Skip to main content

​
Kimi (Moonshot AI)

Uses SSE streaming with OpenAI-compatible tool-calling format. Supports vision (base64 images) and reasoning content — everything from k2.5 onward is natively multimodal, no -vision variant needed. Best for: Agentic workflows, long-context tasks (K3 runs a 1M-token window), 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

​
Reasoning modes

How this model reasons is set in the model card beside the chat input — hover the model switch to preview the card, click to pin it open. The top chip row, labelled Thinking, is the control: pick a chip and it applies from your next message. 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 chip reads Normal) — 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.

​
The chip row

The active chip is tinted; the rest sit quiet. Each model shows only the chips it genuinely supports — a model that always reasons has no Off, a model with a single mode shows that one chip inert, and a model that can’t reason at all replaces the row with “Reasoning is not supported by this model.” Wolffish remembers your choice per model. (Before v1.0.236 this was a colour-coded brain button on the composer; it moved into the model card, beside the Single/Workflow row, so every model knob sits in one panel.) On Kimi: K3 is effort-capable — Off / High / Max, driven by Moonshot’s reasoning_effort dial, and Off genuinely disables thinking (verified against the live API; Moonshot currently ships one real effort level, so High and Max behave alike until lower efforts land). 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 K3 is Moonshot’s frontier flagship, priced alongside the premium Western mid-tier (3.00/3.00 / 15.00) with a 1M-token window. The k2.x line beneath it keeps Kimi’s classic position — between the budget Chinese providers (DeepSeek, MiMo) and the premium Western providers (Anthropic, OpenAI) — offering strong reasoning at a mid-range cost. See Choosing a Provider for guidance on when to use which tier.