We're excited to release grok-4-fast, our latest advancement in cost-efficient reasoning models.
An overview of our models' capabilities and their associated pricing.
Grok 4 Information for Grok 3 Users
When moving from grok-3 / grok-3-mini to grok-4 , please note the following differences: • Grok 4 is a reasoning model. There are no non-reasoning mode when using Grok 4.
• presencePenalty , frequencyPenalty and stop parameters are not supported by reasoning models. Adding them in the request would result in error.
, and parameters are not supported by reasoning models. Adding them in the request would result in error. • Grok 4 does not have a reasoning_effort parameter. If a reasoning_effort is provided, the request will return error.
Requests which make use of xAI provided server-side tools are priced based on two components: token usage and server-side tool invocations. Since the agent autonomously decides how many tools to call, costs scale with query complexity.
All standard token types are billed at the rate for the model used in the request:
Input tokens : Your query and conversation history
: Your query and conversation history Reasoning tokens : Agent's internal thinking and planning
... continue reading