[ xai ]
Grok Build 0.1
Billed at the provider's list price, with no markup. Pay per token in USDF, with no subscription and no minimum. Streaming and the OpenAI-compatible request format are supported.
No route to this model is enabled right now. Requests for it are refused with the error code model_unavailable before any balance is held, so nothing is charged. The listed prices apply once a route is enabled.
Input
$1.00
$ / 1M tokens
Output
$2.00
$ / 1M tokens
Cached input
$0.20
$ / 1M tokens
Context window
256,000
tokens
Prompts above 199,999 tokens bill the whole request at $2.00/M input and $4.00/M output, $0.40/M cached input.
- Model ID
- grok-build-0.1
- Modality
- text
- Unit
- USD per 1M tokens
- Status
- Unavailable
- Last verified
- —
- Endpoints
- /v1/chat/completions
- Context window
- 256,000 tokens
- Max output
- 128,000 tokens
- Pricing basis
- List price
- Cache write (5 min)
- —
- Cache write (1 h)
- —
- Routes enabled
- 0 of 1
- Price sheet
- 2026-10-09.1
Routes
| Provider | Enabled | Upstream input | Upstream output |
|---|---|---|---|
| xai | No | $1.00 | $2.00 |
Make your first request
Use any OpenAI-compatible SDK. Change the base URL, keep everything else. Responses include a receipt with the exact cost.
No account: send the same request to /x402/v1/chat/completions without credentials and the gateway answers 402 with the quote. Pay per request.
This model has no enabled route right now, so the request below is refused with model_unavailable until a route is enabled. Nothing is charged for a refused request.
curl https://api.usdf.fi/v1/chat/completions \
-H "Authorization: Bearer $FOUNDRY_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "grok-build-0.1", "messages": [{"role": "user", "content": "Hello"}]}'