gpt-oss-120b API: toman pricing and code
openai/gpt-oss-120b
toolsreasoningjsonYou are billed for the usage the request actually reported. Prices follow the market.Pricing and top-ups
gpt-oss-120b 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="openai/gpt-oss-120b",
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": "openai/gpt-oss-120b",
"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: "openai/gpt-oss-120b",
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 gpt-oss-120b good for?
OpenAI publishes this model; we expose it under the id "openai/gpt-oss-120b". Its context window is 131,072 tokens, roughly 98k English words in one request. A single response can run to 117,964 tokens. On price it sits in the "very cheap" band — cheaper than 26 and dearer than 380 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 10,735 toman per 1M tokens and output at 49,321 — output costs 4.6× 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 DeepSeek V4 Flash 0423: gpt-oss-120b 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 1,282 thousand-word requests on gpt-oss-120b, and every 1,000 toman is about 12,821 words of round trip. A job with one million input tokens and one million output tokens comes to 60,056 toman in total. Filling this model's 131,072-token window costs 1,407 toman on the input side alone, which is the real reason to keep conversation history short.
This id gets confused with "openai/gpt-oss-120b:batch", because the underlying model is the same. The difference is the suffix: no suffix (the standard variant) against "batch". On a thousand-word request this variant works out 3.6× cheaper (78 against 283 toman). On parameters, this one takes logprobs, seed, top_a, top_logprobs.
OpenAI has 95 models in our catalogue; the cheapest is gpt-oss-20b at 60 toman per thousand words and the dearest o1-pro at 282,872. Among the less common parameters it accepts logit_bias, logprobs, min_p, reasoning_effort, repetition_penalty, top_a — all through the standard request body. By context size the nearest option from another provider is Aion-2.0 at 131,072 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.
gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. It activates 5.1B parameters per forward pass and is optimized...
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 | 36 toman |
| Summarising a ten-page document | 4,000 in + 600 out | 73 toman |
| Classifying a thousand short rows | 120,000 in + 20,000 out | 2,275 toman |
Other variants of this model
Same core model, different execution terms and different price. This page is the standard variant.
| Variant | Model id | Output / 1M | Context |
|---|---|---|---|
| batch (cheaper, slower) | openai/gpt-oss-120b:batch | 174,075 | 131,072 |
Put the variant's id verbatim in the model field; nothing else in your code changes.
Frequently asked
- How do I call gpt-oss-120b 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 "openai/gpt-oss-120b". Nothing else in your code changes.
- What does gpt-oss-120b cost in toman?
- 10,735 toman per 1M input tokens and 49,321 toman per 1M output tokens; a 1,000-word request is around 78 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
- How much input does gpt-oss-120b take?
- Up to 131,072 tokens per request, roughly 98k words. A single answer can reach 117,964 tokens.
- Does gpt-oss-120b 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.