Grok Build
TIP
Key rules
1.
GET https://api.kie.ai/xai/v1/models, not from memory or training data. This endpoint gives the list Grok Build can run on this prefix. The general taskType=Chat catalog is a different, wider list that includes models this endpoint does not serve.2.
Authorization: Bearer. Every KIE endpoint, including the model listing, carries the API key in this one header. A header literally named apikey is rejected with 401.3.
api_backend = "responses". Grok Build's default backend is chat_completions, which sends to /v1/chat/completions. KIE serves these models on /xai/v1/responses.4.
model field with an id from the listing. That is the name sent to KIE. It is neither the table name [model.<name>] nor Grok Build's own spelling (for example grok-4.6). The listing uses a different set of ids (for example grok-4-6). Copy the id from the list; with the built-in name KIE rejects the request even if base_url is right.5.
.grok/config.toml only contributes MCP, plugin and permission keys. A [model.*] table there is not inference configuration.List available models
curl.exe:curl.exe -s -H "Authorization: Bearer $env:KIE_API_KEY" `
https://api.kie.ai/xai/v1/models | jq -r '.data[].id'.data[] is the list: id is the value for model. object, owned_by, created and aliases are boilerplate.Configure
[model.<name>] tables. <name> is the key in the model picker, and model is the id sent to KIE:[models]
default = "kie"
[model.kie]
model = "grok-4-6"
base_url = "https://api.kie.ai/xai/v1"
name = "KIE"
api_backend = "responses"
env_key = "KIE_API_KEY"base_url is the root that requests are sent to. With api_backend = "responses", Grok Build appends /responses itself, so the value is https://api.kie.ai/xai/v1, not the full request URL https://api.kie.ai/xai/v1/responses.env_key names the environment variable Grok Build reads the credential from and sends as a bearer token. It does not hold the key itself. Prefer it over writing the key into api_key.kie here). [models] default must be that key (or another [model.*] key), not a name from Grok's built-in catalog; otherwise new sessions still go to xAI instead of KIE.macOS and Linux
~/.grok/config.toml. Export the credential in the same shell that starts grok, or add it to your shell profile:GROK_HOME to keep the configuration somewhere other than ~/.grok.Windows (PowerShell)
%USERPROFILE%\.grok\config.toml, with identical content.$env:KIE_API_KEY = "…"
setx KIE_API_KEY "…"Verify the setup
grok models should list the custom key. grok inspect reports which config file is in effect. Start grok in a shell where KIE_API_KEY is set and send a message, or run grok -p "…" -m kie.RUST_LOG=debug GROK_LOG_FILE=/tmp/grok.log grok writes a request trace. Check the base_url and the model id.Common pitfalls
1.
apikey. KIE returns 401. Put the key in Authorization: Bearer.2.
base_url. With api_backend = "responses", Grok Build appends /responses itself, so a base_url ending in /responses becomes /responses/responses.3.
api_backend. The default is chat_completions, which sends to /v1/chat/completions, not /xai/v1/responses.4.
model. KIE reads the model field of [model.<name>], which must be an id from the listing. A built-in spelling such as grok-4.6 is not that id.5.
[model.*] in the project-level .grok/config.toml. That file does not carry inference configuration. Use ~/.grok/config.toml.6.
env_key. It takes the name of an environment variable. The key lives in that variable, not in the config file.7.
setx does not affect the current window. It applies to windows opened afterwards. Set $env: as well to use it right away.8.
curl. It is an alias for Invoke-WebRequest and does not accept these arguments. Use curl.exe.