Start Here
Use Codex
Point Codex at Camel Stream with a named Responses provider
Codex can use a custom OpenAI
Responses provider. Camel Stream exposes /v1/responses.
| Provider | camel_stream |
| Model | deepseek-v4-flash |
| Base URL | https://stream.camelai.com/v1 |
| Key | CAMEL_API_KEY |
| Context window | 256k input tokens |
Codex ignores provider settings in project .codex/config.toml files.
Put this in your user Codex home, usually ~/.codex. A separate profile
keeps Stream from replacing your normal OpenAI provider.
1. Install Codex
Follow the Codex CLI installation instructions, or:
npm install -g @openai/codex2. Create a Stream key
Generate an API key in the Stream console. It is shown once.
export CAMEL_API_KEY="qaml_live_..."Keep the key in your shell environment or a secret manager. Do not put it in the TOML file.
3. Add a Camel Stream profile
Create ~/.codex/camel-stream.config.toml:
model = "deepseek-v4-flash"
model_provider = "camel_stream"
[model_providers.camel_stream]
name = "Camel Stream"
base_url = "https://stream.camelai.com/v1"
env_key = "CAMEL_API_KEY"
wire_api = "responses"wire_api = "responses" is the transport for Stream's /v1/responses
endpoint. Unlike Claude Code, this URL includes /v1. See
Codex custom model providers.
4. Start and verify
cd /path/to/your/project
codex --profile camel-streamCodex should use deepseek-v4-flash through camel_stream. If auth
fails, confirm CAMEL_API_KEY is set in the same shell.
Camel Stream queues requests when every subscribed stream is busy. Codex should keep the HTTP connection open. See Queues & errors.