Skip to main content

Kimi (Moonshot AI)

POST https://api.moonshot.ai/v1/chat/completions
Uses SSE streaming with OpenAI-compatible tool-calling format. Supports vision (base64 images) and reasoning content. Best for: Agentic workflows, long-context tasks, reasoning-heavy workloads, and cost-efficient daily automations.

Getting an API Key

  1. Go to platform.moonshot.ai
  2. Sign up or log in
  3. Navigate to API Keys and create a new key
  4. Paste it into Wolffish → Settings → Models → Kimi

Models

ModelContextModesInput / Output (per MTok)CachedNotes
kimi-k2.6256KOff, On0.95/0.95 / 4.00$0.16Latest flagship. Vision + reasoning.
kimi-k2.5256KOff, On0.60/0.60 / 3.00$0.10Vision + reasoning.
kimi-k2.7-code256KOn— / —Code-focused. Reasoning always on.
kimi-k2.7-code-highspeed256KOn— / —Fast code variant. Reasoning always on.
moonshot-v1-auto128K1.00/1.00 / 3.00Auto-selects context tier.
moonshot-v1-128k128K2.00/2.00 / 5.00Long-context.
moonshot-v1-32k32K1.00/1.00 / 3.00Mid-context.
moonshot-v1-8k8K0.20/0.20 / 2.00Short-context, cheapest.

Reasoning modes

The brain icon next to the message box controls how this model reasons. Click it to cycle through the modes the selected model supports. Two separate ideas combine here:

Thinking — whether the model reasons

  • Off — the model answers immediately. Fastest and cheapest; ideal for simple, direct tasks.
  • On — the model first works through the problem in a dedicated reasoning pass before replying. Slower and uses more tokens, but markedly more accurate on multi-step, logical, or ambiguous tasks.

Effort — how hard it thinks

Only effort-capable models expose this; it applies once thinking is on.
  • High — standard reasoning depth. The right default for most agentic work.
  • Max — the model reasons longer and deeper for the hardest problems. More tokens and latency in exchange for higher quality on complex work.

Button states

StateColourMeaning
OffgrayThinking off — direct answer
OnblueThinking on — no effort control
HighpurpleThinking on, standard effort
MaxorangeThinking on, maximum effort
Each model shows only the states it genuinely supports. If a model always reasons (can’t be turned off) or has no effort control, the button reflects that and locks where there’s nothing to change. Wolffish remembers your choice per model. On Kimi: k2.x models are On / Off. The k2.x-code variants reason always-on (locked on). The older moonshot-v1 models don’t reason.
Kimi K2.6 sits between the budget Chinese providers (DeepSeek, MiMo) and the premium Western providers (Anthropic, OpenAI) on price — offering strong reasoning at a mid-range cost. See Choosing a Provider for guidance on when to use which tier.