Before you start
You need:- active Capriole AI Premium or eligible Team access;
- a Capriole AI API key from the API page;
- at least one installed coding agent;
- a terminal where you can set an environment variable.
This guide reuses one key to prove compatibility. For a long-lived setup or a team, create a separate named key for each agent or user. Separate keys reduce the impact of a leaked credential and let you filter usage or revoke access independently from the API page.
Match the agent to its protocol
Each client keeps the wire protocol it was built to use, even though the account key is shared.
Responses and Chat Completions paths include
/v1 in the base URL. Anthropic Messages paths use the API root, except where an integration page documents a client-specific adapter value. Copy the exact value from the matching integration page.
Set up the shared key
1
Export the Capriole API key
Set one shell variable before opening an agent:Verify that the variable exists without printing the secret:The expected result is
Capriole API key is set.2
Choose the client path
Open the integration page from the table and copy its maintained configuration. Use the same value from For OpenClaw:
CAPRIOLE_AI_API_KEY wherever that client asks for a token.- Codex reads the key from
CAPRIOLE_AI_API_KEYthroughenv_key. - Claude Code uses
ANTHROPIC_AUTH_TOKEN. Set it from the shared variable before launch. - Kilo Code references
{env:CAPRIOLE_AI_API_KEY}in its provider configuration. - GitHub Copilot CLI uses
COPILOT_PROVIDER_API_KEYon OpenAI-compatible paths andCOPILOT_PROVIDER_BEARER_TOKENon Anthropic Messages. - OpenCode provider entries use the Capriole key in
apiKeyorauthToken, depending on the provider adapter. - OpenClaw provider entries reference
CUSTOM_API_KEY. Set it from the shared variable before starting the gateway.
3
Keep the model on a compatible route
Start with a maintained alias unless you need an exact model version:
- use
openai-lateston OpenAI Responses paths; - use
claude-lateston Anthropic Messages paths; - use a model listed by the integration page on Chat Completions-compatible paths.
4
Launch and verify the agent
Start the configured client from a test project and ask:Look for a non-empty answer, ideally the requested
CAPRIOLE_OK marker. Models do not always follow exact-output prompts, so the wording may differ.Then open the API page and confirm that the request appears in the usage view under the expected key and model. The usage record is the decisive check that the client used Capriole. A response alone is not enough when the client has another provider or fallback configured. The API keys and usage guide shows the exact filters and key lifecycle.This check does not test every tool or model feature.What success looks like
Coding-agent requests use the eligible personal or Team API balance. They are not part of unlimited paid browser chat. Read Capriole AI charged tokens before running a large automated workload.