Novita AI vs RouterPlus

Novita AI

Per-token prices for about 140 language models are public, and each key can carry an expiry, a model allowlist and a source IP allowlist. No status page, SLA or security.txt was found, the per-model rate limit figures are drawn by script, and both vendor SDK repositories are archived while the docs still point to them.

RouterPlus

The docs are written for agents, every model price is public, and each response carries its own cost. No terms of service, privacy policy, status page or changelog were found. Signup adds no free credit, and the chat catalogue is Claude and GPT only.

Novita AI

1. Set the OpenAI client base URL to https://api.novita.ai/openai and send the key as Authorization: Bearer. Keys start with sk_
2. Do not close a connection to stop generation. A request that reached the model is billed in full under status 499, so cap output with max_tokens
3. On 429, check whether the code is RATE_LIMIT_EXCEEDED or TOKEN_LIMIT_EXCEEDED and back off exponentially. No Retry-After header is documented
4. Read the changelog for retirement notices before pinning a model id. One retirement in October 2026 came with 11 days' notice
5. Ask the account owner for a key with an expiry, a model access policy and an IP allowlist. Keys are created and deleted only in the console

RouterPlus

1. Send max_tokens on every request. Without it the balance hold assumes up to 32,768 output tokens and can return insufficient_quota on a small balance
2. Switch on error_type. Retry rate_limit after retry-after, and stop on insufficient_quota, which needs a person to add credit or raise a cap
3. Don't add a retry loop on top of the SDK's. There is no idempotency key, so a retry that reaches a provider is billed again
4. Copy model ids from GET /v1/models or /api/models.json. An unknown id is a 404 and the gateway never substitutes one
5. Use /v1/messages for Claude when you need thinking or server tools, and /v1/chat/completions with response_format only for GPT ids