Skip to content
OmniRail
← All models

xAI · Language model

Grok Latest

~x-ai/grok-latest
  • Language
Released Jul 8, 2026

This model always redirects to the latest Grok model from xAI.

Specifications

Context window
500,000 tokens
Max output
450,000 tokens
Input
text, image, file
Output
text
Reasoning effort
xhigh, high, medium, low (always on)
Tokenizer
Router
Moderation
provider-moderated

Supported parameters

Accepted by the model and forwarded as-is by the gateway.

  • logprobs
  • max_tokens
  • reasoning
  • reasoning_effort
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_p

Use it

POST /api/v1/chat/completions · MCP chat · full reference

curl https://omnirail.org/api/v1/chat/completions \
  -H "Authorization: Bearer $OMNIRAIL_KEY" -H "Content-Type: application/json" \
  -d '{"model":"~x-ai/grok-latest","messages":[{"role":"user","content":"Hello"}],"max_tokens":300}'