Cloudflare Workers AI vs Nemotron 3.5 Super VL

Cloudflare Workers AI

Per-model prices, rate limits and JSON Schemas are public, 10,000 neurons a day are free, and x402 payment is in beta on /ai/run for four models. No SLA was found, three models moved to paid-only access on 28 July 2026 with no notice, and several docs pages still use a model retired in May.

Nemotron 3.5 Super VL

NVIDIA's free endpoint takes OpenAI-format requests with typed tool calls, JSON Schema output and an OpenAPI 3.1 file, and the weights run anywhere under a permissive licence. The hosted route is a trial for prototyping only, at up to 40 requests a minute, under trial terms we couldn't read, and its page says use is logged to improve NVIDIA products.

Cloudflare Workers AI

1. Check the model page before calling. Seven models need Workers Paid or AI Gateway credits and return 403 with code 5035 on the Free plan
2. Read the internal code on a 429. 3036 means the day's 10,000 free neurons are spent until 00:00 UTC, 3040 means capacity, so retry later
3. Set options.rejectIfBusy to fail fast, or add ?queueRequest=true for the batch route when the answer can wait
4. Send the same x-session-affinity value on every turn of a session to reach the prefix cache and the cached-input price
5. Keep paid frontier models under 20 requests a minute per model, or 50 with prepaid AI Gateway credits

Nemotron 3.5 Super VL

1. Set chat_template_kwargs to {"enable_thinking": false} for short tasks. Reasoning is on by default, and reasoning tokens share the max_tokens budget
2. Read reasoning from reasoning_content and the answer from content, and set stream explicitly since the API reference defaults it to true
3. Don't send confidential or personal data to the hosted trial. The model page asks callers not to and says use is logged
4. Back off and retry on throttling. Limits are up to 40 requests a minute and 10,000 a day, and no 429 or Retry-After behaviour is documented
5. For production, use a partner endpoint or serve the weights. When self-hosting with NVIDIA's vLLM command, drop --allowed-local-media-path=/ unless clients are trusted