Reference
Models & pricing
All models, all prices, all tiers in one table.
§ 01
Tiers
Add tier to the request body to pick a performance level. Default is normal.
Price per token is per model — see the table under Pricing. The tier sets the multiplier:
- normal — full price (as in the model table). Standard real-time inference, default for developer accounts.
- async — 50% off the normal price. Requires
webhook_urland returns 202 with a job id. Result delivered via webhook within 12 hours — see the section below.
§ 02
Model
GET /v1/models — lists the active model (today glm-5.3-flash).
- glm-5.3-cache — chat
- glm-5.3 — chat, resonemang och långa dokument
- deepseek-v4.1-flash-1017 — chat, resonemang och långa dokument
- glm-5.3-flash-cache — chat
- gemma-4-26b-cache — chat
- glm-5.3-flash — chat, resonemang och långa dokument
- gemma-4-26b — chat, liten och snabb
- bge-m3 — embeddings (1024-dim)
- bge-reranker-v2-m3 — rerank
- gliner-multi-pii — PII-detektering
§ 03
Pricing
API (per token, per model). See the Models page for prices; the async tier is discounted off normal. Prepaid wallet via card through Mollie, a cash invoice is sent automatically on each top-up.
| Modell | Enhet | Pris |
|---|---|---|
| Chat (GLM 5.3 Cache) | per token | 1.50 / 0.40 / 4.00 EUR per 1M tokens (in/cachad in/ut, normal-tier) |
| Chat (GLM 5.3) | per token | 0.90 / 0.90 / 1.80 EUR per 1M tokens (in/cachad in/ut, normal-tier) |
| Chat (DeepSeek V4.1 Flash 1017) | per token | 0.50 / 0.10 / 1.50 EUR per 1M tokens (in/cachad in/ut, normal-tier) |
| Chat (GLM 5.3 Flash Cache) | per token | 0.40 / 0.08 / 1.20 EUR per 1M tokens (in/cachad in/ut, normal-tier) |
| Chat (Gemma 4 26b Cache) | per token | 0.30 / 0.06 / 0.90 EUR per 1M tokens (in/cachad in/ut, normal-tier) |
| Chat (GLM 5.3 Flash) | per token | 0.20 / 0.20 / 0.60 EUR per 1M tokens (in/cachad in/ut, normal-tier) |
| Chat (Gemma 4 26B) | per token | 0.15 / 0.15 / 0.45 EUR per 1M tokens (in/cachad in/ut, normal-tier) |
| Embeddings | per 1 M tokens in | 0.01 EUR / 1M input tokens |
| Rerank | per 1 000 queries | 0.05 EUR / 1,000 queries |
| PII-detektering | per 1 M tecken in | 0.02 EUR / 1M input characters |
| Tal till text (KB-Whisper) | per ljudminut | 0.0083 EUR / audio minute |
| Text till tal (Chatterbox) | per 1 M tecken in | 90 EUR / 1M input characters |
Chattmodellerna debiteras per token enligt tabellen ovan. De specialiserade modellerna debiteras per enhet till listpriset: inom ett abonnemang räknas de mot platsens dagliga tak, annars betalas de från plånboken.