Grok Code Fast 1 pricing
Grok Code Fast 1 API cost from xAI (Grok) — $1.00 per 1M input tokens and $2.00 per 1M output tokens. Alias of Grok Build 0.1; prompts ≥200K use 2× rates; Batch unsupported. Estimate your real monthly bill below, then compare it against every other model.
Balanced 256K context · all prices USD per 1M tokens, this price verified 2026-10-10.
Grok Build 0.1 alias and current billing bands
The official model card now lists grok-code-fast-1, grok-code-fast and grok-code-fast-1-0825 as aliases of grok-build-0.1. This page keeps its existing URL so older integrations and bookmarks lead to the current rates.
| Prompt size | Input / 1M | Cache reads / 1M | Output / 1M |
|---|---|---|---|
| Below 200,000 | $1.00 | $0.20 | $2.00 |
| 200,000 or more | $2.00 | $0.40 | $4.00 |
The official Markdown table specifies that reaching 200K triggers higher rates for all tokens in the request. The estimator below includes this boundary. A request with 200K fresh input and 1K output costs $0.404 at Standard rates; 1,000 such requests cost $404.
The model accepts text and image input, returns text, and has a 256,000-token context window. Batch is not supported. Separately confirmed Priority requests use a 2× premium; the estimates here exclude that premium and tool charges. No Flex discount is assumed.
Looking for the coding application's account plans? Read Grok Build pricing and subscription boundaries. The app's Grok 4.7 default has its own API rates.
Grok Code Fast 1 capabilities & limits
Representative specs for this tier — confirm exact limits in the xAI (Grok) docs.
API acting up? Check live xAI (Grok) status → · all AI API status
Call Grok Code Fast 1 from your code
The exact model string and endpoint to use. Works with the OpenAI SDK — just point base_url at the URL below.
grok-build-0.1https://api.x.ai/v1XAI_API_KEYcurl https://api.x.ai/v1/chat/completions \
-H "Authorization: Bearer $XAI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-build-0.1",
"messages": [{"role": "user", "content": "Hello"}]
}'Model strings follow each provider's naming convention; confirm the current id in the xAI (Grok) docs before relying on it.
What a Grok Code Fast 1 API call actually costs
Blended input + output cost at Grok Code Fast 1's list rates — useful yardsticks before you commit to volume.
Grok Code Fast 1 cost calculator
Enter your monthly volume to estimate the Grok Code Fast 1 bill. Runs entirely in your browser.
Input includes cache reads. At ≥200K input, all token rates double. Standard rates only; excludes Priority, paid tools, retries and taxes. Batch is unsupported. For the multi-model breakdown with the same exclusions, use the cost calculator.
xAI (Grok) models — Grok Code Fast 1 in context
How Grok Code Fast 1 prices against its siblings. Cheapest reference cost first.
| Model | Input /1M | Output /1M | Cost / call* | Context | Type |
|---|---|---|---|---|---|
| Grok 3 mini | $0.100 | $0.300 | $0.0004 | 128K | Fast / cheap |
| Grok 4 Fast 2M context | $0.200 | $0.500 | $0.0007 | 2M | Fast / cheap |
| Grok Code Fast 1 Alias of Grok Build 0.1; prompts ≥200K use 2× rates; Batch unsupported | $1.00 | $2.00 | $0.0030 | 256K | Balanced |
| Grok 4 Flagship | $3.00 | $15.00 | $0.018 | 256K | Flagship |
*Reference cost of one call with 1,000 input + 1,000 output tokens — a neutral yardstick. Use the calculator for your real usage. Cheapest row highlighted.
How Grok Code Fast 1 pricing works
Grok Code Fast 1 is billed per token: a lower input price of $1.00 per million tokens for everything you send, and a higher output price of $2.00 per million for everything the model generates. To turn that into a real Grok Code Fast 1 bill, multiply by your monthly request volume and average prompt/response length — the calculator above does exactly that.
Prompt caching is the biggest lever on your Grok Code Fast 1 cost: cached input tokens bill at just $0.200 per million — about 80% cheaper. If you reuse a long system prompt or context across calls, caching can dramatically cut the input portion of your bill.
List prices move fast — always confirm the current numbers on the official xAI (Grok) pricing page before relying on them for budgeting.
Grok Code Fast 1 pricing FAQ
Is Grok Code Fast 1 the same API model as Grok Build 0.1?
The current official model card lists grok-code-fast-1, grok-code-fast and grok-code-fast-1-0825 as aliases of grok-build-0.1. This API model is distinct from the Grok Build coding application and its current Grok 4.7 default.
What happens at exactly 200,000 prompt tokens?
The official Markdown price table applies the higher band at 200,000 prompt tokens: $2 input, $0.40 cached input and $4 output per million tokens, for the whole request. Below that boundary, rates are $1, $0.20 and $2.
Can I apply a Batch discount?
No. The Grok Build 0.1 model card says Batch API is not supported. The calculators use Standard token rates and exclude Priority processing, paid tools, retries and taxes.