Perplexity models, priced in toman
7 Perplexity models are live on uttapen. Prices are in toman per 1 million tokens, and you are charged for the tokens you actually use.
Perplexity on uttapen
Perplexity currently has 7 models in the uttapen catalogue. All of them bill against a toman wallet, for the tokens a request actually used.
The spread inside Perplexity alone is wide: Sonar runs about 900 toman for a 1,000-word request, while Sonar Pro Search costs 8,102 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 Perplexity output price undercuts about 21% of the other paid models.
On capabilities: 4 take image input, 3 do multi-step reasoning. The longest context belongs to Sonar Pro, at 200,000 tokens.
Every Perplexity 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 Perplexity model should I start with?
- Sonar900 · per 1,000 wordsThe cheapest way in: about 900 toman for a 1,000-word request.
- Sonar Pro Search8,102 · per 1,000 wordsFor multi-step problems, maths and debugging: it reasons before it answers.
- Sonar Pro8,102 · per 1,000 wordsThis supplier's longest context, 200,000 tokens — for long documents and RAG.
- Embed V1 0.6B1.80 · per 1,000 wordsAn embedding model for semantic search and RAG; only input tokens are billed.
Every Perplexity model, priced in toman
| Model | Capabilities | Context | Input / 1M | Output / 1M |
|---|---|---|---|---|
Sonarperplexity/sonar | Image input | 127,072 | 346,219 | 346,219 |
Sonar Deep Researchperplexity/sonar-deep-research | Reasoning | 128,000 | 692,439 | 2,769,755 |
Sonar Properplexity/sonar-pro | Image input | 200,000 | 1,038,658 | 5,193,290 |
Sonar Pro Searchperplexity/sonar-pro-search | Image inputReasoningJSON output | 200,000 | 1,038,658 | 5,193,290 |
Sonar Reasoning Properplexity/sonar-reasoning-pro | Image inputReasoning | 128,000 | 692,439 | 2,769,755 |
Embed V1 4Bperplexity/pplx-embed-v1-4b | Embeddings | 32,000 | 10,387 | — |
Embed V1 0.6Bperplexity/pplx-embed-v1-0.6b | Embeddings | 32,000 | 1,385 | — |
Common questions about the Perplexity API
- How do I reach the Perplexity 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 Perplexity model id. No international card, no VPN. - What do Perplexity models cost in toman?
- It depends on the model: the cheapest, Sonar, is about 900 toman for a 1,000-word request, and the dearest, Sonar Pro Search, about 8,102 toman. Each model page carries its own exact price, and you are billed for what the request actually used.
- How many Perplexity models are on uttapen?
- 7. 4 accept image input. 2 are embedding models for /v1/
embeddings. The catalogue re-syncs hourly, so a newly released model shows up here on its own.