Friendli API pricing
6 Friendli models. Source: https://friendli.ai/pricing
- Provider type
- Inference host
- Server location (where inference runs)
- unknown
- Regions
- unknown
- Company HQ (secondary)
- US (outside EU) · FriendliAI Corp, San Francisco, CA; hub in Seoul, Korea (friendli.ai footer).
- EU data residency
- unknown
- Residency notes
- Pricing page does not state serving regions for Serverless Endpoints (custom region / VPC / on-prem deployments are Enterprise options). OpenRouter's provider list reports HQ US, no datacenter countries.
- Residency source
- https://friendli.ai/pricing
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.
Blend input:output
| Provider | Model | Input | Output | Cached in | Blended 3:1* ▲ | Context | EU residency |
|---|---|---|---|---|---|---|---|
| Friendli Inference host | gemma-4-31B-it | $0.14 | $0.40 | — | $0.205 | — | unknown |
| Friendli Inference host | GLM-5.3-Flash | $0.15 | $0.50 | $0.03 | $0.237 | — | unknown |
| Friendli Inference host | MiniMax-M2.5 | $0.30 | $1.20 | $0.06 | $0.525 | — | unknown |
| Friendli Inference host | DeepSeek-V3.2 | $0.50 | $1.50 | $0.25 | $0.75 | — | unknown |
| Friendli Inference host | GLM-5.3 | $1.40 | $4.40 | $0.26 | $2.15 | — | unknown |
| Friendli Inference host | GLM-5.2 | $1.40 | $4.40 | $0.26 | $2.15 | — | unknown |
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. 6 models.
* 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.