Grok

inf grok routes Grok through https://api.inference.net/v1 using the chat completions surface. Grok stores one [model.*] section per registered model, with ids prefixed inference- so they cannot collide with your own entries.

Config file

inf writes fields in ~/.grok/config.toml (TOML). inf owns fields, not the whole file.

inf grok on

inf grok on

See Model mapping for supported aliases and limits.

What gets written

inf writes one [model.inference-<alias>] section per registered model with model, base_url = "https://api.inference.net/v1", api_key, api_backend = "chat_completions", context_window, and name. The default selection lives at [models].default = "inference-<selected alias>".

The three registered sections are inference-glm-5.2-fast, inference-kimi-k3-fast, and inference-deepseek-v4-flash-0731.

[model."inference-glm-5.2-fast"]
model = "glm-5.2-fast"
base_url = "https://api.inference.net/v1"
api_key = "<gateway-key>"
api_backend = "chat_completions"
context_window = 262144
name = "Inference.net · glm-5.2-fast"

inf grok status

inf grok status

inf grok off

inf grok off

off restores unchanged owned fields. It keeps fields that you edited after on.

Examples

Select DeepSeek:

inf grok on --model deepseek-v4-flash-0731

Restart Grok after on or off. See Troubleshooting for drift, recovery, and key revocation.