Command A

command-a-03-2025 returns up to 8,000 output tokens per request, within a 256,000-token context window. Cap the response with the max_tokens parameter so a single call cannot run past your budget.

Recorded results for command-a-03-2025: aa_intelligence_index 7.2; arena_text 72.1. Benchmark positions are a coarse filter only — run your own prompts against the candidate models before you commit, because ranking shifts with task shape and prompt style.

command-a-03-2025 sits alongside gpt-4o-2024-05-13, gpt-5-codex, gpt-4o in the catalog. Compare them on the dimensions that change your bill and your users’ experience: task quality on your own prompts, latency at your concurrency, context and output limits, and cost per completed task rather than per token.

Yes. command-a-03-2025 is reachable through an OpenAI-compatible endpoint, so an existing OpenAI SDK client works after pointing the base URL at MixRoute and setting the model parameter to command-a-03-2025. Keep your current request and response handling.

Set max_tokens on command-a-03-2025 to the longest response your task actually needs, not the 8,000-token ceiling. Keeping the cap tight reduces worst-case spend and shortens tail latency. Raise it only for tasks that demonstrably need longer output.