Sonar Deep Research API: toman pricing and code
perplexity/sonar-deep-research
reasoningYou are billed for the usage the request actually reported. Prices follow the market. Reasoning tokens: 870,375 toman / 1M. Web search: 1,450.63 toman / request.Pricing and top-ups
Sonar Deep Research example: a multi-step problem with reasoning
The example is picked from this model's own capabilities. Drop in your key and it runs as is.
from openai import OpenAI
client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")
resp = client.chat.completions.create(
model="perplexity/sonar-deep-research",
messages=[{"role": "user", "content": (
"A shop has 3 warehouses. A ships 120 orders a day, B ships 85 and C ships 40. "
"If C closes and its load is split between A and B in proportion to their capacity, how many does each ship a day? "
"Work through it step by step and give just the two numbers at the end."
)}],
reasoning_effort="medium", # low | medium | high
)
print(resp.choices[0].message.content)
# reasoning tokens count as output tokens too:
print(resp.usage.completion_tokens_details)curl https://api.uttapen.ir/v1/chat/completions \
-H "Authorization: Bearer sk-up-…" \
-H "Content-Type: application/json" \
-d '{
"model": "perplexity/sonar-deep-research",
"messages": [{"role": "user", "content": "120 and 85 daily orders split across two warehouses; work through it step by step."}],
"reasoning": {"effort": "medium"}
}'import OpenAI from "openai";
const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });
const resp = await client.chat.completions.create({
model: "perplexity/sonar-deep-research",
messages: [{ role: "user", content: "120 and 85 daily orders are split between two warehouses; work through it step by step and give just the two numbers at the end." }],
reasoning_effort: "medium",
});
console.log(resp.choices[0].message.content);
console.log(resp.usage.completion_tokens_details);What is Sonar Deep Research good for?
The id for Sonar Deep Research in our API is "perplexity/sonar-deep-research", served from Perplexity. Context is 128,000 tokens; past that you have to summarise the history yourself. A single response can run to 115,200 tokens. On price it sits in the "mid-range" band — cheaper than 317 and dearer than 89 of the other paid models in the catalogue.
What you get on top of text in, text out: it has a reasoning mode that pays off on multi-step problems, maths and debugging. All of it works through the standard parameters of the official OpenAI SDK — no custom client, no wrapper. Keep in mind that reasoning tokens are output tokens and do appear on the bill.
Input runs at 580,250 toman per 1M tokens and output at 2,321,000 — output costs 4× input, so trimming the answer saves more than trimming the prompt. You are always charged for the usage the request actually reported, never for the estimate, and a failed request costs nothing.
The closest alternative with the same capabilities from a different provider is Command A: Sonar Deep Research works out roughly 1.3× cheaper, and its context window is smaller. Both run on the same key and the same code, so trying the other one is a single string change.
To make the figure concrete: 100,000 toman of credit buys roughly 27 thousand-word requests on Sonar Deep Research, and every 1,000 toman is about 265 words of round trip. A job with one million input tokens and one million output tokens comes to 2,901,250 toman in total. Filling this model's 128,000-token window costs 74,272 toman on the input side alone, which is the real reason to keep conversation history short.
Perplexity has 5 models in our catalogue; the cheapest is Sonar at 754 toman per thousand words and the dearest Sonar Pro Search at 6,789. Among the less common parameters it accepts top_k, web_search_options — all through the standard request body. It does not support response_format, tool_choice, tools, seed, which most models here do, so test before switching if your code relies on them. By context size the nearest option from another provider is Nova Micro 1.0 at 128,000 tokens.
Where it makes sense: product chatbots and internal assistants, where cost and quality have to balance, logic puzzles and code review.
Sonar Deep Research is a research-focused model designed for multi-step retrieval, synthesis, and reasoning across complex topics. It autonomously searches, reads, and evaluates sources, refining its approach as it gathers...
Three real jobs, priced on this model
Each figure is derived from the prices above and moves when they do.
| Job | Tokens | Cost |
|---|---|---|
| One chat turn with a medium history | 1,500 in + 400 out | 1,799 toman |
| Summarising a ten-page document | 4,000 in + 600 out | 3,714 toman |
| Classifying a thousand short rows | 120,000 in + 20,000 out | 116,050 toman |
Frequently asked
- How do I call Sonar Deep Research from Iran?
- Sign up with your mobile number, top the wallet up in toman, create an API key, then in the official OpenAI SDK point base_url at https://api.uttapen.ir/v1 and set model to "perplexity/sonar-deep-research". Nothing else in your code changes.
- What does Sonar Deep Research cost in toman?
- 580,250 toman per 1M input tokens and 2,321,000 toman per 1M output tokens; a 1,000-word request is around 3,772 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
- How much input does Sonar Deep Research take?
- Up to 128,000 tokens per request, roughly 96k words. A single answer can reach 115,200 tokens.
- Can I stream Sonar Deep Research's output?
- Yes — with stream=true you get SSE events as the tokens are produced. This model has no tool calling and no image input, so pick a different one if you need either.