Sao10k models, priced in toman
2 Sao10k models are live on uttapen. Prices are in toman per 1 million tokens, and you are charged for the tokens you actually use.
Sao10k on uttapen
Sao10k currently has 2 models in the uttapen catalogue. All of them bill against a toman wallet, for the tokens a request actually used.
The spread inside Sao10k alone is wide: Llama 3 8B Lunaris runs about 41 toman for a 1,000-word request, while Llama 3.1 Euryale 70B v2.2 costs 765 toman for the same one. Picking the right model inside a brand matters as much as picking the brand.
Measured against the whole catalogue, the median Sao10k output price undercuts about 67% of the other paid models.
The longest context among Sao10k models is Llama 3.1 Euryale 70B v2.2, at 131,072 tokens.
Every Sao10k model answers on the same sk-up- key and the same base_url: switching between them means changing the `model` string and nothing else.
Which Sao10k model should I start with?
Every Sao10k model, priced in toman
| Model | Capabilities | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
Llama 3 8B Lunarissao10k/l3-lunaris-8b | JSON output | 8,192 | 13,849 | 17,311 |
Llama 3.1 Euryale 70B v2.2sao10k/l3.1-euryale-70b | JSON output | 131,072 | 294,286 | 294,286 |
Common questions about the Sao10k API
- How do I reach the Sao10k API from Iran?
- Sign up with your mobile number, top the wallet up in toman and create an sk-up- key. Then, in the official OpenAI SDK, point base_url at https:/
/ api.uttapen.ir/ v1 and set model to the Sao10k model id. No international card, no VPN. - What do Sao10k models cost in toman?
- It depends on the model: the cheapest, Llama 3 8B Lunaris, is about 41 toman for a 1,000-word request, and the dearest, Llama 3.1 Euryale 70B v2.2, about 765 toman. Each model page carries its own exact price, and you are billed for what the request actually used.
- How many Sao10k models are on uttapen?
- 2. The catalogue re-syncs hourly, so a newly released model shows up here on its own.