xAI · Workhorse

Grok 4.3 API pricing and specs

xAI's cheapest general model with a million-token context window.

Input

⁨$1.25⁩

Cached input

⁨$0.20⁩

Output

⁨$2.50⁩

US dollars per million tokens, standard tier, short-prompt rate

xAI did not publish a release date we could confirm. Prompts of 200K tokens or more are billed at the higher rate for every token in the request.

Prompts over 200K tokens are billed at ⁨$2.50⁩ input, ⁨$0.40⁩ cached and ⁨$5⁩ output per million, and the higher rate applies to the whole request.

Spec sheet

API model string: grok-4.3
Provider: xAI
Context: 1M tokens
Max output: —
Released: —
Batch API: No batch discount listed
Documented agent features: Tool callingStructured output

What a task costs

Four reference workloads priced at this model's list rates, with caching applied after the first call. Your numbers will differ; the calculator lets you change every assumption.

Workload	Per task	Per 1,000 tasks
Support bot 4 calls, short tool lookups	⁨$0.027⁩	⁨$27⁩
Coding agent 30 calls, files and test output	⁨$1.31⁩	⁨$1,314⁩
Browser agent 25 calls, screenshots and page text	⁨$0.898⁩	⁨$898⁩
Research agent 15 calls, long search results	⁨$0.779⁩	⁨$779⁩