uttapen
Create an API key

Ling 3.0 Flash API: toman pricing and code

inclusionai/ling-3.0-flash

toolsreasoningjson
Create a keyTry it
Input · per 1M tokens
6,093 toman
Output · per 1M tokens
18,278 toman
One 1,000-word request ≈
32 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 1,219 toman / 1M.Pricing and top-ups

Ling 3.0 Flash 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="inclusionai/ling-3.0-flash",
    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 Ling 3.0 Flash good for?

Ling 3.0 Flash is one of inclusionAI's models. Put "inclusionai/ling-3.0-flash" in the model field and the rest of your code stays as it is. Ling 3.0 Flash keeps 262,144 tokens in view at once, and that number is what caps the conversation history in your product. A single response can run to 32,768 tokens. On price it sits in the "very cheap" band — cheaper than 5 and dearer than 401 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 6,093 toman per 1M input tokens and 18,278 per 1M output tokens. A 1,000-word round trip on Ling 3.0 Flash lands near 32 toman. It supports cached input: repeated context is billed at 1,219 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 Llama 3.1 8B Instruct: Ling 3.0 Flash works out roughly 1.5× 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 3,125 thousand-word requests on Ling 3.0 Flash, and every 1,000 toman is about 31,250 words of round trip. A job with one million input tokens and one million output tokens comes to 24,371 toman in total. Filling this model's 262,144-token window costs 1,597 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "inclusionai/ling-3.0-flash-fin", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 2.8× cheaper (32 against 91 toman). Maximum answer length differs as well: 32,768 against 235,929 tokens. On parameters, this one takes logprobs, top_logprobs while the other takes structured_outputs.

inclusionAI has 4 models in our catalogue; the cheapest is Ling 3.0 Flash at 32 toman per thousand words and the dearest Ling 3.0 Flash Fin at 91. Among the less common parameters it accepts logit_bias, logprobs, min_p, repetition_penalty, top_k, top_logprobs — all through the standard request body. It does not support structured_outputs, 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 Trinity Large Thinking at 262,144 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, analysing a long document or codebase in one request.

Provider's own description

*Ling-3.0-flash* is a *124B-parameter Mixture-of-Experts (MoE) model*, with approximately *5.1B parameters activated per token*. The model is designed with *token efficiency and production-scale agentic inference* as key priorities, enabling developers...

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 out16 toman
Summarising a ten-page document4,000 in + 600 out35 toman
Classifying a thousand short rows120,000 in + 20,000 out1,097 toman

Frequently asked

How do I call Ling 3.0 Flash 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 "inclusionai/ling-3.0-flash". Nothing else in your code changes.
What does Ling 3.0 Flash cost in toman?
6,093 toman per 1M input tokens and 18,278 toman per 1M output tokens; a 1,000-word request is around 32 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Ling 3.0 Flash take?
Up to 262,144 tokens per request, roughly 197k words. A single answer can reach 32,768 tokens.
Does Ling 3.0 Flash 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.