| Signal | Result | Reference |
|---|---|---|
| Tokenizer signature | Not measured | – |
| API surface | No other entry shares this exact contract | api_457e4baa |
| Context and output | 2,000,000 context · 1,800,000 max output | declared |
| Reasoning contract | Mandatory · efforts xhigh, high, medium, low · default medium | declared |
| Serving providers observed | xAI | measured 3 September 2026 |
An x marks a row excluded as corrupt (caching or provider interference detected during measurement). Overhead subtracted: 8551 prompt tokens.
Grok 4.20 Multi-Agent is a variant of SpaceXAI’s Grok 4.20 designed for collaborative, agent-based workflows. Multiple agents operate in parallel to conduct deep research, coordinate tool use, and synthesize information...
Supported parameters
include_reasoninglogprobsmax_tokensreasoningreasoning_effortresponse_formatseedstructured_outputstemperaturetop_logprobstop_p
defaults: {"temperature":null,"top_p":null,"top_k":null,"frequency_penalty":null,"presence_penalty":null,"repetition_penalty":null}
Cite this page as the evidence record for SpaceXAI: Grok 4.20 Multi-Agent: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings.
