Mercury 2 API: toman pricing and code
inception/mercury-2
toolsreasoningjsonYou are billed for the usage the request actually reported. Prices follow the market. Cached input: 7,253 toman / 1M.Pricing and top-ups
Mercury 2 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="inception/mercury-2",
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": "inception/mercury-2",
"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: "inception/mercury-2",
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 Mercury 2 good for?
Mercury 2 is one of Inception's models. Put "inception/mercury-2" in the model field and the rest of your code stays as it is. Mercury 2 keeps 128,000 tokens in view at once, and that number is what caps the conversation history in your product. A single response can run to 50,000 tokens. On price it sits in the "cheap" band — cheaper than 113 and dearer than 293 of the other paid models in the catalogue.
What you get on top of text in, text out: it supports tool calling, so it can invoke your own functions with valid arguments; it returns schema-valid JSON through response_format, ready to hand to your code; 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 72,531 toman per 1M tokens and output at 217,594 — output costs 3× input, so trimming the answer saves more than trimming the prompt. It supports cached input: repeated context is billed at 7,253 toman per 1M, which matters a lot if your system prompt is long. 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 GPT-3.5 Turbo (batch): Mercury 2 works out roughly 1× more expensive, and its context window is larger. 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 265 thousand-word requests on Mercury 2, and every 1,000 toman is about 2,653 words of round trip. A job with one million input tokens and one million output tokens comes to 290,125 toman in total. Filling this model's 128,000-token window costs 9,284 toman on the input side alone, which is the real reason to keep conversation history short.
Its nearest relative in the catalogue is "inception/mercury-2.5-preview", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 5.2× dearer (377 against 72 toman). The context windows differ too: 128,000 against 260,000 tokens. Maximum answer length differs as well: 50,000 against 65,536 tokens.
Inception has 2 models in our catalogue; the cheapest is Mercury 2.5 Preview at 72 toman per thousand words and the dearest Mercury 2 at 377. Among the less common parameters it accepts reasoning_effort — all through the standard request body. It does not support top_p, 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: high-volume work such as classification, tagging and bulk summarising, logic puzzles and code review, agents that reach out to APIs and databases, extracting data against a fixed schema.
Mercury 2 is an extremely fast reasoning LLM, and the first reasoning diffusion LLM (dLLM). Instead of generating tokens sequentially, Mercury 2 produces and refines multiple tokens in parallel, achieving...
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 | 196 toman |
| Summarising a ten-page document | 4,000 in + 600 out | 421 toman |
| Classifying a thousand short rows | 120,000 in + 20,000 out | 13,056 toman |
Frequently asked
- How do I call Mercury 2 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 "inception/mercury-2". Nothing else in your code changes.
- What does Mercury 2 cost in toman?
- 72,531 toman per 1M input tokens and 217,594 toman per 1M output tokens; a 1,000-word request is around 377 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
- How much input does Mercury 2 take?
- Up to 128,000 tokens per request, roughly 96k words. A single answer can reach 50,000 tokens.
- Does Mercury 2 support streaming and tool calling?
- Streaming (stream=true) works on every model here. This one supports tool calling in the standard OpenAI shape. Structured output through response_format works too.