Kimi K2 Thinking
Kimi reasoning model for long-horizon research, planning, and tool use
Cheapest input
$0.3
$/MTok · models.dev
Cheapest output
$1.20
$/MTok
Context
262K
tokens
Offers
12
3 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestmoonshotai/kimi-k2-thinking | NanoGPT | $0.3 | $1.20 | $0 | 256K |
| models.devmoonshotai/kimi-k2-thinking | Vercel AI Gateway | $0.47 | $2 | $0.141 | 216K |
| models.devmoonshotai/Kimi-K2-Thinking | IO.NET | $0.55 | $2.25 | $0.275 | 33K |
| models.devmoonshotai/Kimi-K2-Thinking | Hugging Face | $0.6 | $2.50 | $0.15 | 262K |
| models.devmoonshotai/kimi-k2-thinking | Kilo Gateway | $0.6 | $2.50 | $0.15 | 262K |
| models.devmoonshotai/kimi-k2-thinking | Merge Gateway | $0.6 | $2.50 | $0 | 262K |
| models.devkimi-k2-thinking | Moonshot AI | $0.6 | $2.50 | $0.15 | 262K |
| models.devmoonshotai/kimi-k2-thinking | Novita AI | $0.6 | $2.50 | $0.15 | 262K |
| OpenRoutermoonshotai/kimi-k2-thinking | OpenRouter | $0.6 | $2.50 | $0.15 | 262K |
| models.devmoonshotai/kimi-k2-thinking | ZenMux | $0.6 | $2.50 | $0.15 | 262K |
| models.devmoonshotai/Kimi-K2-Thinking | Meganova | $0.6 | $2.60 | $0 | 262K |
| LiteLLMmoonshotai/Kimi-K2-Thinking | — | $0.8 | $1.20 | $0.08 | — |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Knowledge cutoff: 2024-08Released: 2025-11-06Family: kimi-thinking
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence17.3
- AA coding21
- AA agentic1.8
Sources: Arena AI, Artificial Analysis. See /benchmarks.