DeepInfra vs Router.com (Ramp Router)

DeepInfra

The model list, context sizes and per-token prices are readable without a key, and keys can carry an IP allowlist, a monthly spending cap and model-limited JWTs. Deprecated models get one week's notice and are then redirected to another model, there is no changelog or SLA, and an account needs a card or prepayment before any call.

Router.com (Ramp Router)

Detailed Markdown docs with typed error codes, per-model capability data and routing an agent can set per request. No OpenAPI document, status page, changelog or published rate limits were found. Signup needs a US business email in a browser, and Ramp records prompts and outputs for a year by default unless switched off.

DeepInfra

1. Call GET https://api.deepinfra.com/v1/openai/models at start-up for ids, context sizes and prices. No key is needed
2. Check the model field of each response. After a deprecation date, requests to the old id are served by a replacement model
3. Ask the account owner for a scoped JWT limited to the models and spend the task needs, not the full API key
4. Stay under 200 concurrent requests per model. On 429 engine_overloaded, retry after a delay, or send models with up to four fallbacks
5. Never inspect a JWT with GET /v1/scoped-jwt?jwtoken=, which puts the token in the URL. Keep credentials in the Authorization header

Router.com (Ramp Router)

1. Switch off content recording in Settings before sending private data. It is on by default and keeps prompts and outputs for a year
2. Read model ids from GET /v1/models at runtime. Ids are account-specific, an unknown one is a 404, and Gemini ids need your own Google key
3. Use POST /v1/responses with a models list for fallbacks. Router stops falling back once a stream has started
4. Set fallback_timeout and provider_timeout, or allow_flex_tier: false, when latency matters. Flex routing is on by default
5. Treat both 401 invalid_api_key and 401 api_key_deactivated as a possibly locked key, and stop retrying on 402