302ai
kimi-k2-thinking
Kimi reasoning model for long-horizon research, planning, and tool use
Cheapest input
$0.4
$/MTok · models.dev
Cheapest output
$2.50
$/MTok
Context
262K
tokens
Offers
9
2 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.devcheapestkimi-k2-thinking | OpenCode Zen | $0.4 | $2.50 | $0.4 | 262K |
| models.devkimi-k2-thinking | Helicone | $0.48 | $2 | $0 | 256K |
| models.devkimi-k2-thinking | Alibaba / Qwen | $0.574 | $2.29 | $0 | 262K |
| models.devkimi-k2-thinking | 302.AI | $0.575 | $2.30 | $0 | 262K |
| models.devkimi-k2-thinking | LLM Gateway | $0.6 | $2.50 | $0.06 | 262K |
| models.devkimi-k2-thinking | Moonshot AI (China) | $0.6 | $2.50 | $0.15 | 262K |
| LiteLLMkimi-k2-thinking | — | $0.6 | $2.50 | $0.06 | — |
| models.devkimi-k2-thinking | Cortecs | $0.656 | $2.73 | $0 | 262K |
| LiteLLMKimi-K2-Thinking | — | $0.8 | $1.20 | $0.08 | — |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- Out: text
Knowledge cutoff: 2025-06Released: 2025-09-05Family: 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.