---
id: "x-ai/grok-4.20"
also: ["x-ai/grok-4.20-20260309"]
card_usd_per_m: "1.25 in, 2.5 out, at xai"
cheapest_list_usd_per_m: "1.25 in, 2.5 out, at xai on openrouter"
cheapest_effective_usd_per_m: "0.6023 in, 2.5714 out, at xai on openrouter"
context: 2000000
max_output: 1800000
input: ["text", "image", "file"]
output: ["text"]
released: "2026-03-31"
api: ["/api/v1/chat/completions", "/api/v1/completions", "/api/v1/messages", "/api/v1/responses"]
params: ["include_reasoning", "logprobs", "max_tokens", "reasoning", "response_format", "seed", "structured_outputs", "temperature", "tool_choice", "tools", "top_logprobs", "top_p"]
endpoints: 4
gateways: "openrouter (4)"
no_training: 4
trains: 0
retains_prompts: 2
---
# SpaceXAI: Grok 4.20

Grok 4.20 is a reasoning model from SpaceXAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherance, delivering...