LLMFrontière AI API pricing
20 Frontière AI models. Source: https://getfrontiereai.eu/api/v1/models
- Provider type
- Aggregator
- Server location (where inference runs)
- EU, Non-EU (per model)
- Regions
- EU, Non-EU (per model)
- Company HQ (secondary)
- France (EU) · Operated by FLEECE AI SASU, 10 rue Pierre Poisson, 63400 Chamalières, France (RCS Clermont-Ferrand 932 329 188, EU VAT FR45932329188), per the legal notice. Checked 2026-10-30. · legal source
- EU data residency
- some models / regions (see each model)
- Residency notes
- Routes each model to a named upstream: EU-sovereign models run on Scaleway, AKI.IO, Mistral AI (EU region) or Infomaniak; others go to US providers (OpenRouter, Modal). Each model carries a sovereign / EU-residency label in the public catalog. Privacy policy: no prompt or completion stored by Frontière.
- Listing note
- Prices are shown excluding VAT. Frontière AI publishes prepaid euro rates VAT-inclusive (TTC, French standard VAT 20%; intra-EU VAT FR45932329188) in its public catalog, and its own comparison pages convert TTC to HT by dividing by 1.20. We store and display that net (HT) figure. The amount actually debited from a prepaid balance is the published TTC price. Image and embedding models are omitted.
- Residency source
- https://getfrontiereai.eu/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.
20 of 20 models.
| Provider | Model | Input | Output | Cached in | Blended 3:1* ▲ | Context | EU residency |
|---|---|---|---|---|---|---|---|
| Frontière AI Aggregator | Gemma 3 27B | €0.112 | €0.616 | — | €0.238 | 131K | no |
| Frontière AI Aggregator | Pixtral 12B | €0.28 | €0.28 | — | €0.28 | 131K | yes |
| Frontière AI Aggregator | Mistral Small 3.2 24B | €0.21 | €0.49 | — | €0.28 | — | yes |
| Frontière AI Aggregator | Gemma 4 26B A4B | €0.14 | €0.70 | — | €0.28 | 256K | yes |
| Frontière AI Aggregator | Qwen3.8 Flash | €0.21 | €0.644 | — | €0.319 | 1M | no |
| Frontière AI Aggregator | gpt-oss-120b | €0.21 | €0.84 | — | €0.367 | — | yes |
| Frontière AI Aggregator | Qwen3.8 27B | €0.21 | €0.91 | €0.105 | €0.385 | 262K | yes |
| Frontière AI Aggregator | Mistral Small 4 | €0.231 | €0.924 | — | €0.404 | 262K | yes |
| Frontière AI Aggregator | DeepSeek V4 Flash 0731 | €0.56 | €1.12 | €0.112 | €0.70 | 256K | yes |
| Frontière AI Aggregator | Qwen3.6 35B A3B | €0.35 | €2.10 | — | €0.787 | 262K | yes |
| Frontière AI Aggregator | GLM 5.3 Flash | €0.574 | €1.89 | — | €0.903 | 1.05M | no |
| Frontière AI Aggregator | Llama 3.3 70B | €1.26 | €1.26 | — | €1.26 | — | yes |
| Frontière AI Aggregator | DeepSeek V4.1 Flash | €0.84 | €2.52 | €0.168 | €1.26 | 1.05M | yes |
| Frontière AI Aggregator | Apertus v1.5 70B | €1.08 | €3.85 | — | €1.77 | 100K | yes |
| Frontière AI Aggregator | Qwen3.5 397B A17B | €0.84 | €5.04 | — | €1.89 | 250K | yes |
| Frontière AI Aggregator | DeepSeek V4 Pro | €2.04 | €4.27 | — | €2.60 | 1M | no |
| Frontière AI Aggregator | Mistral Large 4 | €2.09 | €6.44 | €0.216 | €3.18 | 524K | yes |
| Frontière AI Aggregator | GLM 5.2 | €2.52 | €7.70 | — | €3.82 | 256K | yes |
| Frontière AI Aggregator | GLM 5.3 | €2.52 | €7.70 | €0.35 | €3.82 | 524K | yes |
| Frontière AI Aggregator | Kimi K3 | €3.78 | €18.90 | €0.378 | €7.56 | 1.05M | no |
Per 1M tokens, standard (non-promo) list prices; short-context / peak tier where tiered. USD unless shown with €, CHF or ₹: those are as published and not converted. ₹ rows also show ≈ USD at the RBI reference rate of ₹93.8579 per USD (2026-11-09); sorting still uses the published ₹ amount. Rows marked “Calculated from credits” have no official per-token price; see how they are calculated. 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.