Antseed vs Nemotron 3.5 Super VL

Antseed

A buyer needs no account. The CLI creates a wallet key, free models answer at once and paid ones draw on deposited USDC, with seller, tokens and cost returned in response headers. Sellers are unvetted and can read prompts unless TEE-verified, the proxy forwards a client's own credential headers to them, and every package is pre-1.0.

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.

Antseed

1. Send a placeholder key such as antseed-p2p. The proxy forwards whatever Authorization or x-api-key header the client sends to the seller
2. Call GET /v1/models first and request a concrete id. The antseed alias works only when the desktop app has a model selected
3. Handle 402 insufficient_deposits by reading suggestedAmount, then fund the address from antseed buyer deposit with USDC on Base
4. Pass --verifiers antseed-verifier --require-verifier to antseed buyer start when prompts are private, so only TEE-verified sellers are routed
5. Read x-antseed-peer-id and x-antseed-estimated-cost-usd on each response, and pin a seller with <peerId>@<model> when the same one must answer

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