Skip to main content

​
xAI (Grok)

Uses SSE streaming with OpenAI-compatible tool-calling format. Supports vision (base64 images) and reasoning content. xAI offers Grok models with strong reasoning capabilities and competitive pricing. Since v1.0.251, Grok 4.6 is the flagship and the default picked when you connect xAI — frontier-class, 500K context, vision, at the same price as the 4.5 it succeeds. Grok 4.3 stays the value pick with a full 1M of context, and the Grok Build model is purpose-built for code generation at an attractive price point. Best for: Reasoning-heavy workflows, code generation, vision tasks, and agentic automations where you want a balance of capability and cost.

​
Getting an API Key

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

​
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 xAI: Grok’s effort knob is a five-rung ladder, not a low/high pair — a fact established in v1.0.251 by sweeping the parameter against the live API, which found a rung above High that had never been used. The three settings now land on distinct rungs, with Max reaching the top of the ladder. grok-4.6 and 4.5 reason always-on with High and Max as real, different depths; grok-4.3 adds Off; grok-4.20-reasoning and grok-build reason always-on with no effort control; the non-reasoning 4.20 variant has none.
Grok 4.6 is competitively priced against Anthropic and OpenAI while offering 500K context, vision, and frontier-class reasoning — and Grok 4.3 keeps a full 1M context at half the price. If you need a mid-tier provider with strong reasoning that’s cheaper than Claude or GPT, xAI is a solid choice.