Inferray vs OpenRouter
OpenRouter and Inferray both give you many models behind one API at the labs' list prices. The differences are in what you pay on top, what happens to unused credit, and what you get at volume.
Competitor details were checked against their official pages on November 4, 2026. Prices and limits change; follow the links to confirm.
The short version
| OpenRouter | Inferray | |
|---|---|---|
| Model prices | Provider list price | List price |
| Fee on top | 5.5% on credit purchases (Standard), 8% (Business) | None |
| Unused credit | "We reserve the right to expire unused credits" after 365 days | Never expires |
| Volume discounts | Fee discounts on Enterprise; "we do not discount inference" | Per-customer discounts on request |
| Monthly plans | — | Token Plans: $60 of usage for $20 |
| APIs | OpenAI-compatible | OpenAI- and Anthropic-compatible |
OpenRouter figures are from its pricing page, FAQ and terms, as of November 4, 2026.
Where OpenRouter is the better fit
- A much larger catalog. OpenRouter lists far more models and providers than we do, including free models with low daily limits.
- Bring your own keys. OpenRouter can route traffic over your own provider keys, free up to $25,000 of list-price usage a month and 5% above that.
If you need a long tail of models or BYOK, OpenRouter does that and we don't.
Where Inferray is the better fit
- Nothing on top. No fee on credit purchases. What you top up is what you can spend.
- Credit that stays. Pay-as-you-go credit never expires.
- Volume pricing. If you spend steadily every month, we discount the models you use most.
- Token Plans. Coding agents run on a monthly plan worth 3× its price in usage, with no 5-hour or weekly windows.
- Anthropic-compatible too. Claude Code and the Anthropic SDK work against
/v1/messagesas they are.
The frontier models, at list price:
| Model | Input / 1M | Cached / 1M | Output / 1M | Context |
|---|---|---|---|---|
| Claude Opus 5.5 | $4 | $0.2 | $20 | 1M |
| Claude Sonnet 5.5 | $2 | $0.1 | $10 | 1M |
| GPT-6.1 Sol | $2 | $0.1 | $10 | 1.1M |
| Gemini 4 Argon | $4 | $0.2 | $20 | 1.0M |
| DeepSeek V4.1 Flash | $0.15 | $0.003 | $0.6 | 1M |
| Kimi K3 | $3 | $0.3 | $15 | 1.0M |
Moving over
Change the base URL and the key; model ids are the names in our catalog.
from openai import OpenAI
client = OpenAI(base_url="https://api.inferray.com/v1", api_key="inferray_...")
Prices on this page come from the model catalog and were current on November 12, 2026.