheaper output
- Claude Haiku 5.5$0.50 Overall 43.4 against 27.0 · 85% cheaper output
- GLM 5.3 Flash$0.50 Overall 41.8 against 27.0 · 85% cheaper output
- GPT-6 Luna$0.50 Overall 38.1 against 27.0 · 85% cheaper output
Kimi K2.6 pricing questions
- How much does Kimi K2.6 cost per million tokens?
- $0.65 per million input tokens and $3.41 per million output tokens, as listed on OpenRouter on October 21, 2026.
- Does Kimi K2.6 support prompt caching?
- Yes. OpenRouter lists cached input at $0.15 per million tokens, against $0.65 for uncached input.
- Is there a cheaper model as good as Kimi K2.6?
- Ling 3.1 Flash scores 41.1 on the Artificial Analysis Intelligence Index, within two points of Kimi K2.6 or above it, and costs $0.225 per million output tokens.
- Has the price of Kimi K2.6 changed?
- Not since we started recording it daily on October 15, 2026.