Avian API pricing
10 Avian models. Source: https://avian.io/pricing
- Provider type
- Inference host
- Server location (where inference runs)
- US
- Regions
- US
- Company HQ (secondary)
- US (outside EU) · Avian Data Inc., a Delaware corporation headquartered in New York (avian.io/about).
- EU data residency
- no
- Residency notes
- Privacy policy: 'Our servers are located in the United States'; zero data retention of prompts/completions. Dedicated nodes 'Available in North America (US) only'.
- Residency source
- https://avian.io/privacy
Primary location is where inference servers run (server region, from the cited source; otherwise 'unknown'). Company HQ is secondary public company information. OpenRouter prices are volatile: refreshed twice daily and excluded from cheapest-price answers.
Tap a box to filter by it; tap it again to remove that filter. Filters combine.
10 of 10 models.
| Provider | Model | Input | Output | Cached in | Blended 3:1* ▲ | Context | EU residency |
|---|---|---|---|---|---|---|---|
| Avian Inference host | DeepSeek V4 Flash | $0.14 | $0.28 | $0.0028 | $0.175 | — | no |
| Avian Inference host | MiMo-V2.6 Flash | $0.14 | $0.28 | $0.0028 | $0.175 | — | no |
| Avian Inference host | GLM-5.3 Flash | $0.128 | $0.425 | $0.0255 | $0.202 | — | no |
| Avian Inference host | DeepSeek V4.1 Flash | $0.128 | $0.51 | $0.0026 | $0.223 | — | no |
| Avian Inference host | MiniMax M3 | $0.255 | $1.02 | $0.051 | $0.446 | — | no |
| Avian Inference host | MiMo-V2.6 Pro | $0.37 | $0.74 | $0.0031 | $0.462 | — | no |
| Avian Inference host | MiMo-V2.5 Pro | $0.37 | $0.74 | $0.0031 | $0.462 | — | no |
| Avian Inference host | DeepSeek V4 Pro 0813 | $0.561 | $1.68 | $0.0187 | $0.842 | — | no |
| Avian Inference host | GLM-5.3 | $1.19 | $3.74 | $0.221 | $1.83 | — | no |
| Avian Inference host | Kimi K3 | $2.55 | $12.75 | $0.255 | $5.10 | — | no |
Per 1M tokens, standard (non-promo) list prices; short-context / peak tier where tiered. USD unless shown with € or CHF: those are as published and not converted. Click a header to sort.
* Blended assumes 3 input tokens for every output token: (3×input + output) / 4. Your real mix will differ, so use the cost calculator with your own token counts for a real estimate.