Coding CLI · configuration guide + live pricing · sign up for trial credit
OpenAI Codex CLI lets you override the model provider in config.toml and point it at the relay.
Codex CLI in one line: Override the provider in ~/.codex/config.toml and export OPENAI_API_KEY. Recommended models and their market floor prices are in the table below; the full catalog is at https://321ai.cc/en/models/.
| Setting | Value | Notes |
|---|---|---|
base_url | https://321ai.cc/v1 | provider section of ~/.codex/config.toml |
env_key | OPENAI_API_KEY | the key is read from this environment variable |
model | e.g. gpt-6.1-sol |
1. Edit ~/.codex/config.toml and add a custom model_provider pointing at the relay base_url
2. Export OPENAI_API_KEY with your platform key
3. Run codex to verify connectivity
| What | Where | Notes |
|---|---|---|
| Live market floor pricing | https://321ai.cc/en/models/ | input per 1M tokens, per-supplier quotes on the marketplace |
Prices are the multi-supplier market floor and move in realtime; see all model prices →
Depends on the Codex CLI version configuration (the wire_api setting); follow the official docs and the platform's protocol support per model.