Base models + smart routes · one API
Up to 55.0% cheaper than OpenRouter’s cheapest zero-retention providers.
On these four models, pay less for both input and output than the lowest published price among OpenRouter providers with a zero-data-retention (no prompt storage, no training) policy.
| Model | Synap | OpenRouter cheapest (ZDR) | You save |
|---|---|---|---|
| Qwen3 VL 30B | Input$0.14Output$0.55 |
Input$0.15Output$0.60 | Input6.7%Output8.3% |
| Qwen3 30B | Input$0.081Output$0.244 |
Input$0.09Output$0.30 | Input9.7%Output18.7% |
| Qwen3 Coder 30B | Input$0.068Output$0.27 |
Input$0.15Output$0.60 | Input55.0%Output55.0% |
| Muse Glimmer 30B | Input$0.28Output$1.10 |
Input$0.30Output$1.20 | Input6.7%Output8.3% |
USD per 1M tokens · Input and output compared separately · Checked .
“OpenRouter cheapest (ZDR)” is the lowest published rate for each leg among OpenRouter-listed providers with a zero-data-retention policy (no prompt storage, no training), per OpenRouter’s own provider data-policy listing — before caching or batch discounts. Savings rounded to 0.1%; maximum is Qwen3 Coder 30B. Synap rates ↗ · Benchmarks →
Zero data retention
How this compares. Most AI APIs keep your requests on their servers for a while, even when they don't train on them:
- OpenAI — retains inputs and outputs up to 30 days by default for abuse monitoring; true zero retention needs separate account approval, and not every endpoint qualifies.
- Anthropic — auto-deletes within 30 days by default; zero retention requires a signed agreement.
On Synap it isn't an add-on. Every request we send out is checked in code against a zero-retention allowlist before it leaves — a provider able to store it is refused before one ever runs.
Prices per 1M tokens · zero data retention on every request.
See the benchmark →