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...
| Field | Per token (USD) | Per million |
|---|---|---|
| prompt | 0.00000125 | $1.25 |
| completion | 0.0000025 | $2.50 |
| web_search | 0.005 | $5000 |
| input_cache_read | 0.0000002 | $0.200 |
| overrides | [object Object] | — |
{
"temperature": null,
"top_p": null,
"top_k": null,
"frequency_penalty": null,
"presence_penalty": null,
"repetition_penalty": null
}1 answerin this database. A round opens every model's answer to the same prompt.