config-advanced.md Codex Docs, 2026-04-13 00:44 UTC → 2026-04-16 00:46 UTC

127 127 

128## Custom model providers128## Custom model providers

129 129 

130A model provider defines how Codex connects to a model (base URL, wire API, and optional HTTP headers).130A model provider defines how Codex connects to a model (base URL, wire API, authentication, and optional HTTP headers). Custom providers can't reuse the reserved built-in provider IDs: `openai`, `ollama`, and `lmstudio`.

131 131 

132Define additional providers and point `model_provider` at them:132Define additional providers and point `model_provider` at them:

133 133 

140base_url = "http://proxy.example.com"140base_url = "http://proxy.example.com"

141env_key = "OPENAI_API_KEY"141env_key = "OPENAI_API_KEY"

142 142 

143[model_providers.ollama]143[model_providers.local_ollama]

144name = "Ollama"144name = "Ollama"

145base_url = "http://localhost:11434/v1"145base_url = "http://localhost:11434/v1"

146 146 

158env_http_headers = { "X-Example-Features" = "EXAMPLE_FEATURES" }158env_http_headers = { "X-Example-Features" = "EXAMPLE_FEATURES" }

159```159```

160 160 

161Use command-backed authentication when a provider needs Codex to fetch bearer tokens from an external credential helper:

162 

163```toml

164[model_providers.proxy]

165name = "OpenAI using LLM proxy"

166base_url = "https://proxy.example.com/v1"

167wire_api = "responses"

168 

169[model_providers.proxy.auth]

170command = "/usr/local/bin/fetch-codex-token"

171args = ["--audience", "codex"]

172timeout_ms = 5000

173refresh_interval_ms = 300000

174```

175 

176The auth command receives no `stdin` and must print the token to stdout. Codex trims surrounding whitespace, treats an empty token as an error, and refreshes proactively at `refresh_interval_ms`; set `refresh_interval_ms = 0` to refresh only after an authentication retry. Don't combine `[model_providers.<id>.auth]` with `env_key`, `experimental_bearer_token`, or `requires_openai_auth`.

177 

161## OSS mode (local providers)178## OSS mode (local providers)

162 179 

163Codex can run against a local "open source" provider (for example, Ollama or LM Studio) when you pass `--oss`. If you pass `--oss` without specifying a provider, Codex uses `oss_provider` as the default.180Codex can run against a local "open source" provider (for example, Ollama or LM Studio) when you pass `--oss`. If you pass `--oss` without specifying a provider, Codex uses `oss_provider` as the default.

176env_key = "AZURE_OPENAI_API_KEY"193env_key = "AZURE_OPENAI_API_KEY"

177query_params = { api-version = "2025-04-01-preview" }194query_params = { api-version = "2025-04-01-preview" }

178wire_api = "responses"195wire_api = "responses"

179 

180[model_providers.openai]

181request_max_retries = 4196request_max_retries = 4

182stream_max_retries = 10197stream_max_retries = 10

183stream_idle_timeout_ms = 300000198stream_idle_timeout_ms = 300000

184```199```

185 200 

201To change the base URL for the built-in OpenAI provider, use `openai_base_url`; don't create `[model_providers.openai]`, because you can't override built-in provider IDs.

202 

186## ChatGPT customers using data residency203## ChatGPT customers using data residency

187 204 

188Projects created with [data residency](https://help.openai.com/en/articles/9903489-data-residency-and-inference-residency-for-chatgpt) enabled can create a model provider to update the base_url with the [correct prefix](https://platform.openai.com/docs/guides/your-data#which-models-and-features-are-eligible-for-data-residency).205Projects created with [data residency](https://help.openai.com/en/articles/9903489-data-residency-and-inference-residency-for-chatgpt) enabled can create a model provider to update the base_url with the [correct prefix](https://platform.openai.com/docs/guides/your-data#which-models-and-features-are-eligible-for-data-residency).