# Migrating from OpenRouter (/en/docs/cookbook/migration/from-openrouter) Keep the OpenAI SDK, replace the connection settings and model ID, then review every OpenRouter-specific option before switching traffic. ```diff client = OpenAI( - base_url="https://openrouter.ai/api/v1", - api_key=os.environ["OPENROUTER_API_KEY"], + base_url="https://api.deepraxis.com/openai/v1", + api_key=os.environ["PRAXIS_API_KEY"], ) -model = "openai/gpt-4o" +model = "deepseek-flash" ``` ## 1. Prepare [#1-prepare] You need Python 3.10+, [uv](https://docs.astral.sh/uv/getting-started/installation/), and a Praxis key. Create one in [Console → API Keys](https://console.deepraxis.ai/keys) and securely inject it into the current terminal as `PRAXIS_API_KEY`. Never put the key in code or logs. Keep your original service configuration and key for rollback. Run the commands below in Bash on macOS or Linux. ```bash test -n "${PRAXIS_API_KEY:-}" ``` Expected: exit code 0. Exit code 1 means the variable is missing; set it before continuing. ## 2. Replace model IDs [#2-replace-model-ids] | OpenRouter selection | Praxis selection | | ------------------------ | ------------------------------------------------------------------------------------------ | | `openai/gpt-4o` | Start with `deepseek-flash`; this is a different model, not an alias | | `vendor/model` | Copy the exact ID from the Praxis catalog; do not assume removing the prefix is sufficient | | An ID ending in `:nitro` | Select a catalog ID without the suffix; the suffix is unsupported | | `openrouter/auto` | Choose a specific model, or configure a `models` fallback list | Expected: `client.models.list()` includes your chosen ID. All entries in a fallback list must be valid Praxis IDs offering the operation you call. ## Behavior differences [#behavior-differences] | OpenRouter option | Migration action | | ---------------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- | | `provider.order`, `provider.only`, `provider.ignore` | Available only with your own upstream key (BYOK). With platform credentials, remove them or receive `400 provider_selection_not_allowed` | | `provider.allow_fallbacks`, `provider.sort` | Have no effect; remove them and reassess any routing assumptions | | `provider.data_collection`, `provider.zdr` | Have no effect; do not treat accepted requests as enforcement of these policies | | `models` | A model fallback list is available; replace every ID and verify the returned `model` | | `provider.require_parameters: true` | Checks support for tool parameters and declared sampling parameters; returns 400 when a requested parameter is not declared as supported. Unsupported sampling parameters are otherwise ignored by default | The parameter check covers tool parameters and declared sampling parameters, not arbitrary provider features. See [Chat Completions field support](/en/docs/api/compatible/openai/createChatCompletion) for the precise scope. If your application requires a data policy controlled by an ignored option, keep it on the original service until you have separately confirmed the required policy. Chat's `usage.cost` is the amount charged; Responses and Messages currently omit it. When `X-Praxis-Generation-Id` is present, use `GET /model/v1/generation?id=GENERATION_ID` as described in the [generation record API](/en/docs/api/native/model/getGeneration). Records may take a few seconds to appear. If the header is absent, check [Console → Usage and costs](https://console.deepraxis.ai/usage). Neither the response body's `id` nor `X-Request-Id` is a substitute for a generation ID. Missing cost does not mean zero cost. ## Unsupported operations and alternatives [#unsupported-operations-and-alternatives] `vendor/model`, `:nitro`, and `openrouter/auto` are not supported model selectors. There is no automatic mapping. For absent OpenAI endpoints, use the [unsupported endpoint table and alternatives](/en/docs/cookbook/migration/from-openai#unsupported-endpoints-and-alternatives). The [API reference](/en/docs/api/compatible/openai) owns operation and field details; do not assume OpenRouter extensions apply to Responses. ## 3. Verify one request [#3-verify-one-request] First prove the simplest Chat request, with no provider preferences: ```bash unset HTTP_PROXY HTTPS_PROXY ALL_PROXY http_proxy https_proxy all_proxy uv run -q --no-project --with openai --with anthropic python - <<'PY' import os from openai import OpenAI client = OpenAI( base_url="https://api.deepraxis.com/openai/v1", api_key=os.environ["PRAXIS_API_KEY"], timeout=90.0, max_retries=0, ) models = client.models.list() assert "deepseek-flash" in {m.id for m in models.data} raw = client.chat.completions.with_raw_response.create( model="deepseek-flash", messages=[{"role": "user", "content": "Reply OK."}], max_tokens=1024, ) reply = raw.parse() text = reply.choices[0].message.content print("HTTP", raw.status_code) print("X-Request-Id:", raw.headers.get("x-request-id")) print("X-Praxis-Generation-Id:", raw.headers.get("x-praxis-generation-id")) print(text) assert raw.status_code == 200 and text and text.strip() assert raw.headers.get("x-request-id") PY ``` Expected: exit code 0, `HTTP 200`, nonempty text (usually `OK.`), and an `X-Request-Id`. Assertions check both model availability and a real reply, not just connectivity. Keep the request ID for troubleshooting, never the key. The example incurs a small usage charge. Then add back only the options your application needs, one at a time. Expected: each request succeeds and returns the intended model; an ignored field is not proof that a policy was applied. ## Failures [#failures] | Observed error | Action | | ------------------------------------ | --------------------------------------------------------------------------------------------------------- | | `400 provider_selection_not_allowed` | Remove provider selection when using platform credentials, or configure BYOK before selecting an upstream | | `404` with `does not exist` | Replace the namespaced ID, suffix, or automatic selector with a catalog ID | | `404 model_protocol_not_offered` | Choose a model offering the requested operation | ## 4. Roll back [#4-roll-back] Restore `https://openrouter.ai/api/v1`, the original `OPENROUTER_API_KEY`, your original model ID, and your saved OpenRouter options. Restart the client and run the original smoke request. Do not send the Praxis key to OpenRouter. Expected: the original request returns usable text with the intended model. Any calls already charged on Praxis remain charged. [API reference →](/en/docs/api/compatible/openai) · [Cookbook: OpenAI SDK →](/en/docs/cookbook/sdk/openai-sdk)