AI models · xAI

Grok Build 0.1

Grok Build 0.1 is xAI's coding model and replaces the older grok-code-fast-1. xAI says it writes more than 100 tokens per second, and on the API it costs $1 input and $2 output, which makes it the cheapest Grok. It suits quick fixes, smaller tasks and agents that call tools many times in a row. For big projects, the newer Grok 4.7 is the better pick.

Strengths

  • The cheapest Grok on the API: $1 input and $2 output per million tokens.
  • xAI says it is their fastest coding model, writing more than 100 tokens per second.
  • Trained specifically for coding agents: web development, debugging and working with tools over MCP.
  • It also works in other companies' tools, such as Cursor, Kilo Code, OpenCode and OpenClaw.

Weaknesses

  • Its 256K-token context window is smaller than that of the other current Grok models (500K to 1 million).
  • xAI released it in May 2026 as early access and a public beta. It does not support the Batch API.
  • It is no longer the default in the Grok Build tool: Grok 4.5 took over in July 2026 and today the default is Grok 4.7. The grok-build-latest alias points to Grok 4.5.
  • It runs only in US data centres, with no EU region.

Best for

  • fast coding agents
  • cheap repeated tool calls
  • coding right inside your code editor

Not ideal for

  • analysing long documents
  • complex projects where an agent works for hours

How to use it in Europe

Developers use it through the xAI API, available across Europe, or in tools such as Cursor, Kilo Code and OpenCode. In May 2026 it powered the Grok Build tool, but since July xAI has used newer models there by default, currently Grok 4.7. Data is processed in the US only.

Price compared with similar models

0.3 1 3 10 30 Ministral 3 14B0.2 Llama 4 Scout0.24 Qwen3.8-Flash0.47 Claude Haiku 5.50.5 Nemotron 3.5 Super VL0.5 GPT-6 Luna0.5 GLM-5.3-Flash0.5 Mistral Small 40.6 Llama 4 Maverick0.65 Codestral 25.080.9 Beam 1.01 DeepSeek V4.1 Flash1.2 Muse Glimmer 30B1.2 Mistral Large 31.5 Qwen3.7-Plus1.6 Grok Build 0.12 Gemini 3.5 Flash-Lite2.5 Grok 4.32.5 Qwen3.8-27B3 Gemini 3.8 Flash3.75 DeepSeek V4 Pro3.96 Mistral Large 44.18 Muse Spark 1.34.25 Muse Spark Open4.25 GLM-5.34.4 GPT-6.1 Terra5 Qwen3.8-Max6 Qwen3.8-2.4T-A95B6 Grok 4.76 Mistral Medium 3.57.5 Claude Sonnet 5.510 Gemini 4 Carbon10 Gemini 4 Argon10 Kimi K3.1 Pro10 GPT-6.1 Sol10 Kimi K315 Claude Opus 5.520 Muse Wonder20 Claude Fable 5.150 GPT-6 Astra50
Output price in USD per 1M tokens (log scale). Lighter bars are open-weight models.

Benchmark results

BenchmarkScoreSource
Output speed100+ tokens/sx.ai ↗ (vendor-reported), May 2026

Benchmarks cover only a narrow slice of ability and vendors often report them at their best settings. Treat them as a rough guide.

More models from this vendor

  • Grok 4.7: xAI's strongest model for agentic coding and professional work, with cheaper output than most rivals.
  • Grok 4.3: An older, cheaper Grok from April 2026 with a 1-million-token window. Good for lots of low-cost API calls.

Similar models from other vendors

  • Codestral 25.08 (Mistral AI): Mistral's model for code completion right in your editor. Fast and cheap, but dated for autonomous coding agents.
  • GLM-5.3 (Z.ai (Zhipu AI)): Z.ai's open model for agentic coding, also offered through Mistral's European API with data kept in the EU.

Sources

Prices and models change often. The data comes from official vendor pricing pages and documentation, and every page shows when it was last checked. Before a larger purchase, confirm the price with the vendor.

← All AI models

Not sure which model fits your business?

I can help you pick a model and plan based on what you actually need, set it up safely for company data and train your team to use it well. Let’s start with an intro consultation.

See pricing [email protected]