The Orchestrator › Models › SpaceX AI
SpaceX AI: Grok 4.20 Reasoning
Grok 4.20 Beta is the newest flagship model from xAI with industry-leading speed and agentic tool calling capabilities. It combines the lowest hallucination rate on the market with strict prompt adherence, delivering consistently precise and truthful responses.
Specifications
| Provider | SpaceX AI |
| Model ID | spacexai/grok-4.20-reasoning |
| Context window | 2M tokens (2,000,000) |
| Modalities | text + image + pdf → text |
| Tokenizer | — |
| Router sources | Vercel AI Gateway |
| Released | 2026-03-10 |
| Tracked since | 2026-11-14 |
| Popularity | Not in the ranked set |
| Reasoning | — |
Pricing (per million tokens)
| Variant | Source | API ID | Input | Output | Context |
|---|---|---|---|---|---|
| standard | Vercel AI Gateway | spacexai/grok-4.20-reasoning | $1.25 | $2.50 | 2M |
| batch | Vercel AI Gateway | spacexai/grok-4.20-reasoning:batch | $1.00 | $2.00 | 2M |
Recorded price history
| Date | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| 2026-11-14 | $1.25 | $2.50 | 2M |
Capabilities
Vision (image input)Agentic tool useStructured outputs1M+ context windowControllable reasoningZero data retentionNo training on inputs (attested)
Trust flags come from TrustedRouter's per-provider attestations.
Supported parameters
max_tokens, temperature, stop, tools, tool_choice, reasoning, include_reasoning, response_format, structured_outputs