K2-Think
by LLM360Chat
Kimi reasoning model for long-horizon research, planning, and tool use
- Context
- 128K tokens
- Max output
- 32,768 tokens
- Released
- 2025-07-26
- Weights
- Open
llm360/k2-think
Specifications
Full facts as recorded, incl. what is unknown.
- Released
- 2025-07-26
- Weights
- Open
- Input
- Text
- Output
- Text
- Context window
- 128,000 max across endpoints
- Max output
- 32,768
- Providers
- 0 + 1 gateway, not counted as providers
- Epoch Capabilities Index
- not evaluated
- Direct price range
- $0.17 in at NanoGPT, via gateway, fees not verified
More details
- Last updated
- 2025-07-26
- Knowledge cutoff
Capabilities
Across all endpoints: supported if any endpoint supports it.
- Tool calling
- Parallel toolsunknown
- Structured output
- Reasoning
- Image input
- PDF input
- Audio input
- Audio outputunknown
- Video input
- Prompt cachingunknown
- Web searchunknown
- Computer useunknown
- System messagesunknown
- Assistant prefillunknown
- Temperatureunknown
- Streamingunknown
- Attachments
Endpoints
One row per provider and variant; gateways are listed separately.
Loading endpoints…
Cost calculator
Loading endpoints…
Similarly priced models
Blended rate per 1M tokens, each at its own cheapest provider (10M input : 2M output mix).
| Model | Blended/1M | In/1M | Out/1M | Context | vs K2-Think |
|---|---|---|---|---|---|
| Phi-4-MiniMicrosoft | $0.255 | $0.17 | $0.68 | 131K | +0% |
| Qwen3-Next 80B-A3B InstructAlibaba (Qwen) | $0.258 | $0.09 | $1.10 | 131K | +1% |
| Qwen3.8 Flash NextAlibaba (Qwen) | $0.25 | $0.20 | $0.50 | 262K | −2% cheaper |
| Grok-4.1-FastxAI | $0.25 | $0.20 | $0.50 | 2M | −2% cheaper |
| Grok 4 Fast Non-ReasoningxAI | $0.25 | $0.20 | $0.50 | 2M | −2% cheaper |
| Mistral SabaMistral AI | $0.265 | $0.199 | $0.595 | 32.8K | +4% |
| Qwen3.5 122B-A10BAlibaba (Qwen) | $0.244 | $0.113 | $0.901 | 262K | −4% cheaper |
| Nemotron Nano 12B v2 VLNVIDIA | $0.267 | $0.20 | $0.60 | 131K | +5% |
Heads up: prices are indicative list rates scraped from provider pricing pages; verify with the provider before relying on them. Report incorrect data for this model