uttapen

DeepSeek V3.1 Terminus API: toman pricing and code

deepseek/deepseek-v3.1-terminus

toolsreasoningjson
Input · per 1M tokens
78,334 toman
Output · per 1M tokens
290,125 toman
One 1,000-word request ≈
479 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 39,167 toman / 1M.Pricing and top-ups

DeepSeek V3.1 Terminus 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="deepseek/deepseek-v3.1-terminus",
    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)

What is DeepSeek V3.1 Terminus good for?

DeepSeek publishes this model; we expose it under the id "deepseek/deepseek-v3.1-terminus". Its context window is 163,840 tokens, roughly 123k English words in one request. A single response can run to 32,768 tokens. On price it sits in the "cheap" band — cheaper than 135 and dearer than 271 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 78,334 toman per 1M tokens and output at 290,125 — output costs 3.7× input, so trimming the answer saves more than trimming the prompt. It supports cached input: repeated context is billed at 39,167 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 Qwen3 Coder 480B A35B: DeepSeek V3.1 Terminus works out roughly 1× 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 209 thousand-word requests on DeepSeek V3.1 Terminus, and every 1,000 toman is about 2,088 words of round trip. A job with one million input tokens and one million output tokens comes to 368,459 toman in total. Filling this model's 163,840-token window costs 12,834 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "deepseek/deepseek-v3.2-exp", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out 1.9× dearer (479 against 256 toman). Maximum answer length differs as well: 32,768 against 65,536 tokens. On parameters the other takes logprobs, top_logprobs.

DeepSeek has 17 models in our catalogue; the cheapest is DeepSeek V4 Flash Latest at 79 toman per thousand words and the dearest DeepSeek V4 Pro 0813 (batch) at 1,991. Among the less common parameters it accepts logit_bias, min_p, repetition_penalty, top_k — all through the standard request body. By context size the nearest option from another provider is Llama Guard 4 12B at 163,840 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.

Provider's own description

DeepSeek-V3.1 Terminus is an update to [DeepSeek V3.1](/deepseek/deepseek-chat-v3.1) that maintains the model's original capabilities while addressing issues reported by users, including language consistency and agent capabilities, further optimizing the model's...

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 out234 toman
Summarising a ten-page document4,000 in + 600 out487 toman
Classifying a thousand short rows120,000 in + 20,000 out15,203 toman

Frequently asked

How do I call DeepSeek V3.1 Terminus 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 "deepseek/deepseek-v3.1-terminus". Nothing else in your code changes.
What does DeepSeek V3.1 Terminus cost in toman?
78,334 toman per 1M input tokens and 290,125 toman per 1M output tokens; a 1,000-word request is around 479 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does DeepSeek V3.1 Terminus take?
Up to 163,840 tokens per request, roughly 123k words. A single answer can reach 32,768 tokens.
Does DeepSeek V3.1 Terminus 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.