Get a Wokey API key, point Grok CLI at the Wokey base URL, then confirm the connection with one curl request.
Every client uses the same Wokey API key and the same base URL.
Sign in and create a platform key on the API page. Keys in one account share its balance.
Create an API keykeySet the client base URL to the gateway domain; the configuration below shows whether to append /v1.
Point the client at Wokey with the configuration below.
Use the official Grok CLI config to connect to Wokey. Add a grok-4.7 model entry with its own api_key; the api_key in a model entry takes precedence over the grok login session, so Responses requests go to the Wokey gateway.
# ~/.grok/config.toml
[models]
default = "grok-4.7"
[model."grok-4.7"]
model = "grok-4.7"
name = "Grok 4.7 via Wokey"
base_url = "https://api.wokey.ai"
api_backend = "responses"
api_key = "YOUR_API_KEY"
context_window = 500000
supports_reasoning_effort = true
reasoning_effort = "high"
reasoning_efforts = [
{ value = "low", label = "Low" },
{ value = "medium", label = "Medium" },
{ value = "high", label = "High" },
{ value = "xhigh", label = "Extra High" }
]
If the client reports an error, rule out the key and base URL with curl first.
Grok CLI uses the OpenAI Responses format by default. A 200 from this request means the key and base URL are right. Replace YOUR_API_KEY with your key before sending it.
curl https://api.wokey.ai/v1/responses \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-6-sol",
"instructions": "You are a helpful assistant.",
"input": [
{ "role": "user", "content": "Hello" }
],
"store": false,
"stream": false
}'Separate auth, balance, rate limit, model availability, and upstream timeout cases first.
The key is missing, mistyped, deleted, or Authorization / x-api-key headers conflict.
The account balance is too low. Top up before sending more requests.
Traffic is too frequent. Retry later or reduce concurrency.
The upstream model service is temporarily unavailable. Switch models or retry later.
The upstream response timed out. Shorten context, reduce max_tokens, or retry.
The official upstream route is out of quota. Wait for routing recovery or switch models.