xAI · 2026-05-28 · major
Grok Build 0.1 Lands on the xAI API in Public Beta — 256K Context, $1/$2 per 1M Tokens, 100+ Tokens/Sec for Agentic Coding
xAI exposes the coding-specialized model that powers the Grok Build CLI as a standalone API endpoint, with text+image inputs, function calling, structured outputs, and 256K context.
xAI's coding-focused model goes from CLI-only to a public-beta API at $1 in, $2 out per million tokens.
Key specs
| Context window | 256K tokens |
|---|---|
| Input | $1.00 / 1M tok |
| Cached input | $0.20 / 1M tok |
| Output | $2.00 / 1M tok |
| Throughput | 100+ tok/s |
| Rate limit | 1,800 req/min, 10M tok/min |
What is it?
Grok Build 0.1 is xAI's coding-specialized model — the same engine that powers the Grok Build CLI launched earlier in May. The public-beta API exposes it directly, so any agent framework, IDE plugin, or autonomous build pipeline can hit it as a regular xAI endpoint instead of going through the CLI wrapper.
How does it work?
The model accepts text and image inputs (it can read diagrams, UI mockups, or error screenshots), serves output at 100+ tokens/sec, and runs a 256K-token context window. xAI exposes native function calling, structured outputs, and reasoning, with the model trained specifically for agentic coding tasks including web development, debugging, and MCP integration. Public-beta rate limits start at 1,800 req/min and 10M tok/min in us-east-1 and eu-west-1.
Why does it matter?
Coding agents have largely been priced and rate-limited around Claude and GPT models. A 100+ tok/s coding model at $1/$2 per million tokens gives builders a third independent provider to spread cost and capacity across, and the 256K context handles the full file trees most agentic loops need without aggressive trimming.
Who is it for?
Developers building coding agents, IDE plugins, or autonomous build pipelines.
Try it
model id `grok-build-0.1` on the xAI API