Grok Code Fast 1
Last refreshed 2026-05-20. Next refresh: weekly.
Grok Code Fast 1 is a legacy integration reference; evaluate Grok Build 0.1 before starting new work.
Decision context: Coding task fit, 3 tracked provider routes, and research from 2026-05-20.
Use it for
- Teams maintaining an existing integration
- Workloads that can use a 262k context window
- Buyers comparing 2 tracked provider routes
Do not use it for
- New production launches
- Vision or document-understanding workloads
Cheapest output
$1.50
OpenRouter per 1M tokens
Provider routes
3
Tracked API hosts
Quality / dollar
Unknown
No output-token price in the ladder
Freshness
2026-05-20
Researched 13d ago
Top use-case fit
Coding
1 relevant benchmark in the decision map.
RAG
Included by capability and metadata signals in the decision map.
Agents
1 relevant benchmark in the decision map.
Provider price ladder
Compare all 3| Provider | Input / 1M | Output / 1M | Route |
|---|---|---|---|
| OpenRouter | $0.200 | $1.50 | Serverless |
| Microsoft Foundry | - | - | ServerlessPartial |
Benchmark peer barsfor Coding
Migration checks
No linked migration route is available for this model yet.
This model is deprecated. xAI recommends switching to Grok Build 0.1.
About
xAI's Grok Code Fast 1 is a code-specialized Mixture-of-Experts model released August 27, 2025. It was retired on May 15, 2026; xAI lists grok-build-0.1 as its direct replacement for current coding-agent work.
Grok Code Fast 1 is a proprietary model in the Grok 4 family. The structured metadata tracks a 262k-token context window, function calling, tool use, and structured outputs. This page tracks provider routes through OpenRouter, Microsoft Foundry, and xAI Console, with the cheapest tracked route listed at $0.2 input and $1.5 output per 1M tokens. Headline tracked benchmarks include SWE-bench Verified 70.8.
Capabilities
Benchmark Scores(1)
| Benchmark | Score | Version | Source |
|---|---|---|---|
| SWE-bench Verified | 70.8 | SWE-bench Verified | https://www.swebench.com/verified.html |
