Model reference · Synced 2025-04-29
kimi-k2-thinking
kimi-k2-thinking is an AI model from Kimi For Coding. 262K context window. Capabilities: reasoning, tool calling, open weights. Available on 25 providers. Cheapest listing: $0 input / $0 output per 1M tokens.
Quick facts
- Cheapest input: $0 per 1M tokens (Kimi For Coding)
- Cheapest output: $0 per 1M tokens
- Context window: 262K tokens
- Max output: 33K tokens
- Release date: 2025-11
- Knowledge cutoff: 2025-07
- Capabilities: reasoning, tool calling, open weights
- Provider count: 25
Provider pricing
Same model, different providers, different prices. Cheapest first.
| Provider | Input / 1M | Output / 1M | Context | Listed |
|---|---|---|---|---|
| Kimi For Coding | $0 | $0 | 262K | 2025-11 |
| Nvidia | $0 | $0 | 262K | 2025-11 |
| NanoGPT | $0.3 | $1.2 | 256K | 2025-11-06 |
| OpenCode Zen | $0.4 | $2.5 | 262K | 2025-09-05 |
| Deep Infra | $0.47 | $2 | 131K | 2025-11-06 |
| Vercel AI Gateway | $0.47 | $2 | 216K | 2025-11-06 |
| Helicone | $0.48 | $2 | 256K | 2025-11-06 |
| IO.NET | $0.55 | $2.25 | 33K | 2024-11-01 |
| Synthetic | $0.55 | $2.19 | 262K | 2025-11-07 |
| 302.AI | $0.575 | $2.3 | 262K | 2025-09-05 |
| OpenRouter | $0.6 | $2.5 | 262K | 2025-11-06 |
| Fireworks AI | $0.6 | $2.5 | 256K | 2025-11-06 |
| Hugging Face | $0.6 | $2.5 | 262K | 2025-11-06 |
| ZenMux | $0.6 | $2.5 | 262K | 2025-11-06 |
| NovitaAI | $0.6 | $2.5 | 262K | 2025-11-07 |
| Amazon Bedrock | $0.6 | $2.5 | 256K | 2025-12-02 |
| Baseten | $0.6 | $2.5 | 262K | 2025-11-06 |
| Moonshot AI (China) | $0.6 | $2.5 | 262K | 2025-11-06 |
| Azure Cognitive Services | $0.6 | $2.5 | 262K | 2025-11-06 |
| Meganova | $0.6 | $2.6 | 262K | 2025-11-06 |
| LLM Gateway | $0.6 | $2.5 | 262K | 2025-11-06 |
| Vertex | $0.6 | $2.5 | 262K | 2025-11-13 |
| Azure | $0.6 | $2.5 | 262K | 2025-11-06 |
| Moonshot AI | $0.6 | $2.5 | 262K | 2025-11-06 |
| Cortecs | $0.656 | $2.73 | 262K | 2025-12-08 |
Prices synced daily from models.dev + provider docs.
How to use this model
If you're picking kimi-k2-thinking for a project, the three things that matter most:
- Compare it side-by-side with one or two alternatives in the live comparison tool. Pricing differences matter more than benchmarks at scale.
- Pick the cheapest provider that meets your latency / SLA need. Big spread across providers for the same weights.
- Re-evaluate every 3 months. Frontier prices drop fast; a model that's cheapest today may not be in a quarter.
Related models
FAQ
How much does kimi-k2-thinking cost? $0 input / $0 output per 1M tokens at the cheapest listing. See the table above for other providers.
What is the context window? 262K tokens.
Which providers offer it? 302.AI, NanoGPT, OpenRouter, Fireworks AI, Kimi For Coding, IO.NET, Hugging Face, ZenMux, NovitaAI, Deep Infra, and others — see the full table above.
Where do these numbers come from? models.dev + provider documentation, synced daily. About the data.