by Grok
Grok 4.20 is our newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.
Grok 4.20 is our newest flagship model with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering consistently precise and truthful responses.
grok-4.20-multi-agent-0309 has a 2,000,000 token context window.
On AIHubMix, grok-4.20-multi-agent-0309 costs $2 per million input tokens and $6 per million output tokens. Cached input reads are billed at $0.2 per million tokens.
grok-4.20-multi-agent-0309 accepts text and image input.
grok-4.20-multi-agent-0309 supports thinking, tool calling, function calling, structured outputs and long context. Per-protocol parameter support is listed in the capability table on this page.
grok-4.20-multi-agent-0309 is available through the AIHubMix unified API. The API is OpenAI-compatible: point your OpenAI SDK at https://aihubmix.com/v1, use your AIHubMix API key, and set the model name to grok-4.20-multi-agent-0309 — no other code changes needed.
grok-4.20-multi-agent-0309 is developed by Grok. AIHubMix aggregates it alongside models from other providers behind one API and one bill.
Grok 4.5 was trained on datasets spanning knowledge in coding, science, engineering, and…
Fast coding model trained specifically for agentic coding workflows.
Grok 4.3 is amongst the leading models in intelligence and well priced when comparing to…
Grok 4.2 is xAI’s latest large language model, built for strong reasoning, multimodal…
Grok 4.2 is xAI’s latest large language model, built for strong reasoning, multimodal…
Grok 4.1 is a new conversational model with significant improvements in real-world…
Use grok-4.20-multi-agent-0309 via the AIHubMix unified API — one interface for every major LLM.