Grok Model Deprecation on May 15, 2026

As we continue advancing Grok, we are retiring several earlier models to focus fully on our newest generation. Effective May 15, 2026 at 12:00pm PT, the following models will be deprecated from the xAI API:

• grok-4-1-fast-reasoning
• grok-4-1-fast-non-reasoning
• grok-4-fast-reasoning
• grok-4-fast-non-reasoning
• grok-4-0709
• grok-code-fast-1
• grok-3
• grok-imagine-image-pro

We know transitions like this can be disruptive, and we truly appreciate your understanding as we make this shift. Our goal is to deliver the best possible performance and capabilities to everyone building with us, and we have some exciting model releases planned in the coming weeks!

We have newer, more capable models ready for every workload. In most cases, migrating is as simple as changing the "model" field in your API request.

If you are using grok-4-1-fast-reasoning, grok-4-fast-reasoning, or grok-4-0709, we recommend migrating to grok-4.3.

Grok 4.3 is the fastest, most intelligent model we have ever built. It tops the leaderboards in agentic tool calling and instruction following, and includes:

• 1 million token context window
• 3 reasoning effort levels (low, medium, and high)
• Priced at $1.25 / 1M input and $2.50 / 1M output

If you are using grok-4-1-fast-non-reasoning or grok-4-fast-non-reasoning, we recommend migrating to grok-4.20-non-reasoning.

For less latency-sensitive workloads, consider using grok-4.3 with reasoning_effort set to low.

If you are using grok-code-fast-1, we recommend migrating to grok-4.3, which delivers significantly improved agentic coding and web dev capabilities.

We are here to support you through this migration. If you have any questions or need assistance, please reach out to support@x.ai.

For general information on model lifecycle and deprecation policies, see Migrating to New Models.