Kimi K2 Thinking Turbo
Last verified August 3, 2026 · Moonshot pricing ↗$1.15/1M input · $8.00/1M output · 262K context · Moonshot
Kimi K2 Thinking Turbo last cost $1.15 per 1M input tokens and $8.00 per 1M output tokens from Moonshot, with a 262K-token context window. A typical chat reply (1,500 tokens in, 400 out) costs $0.0049, or $49.25 per 10,000 requests.
Not generally available
Moonshot has shut Kimi K2 Thinking Turbo down. You cannot buy it at the rate below. The price is kept so past spend and old estimates still reconcile, and it is excluded from the calculator’s default model list and from every ranking.
Moonshot’s own page ↗Count Tokens
Estimate Monthly Cost
Monthly Cost Estimator
Pick a preset above or enter custom usage
What Kimi K2 Thinking Turbo Costs Per Request
At $1.15 per 1M input and $8.00 per 1M output tokens, before caching or batch discounts.
| Workload | Input / output tokens | Per request | Per 10,000 requests |
|---|---|---|---|
| Chat reply | 1,500 / 400 | $0.0049 | $49.25 |
| RAG answer over retrieved docs | 8,000 / 600 | $0.014 | $140.00 |
| Coding-agent step | 30,000 / 2,000 | $0.051 | $505.00 |
Kimi K2 Thinking Turbo vs Similarly Priced Models
Nearest buyable models by price, with the RAG answer above (8,000 in / 600 out) priced on each.
| Model | Input /1M | Output /1M | Context | RAG answer |
|---|---|---|---|---|
| Kimi K2 Thinking Turbo Moonshot | $1.15 | $8.00 | 262K | $0.014 |
| Kimi K3.1 Pro Moonshot | $2.00 | $10.00 | 1.0M | $0.022 |
| Qwen3.6-Max-Preview Alibaba | $1.30 | $7.80 | 262K | $0.015 |
| Mistral Medium 3.5 Mistral | $1.50 | $7.50 | 256K | $0.017 |
Alternatives to Kimi K2 Thinking Turbo
Pricing Details
Price History
Frequently Asked Questions
Common questions about Kimi K2 Thinking Turbo pricing and usage