uttapen
Create an API key

gpt-oss-safeguard-20b API: toman pricing and code

openai/gpt-oss-safeguard-20b

toolsreasoningjson
Create a keyTry it
Input · per 1M tokens
21,759 toman
Output · per 1M tokens
87,038 toman
One 1,000-word request ≈
141 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 10,880 toman / 1M.Pricing and top-ups

gpt-oss-safeguard-20b example: JSON output against a schema

The example is picked from this model's own capabilities. Drop in your key and it runs as is.

from openai import OpenAI
import json

client = OpenAI(base_url="https://api.uttapen.ir/v1", api_key="sk-up-…")

schema = {
    "name": "ticket",
    "schema": {
        "type": "object",
        "properties": {
            "category": {"type": "string", "enum": ["fani", "mali", "forush"]},
            "priority": {"type": "integer", "minimum": 1, "maximum": 5},
            "summary": {"type": "string"},
        },
        "required": ["category", "priority", "summary"],
        "additionalProperties": False,
    },
    "strict": True,
}

resp = client.chat.completions.create(
    model="openai/gpt-oss-safeguard-20b",
    messages=[{"role": "user", "content": "Ticket: "For two days I cannot download my invoice and I was charged twice.""}],
    response_format={"type": "json_schema", "json_schema": schema},
)
print(json.loads(resp.choices[0].message.content))

What is gpt-oss-safeguard-20b good for?

gpt-oss-safeguard-20b is one of OpenAI's models. Put "openai/gpt-oss-safeguard-20b" in the model field and the rest of your code stays as it is. gpt-oss-safeguard-20b keeps 131,072 tokens in view at once, and that number is what caps the conversation history in your product. A single response can run to 65,536 tokens. On price it sits in the "very cheap" band — cheaper than 61 and dearer than 345 of the other paid models in the catalogue.

What it can do beyond plain text: 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.

Pricing is 21,759 toman per 1M input tokens and 87,038 per 1M output tokens. A 1,000-word round trip on gpt-oss-safeguard-20b lands near 141 toman. It supports cached input: repeated context is billed at 10,880 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 Voxtral Small 24B 2507: gpt-oss-safeguard-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 709 thousand-word requests on gpt-oss-safeguard-20b, and every 1,000 toman is about 7,092 words of round trip. A job with one million input tokens and one million output tokens comes to 108,797 toman in total. Filling this model's 131,072-token window costs 2,852 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "openai/gpt-oss-120b", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 1.8× dearer (141 against 78 toman). Maximum answer length differs as well: 65,536 against 117,964 tokens. On parameters the other takes frequency_penalty, logit_bias, logprobs, min_p.

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. By context size the nearest option from another provider is Aion-2.0 at 131,072 tokens.

Good fits: 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.

Provider's own description

gpt-oss-safeguard-20b is a safety reasoning model from OpenAI built upon gpt-oss-20b. This open-weight, 21B-parameter Mixture-of-Experts (MoE) model offers lower latency for safety tasks like content classification, LLM filtering, and trust...

Three real jobs, priced on this model

Each figure is derived from the prices above and moves when they do.

JobTokensCost
One chat turn with a medium history1,500 in + 400 out67 toman
Summarising a ten-page document4,000 in + 600 out139 toman
Classifying a thousand short rows120,000 in + 20,000 out4,352 toman

Frequently asked

How do I call gpt-oss-safeguard-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-safeguard-20b". Nothing else in your code changes.
What does gpt-oss-safeguard-20b cost in toman?
21,759 toman per 1M input tokens and 87,038 toman per 1M output tokens; a 1,000-word request is around 141 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does gpt-oss-safeguard-20b take?
Up to 131,072 tokens per request, roughly 98k words. A single answer can reach 65,536 tokens.
Does gpt-oss-safeguard-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.