Compare
Grok API pricing, 40% under xAI.
Draftworks serves Grok 4.6 through the same OpenAI-compatible API as the rest of the catalog: $1.20 per million input tokens and $3.60 per million output on the Base tier, against xAI's published $2.00 and $6.00. No xAI account, no separate integration.
| Per 1M tokens | xAI list | Draftworks Base | Draftworks Scale |
|---|---|---|---|
| Grok 4.6grok-4.6 | |||
| Input | $2.00 | $1.20 | $1.20 |
| Cached input | $0.50 | $0.30 | $0.30 |
| Output | $6.00 | $3.60 | $3.60 |
xAI column is xAI's published API price. Base applies from your first dollar; Scale applies permanently at $5,000 lifetime purchases. The same discount covers every model in the catalog.
Common questions.
- How much does the Grok API cost on Draftworks?
- Grok 4.6 is $1.20 per 1M input tokens, $0.30 per 1M cached input, and $3.60 per 1M output on the Base tier, against xAI's list of $2.00, $0.50, and $6.00. Both Base and Scale pay 40% under list.
- Is this the real Grok 4.6?
- Yes. The model is served from Azure's Grok fleet, responses report the model id, and every response carries an Ed25519-signed receipt over the model id, token counts, and hashes of the exact request and response bytes.
- Do I need an xAI account?
- No. One Draftworks API key covers Grok 4.6 alongside the GPT-6 Astra, Claude, Kimi K3, and GLM 5.3, billed from one prepaid credit balance.
- Which endpoint does Grok use?
- POST /v1/chat/completions with the standard OpenAI request shape, including streaming and tool calls. Grok's reasoning tokens are billed as output, exactly as xAI meters them.
- What is the context window?
- 500,000 tokens. Requests with at least 200,000 input tokens use double the standard input, cached-input, and output rates.