gpt-oss-20b API: toman pricing and code
openai/gpt-oss-20b
toolsreasoningjsonYou are billed for the usage the request actually reported. Prices follow the market. Cached input: 8,704 toman / 1M.Pricing and top-ups
gpt-oss-20b 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-20b",
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-20b",
"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-20b",
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-20b good for?
The id for gpt-oss-20b in our API is "openai/gpt-oss-20b", served from OpenAI. Context is 131,072 tokens; past that you have to summarise the history yourself. A single response can run to 117,964 tokens. On price it sits in the "very cheap" band — cheaper than 15 and dearer than 391 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 8,704 toman per 1M tokens and output at 37,716 — output costs 4.3× input, so trimming the answer saves more than trimming the prompt. It supports cached input: repeated context is billed at 8,704 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 Nova Micro 1.0: gpt-oss-20b works out roughly 1.1× cheaper, 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 1,667 thousand-word requests on gpt-oss-20b, and every 1,000 toman is about 16,667 words of round trip. A job with one million input tokens and one million output tokens comes to 46,420 toman in total. Filling this model's 131,072-token window costs 1,141 toman on the input side alone, which is the real reason to keep conversation history short.
This id gets confused with "openai/gpt-oss-20b: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 1.6× cheaper (60 against 94 toman). On parameters, this one takes logprobs, seed, tool_choice, tools.
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_k — 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-20b is an open-weight 21B parameter model released by OpenAI under the Apache 2.0 license. It uses a Mixture-of-Experts (MoE) architecture with 3.6B active parameters per forward pass, optimized for...
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 | 28 toman |
| Summarising a ten-page document | 4,000 in + 600 out | 57 toman |
| Classifying a thousand short rows | 120,000 in + 20,000 out | 1,799 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-20b:batch | 58,025 | 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-20b 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-20b". Nothing else in your code changes.
- What does gpt-oss-20b cost in toman?
- 8,704 toman per 1M input tokens and 37,716 toman per 1M output tokens; a 1,000-word request is around 60 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
- How much input does gpt-oss-20b take?
- Up to 131,072 tokens per request, roughly 98k words. A single answer can reach 117,964 tokens.
- Does gpt-oss-20b 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.