Amazon models, priced in toman
8 Amazon models are live on uttapen. Prices are in toman per 1 million tokens, and you are charged for the tokens you actually use.
Amazon on uttapen
Amazon currently has 8 models in the uttapen catalogue. All of them bill against a toman wallet, for the tokens a request actually used.
The spread inside Amazon alone is wide: Nova Micro 1.0 runs about 79 toman for a 1,000-word request, while Nova Premier 1.0 costs 6,751 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 Amazon output price undercuts about 40% of the other paid models.
On capabilities: 5 take image input, 5 support tool calling, 1 does multi-step reasoning. The longest context belongs to Nova 2 Lite, at 1,000,000 tokens.
Every Amazon 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 Amazon model should I start with?
- Nova Micro 1.079 · per 1,000 wordsThe cheapest way in: about 79 toman for a 1,000-word request.
- Nova 2 Lite1,260 · per 1,000 wordsFor multi-step problems, maths and debugging: it reasons before it answers.
- Titan Text Embeddings V29.00 · per 1,000 wordsAn embedding model for semantic search and RAG; only input tokens are billed.
Every Amazon model, priced in toman
| Model | Capabilities | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
Nova 2 Liteamazon/nova-2-lite-v1 | Image inputTool callingReasoningFile input | 1,000,000 | 103,866 | 865,548 |
Nova Lite 1.0amazon/nova-lite-v1 | Image inputTool calling | 300,000 | 20,773 | 83,093 |
Nova Micro 1.0amazon/nova-micro-v1 | Tool calling | 128,000 | 12,118 | 48,471 |
Nova Premier 1.0amazon/nova-premier-v1 | Image inputTool calling | 1,000,000 | 865,548 | 4,327,742 |
Nova Pro 1.0amazon/nova-pro-v1 | Image inputTool calling | 300,000 | 276,975 | 1,107,902 |
Titan Multimodal Embeddings G1amazon/titan-embed-image-v1 | Image inputEmbeddings | 128 | 276,975 | — |
Titan Embeddings G1 - Textamazon/titan-embed-text-v1 | Embeddings | 8,192 | 34,622 | — |
Titan Text Embeddings V2amazon/titan-embed-text-v2 | Embeddings | 8,192 | 6,924 | — |
Common questions about the Amazon API
- How do I reach the Amazon 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 Amazon model id. No international card, no VPN. - What do Amazon models cost in toman?
- It depends on the model: the cheapest, Nova Micro 1.0, is about 79 toman for a 1,000-word request, and the dearest, Nova Premier 1.0, about 6,751 toman. Each model page carries its own exact price, and you are billed for what the request actually used.
- How many Amazon models are on uttapen?
- 8. 5 support tool calling and 5 accept image input. 3 are embedding models for /v1/
embeddings. The catalogue re-syncs hourly, so a newly released model shows up here on its own.