The Orchestrator › Models › Moonshot AI
Moonshot AI: MoonshotAI: Kimi K2 Thinking
Kimi K2 Thinking is Moonshot AI’s most advanced open reasoning model to date, extending the K2 series into agentic, long-horizon reasoning. Built on the trillion-parameter Mixture-of-Experts (MoE) architecture introduced in...
Specifications
| Provider | Moonshot AI |
| Model ID | moonshotai/kimi-k2-thinking |
| Context window | 262K tokens (262,144) |
| Modalities | text → text |
| Tokenizer | Other |
| Router sources | OpenRouter, TrustedRouter |
| Released | 2025-11-06 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | Mandatory |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | OpenRouter | moonshotai/kimi-k2-thinking | $0.6 | $2.50 | 262K |
| standard | TrustedRouter | moonshotai/kimi-k2-thinking | $0.633 | $1.27 | 262K |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $0.633 | $1.27 | 262K |
| 2026-11-14 | $0.6 | $2.50 | 262K |
Capabilities
Agentic tool useStructured outputsReasoning (always on)256K+ context windowControllable reasoningNo content storage (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
frequency_penalty, include_reasoning, max_tokens, presence_penalty, reasoning, repetition_penalty, response_format, seed, stop, structured_outputs, temperature, tool_choice, tools, top_k, top_p