DeepInfra vs Vercel AI Gateway

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.

Vercel AI Gateway

Token prices pass through with no markup, prompts are not stored by the gateway, and budgets, provider failover and per-request logs are built in. The free monthly credit needs a card on file, rate limits are not published as numbers, no SLA covers the API, and the contractual promise not to train on content applies to Enterprise subscriptions only.

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

Vercel AI Gateway

1. Read GET https://ai-gateway.vercel.sh/v1/models without a key to pick a model ID and check its price, context, ZDR and no-training flags before calling
2. Set zeroDataRetention or disallowPromptTraining to true in providerOptions.gateway on sensitive requests. Default routing ignores provider retention and training policies
3. Treat a 429 as retryable and honour retry-after when present. A 402 with quota_for_entity_exceeded is a spent budget, so do not retry it
4. On a Token Pass key, a 403 with no_providers_available means spent credit or a model outside the pass. Retry with a standard AI Gateway key, which bills credits
5. Set inferenceRegion when data residency matters. The default global may run inference outside the user's jurisdiction