uttapen

Claude Opus 4.1 (batch) API: toman pricing and code

anthropic/claude-opus-4.1:batch

visiontoolsreasoningjsonfiles
Input · per 1M tokens
2,175,938 toman
Output · per 1M tokens
10,879,688 toman
One 1,000-word request ≈
16,972 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 217,594 toman / 1M. Web search: 2,901.25 toman / request.Pricing and top-ups

Claude Opus 4.1 (batch) example: reading an image into JSON

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

# tip: a data URI works too — base64 the file and prefix it with data:image/jpeg;base64,
curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "anthropic/claude-opus-4.1:batch",
    "messages": [{
      "role": "user",
      "content": [
        {"type": "text", "text": "Return only the invoice number and the total, as JSON."},
        {"type": "image_url", "image_url": {"url": "https://example.com/factor.jpg"}}
      ]
    }]
  }'

What is Claude Opus 4.1 (batch) good for?

Claude Opus 4.1 (batch) comes from Anthropic; in uttapen you reach it with the model id "anthropic/claude-opus-4.1:batch". It accepts up to 200,000 tokens of input per call, so a long document or several source files fit in a single request. A single response can run to 32,000 tokens. On price it sits in the "expensive" band — cheaper than 386 and dearer than 20 of the other paid models in the catalogue.

What it can do beyond plain text: it reads images directly, which makes it a real option for invoices, forms and screenshots; it takes files such as PDFs as input; 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 2,175,938 toman per 1M input tokens and 10,879,688 per 1M output tokens. A 1,000-word round trip on Claude Opus 4.1 (batch) lands near 16,972 toman. It supports cached input: repeated context is billed at 217,594 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 GPT-4 Turbo: Claude Opus 4.1 (batch) works out roughly 1.1× more expensive, 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 6 thousand-word requests on Claude Opus 4.1 (batch), and every 1,000 toman is about 59 words of round trip. A job with one million input tokens and one million output tokens comes to 13,055,625 toman in total. Filling this model's 200,000-token window costs 435,188 toman on the input side alone, which is the real reason to keep conversation history short.

This id gets confused with "anthropic/claude-opus-4.1", because the underlying model is the same. The difference is the suffix: "batch" against the standard variant. On a thousand-word request this variant works out 2× cheaper (16,972 against 33,945 toman). On parameters, this one takes response_format, structured_outputs while the other takes top_k, top_p.

Anthropic has 31 models in our catalogue; the cheapest is Claude 3 Haiku at 566 toman per thousand words and the dearest Claude Opus 4.1 at 33,945. It does not support top_p, seed, 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 o1 at 200,000 tokens.

Good fits: work where the quality of the answer matters more than its cost, logic puzzles and code review, pulling text and fields out of images, 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

Claude Opus 4.1 is an updated version of Anthropic’s flagship model, offering improved performance in coding, reasoning, and agentic tasks. It achieves 74.5% on SWE-bench Verified and shows notable gains...

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 out7,616 toman
Summarising a ten-page document4,000 in + 600 out15,232 toman
Classifying a thousand short rows120,000 in + 20,000 out478,706 toman

Other variants of this model

Same core model, different execution terms and different price. This page is the batch (cheaper, slower) variant.

VariantModel idOutput / 1MContext
standardanthropic/claude-opus-4.121,759,375200,000

Put the variant's id verbatim in the model field; nothing else in your code changes.

Frequently asked

How do I call Claude Opus 4.1 (batch) 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 "anthropic/claude-opus-4.1:batch". Nothing else in your code changes.
What does Claude Opus 4.1 (batch) cost in toman?
2,175,938 toman per 1M input tokens and 10,879,688 toman per 1M output tokens; a 1,000-word request is around 16,972 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Claude Opus 4.1 (batch) take?
Up to 200,000 tokens per request, roughly 150k words. A single answer can reach 32,000 tokens.
Does Claude Opus 4.1 (batch) support streaming and tool calling?
Streaming (stream=true) works on every model here. This one supports tool calling in the standard OpenAI shape. Image input is accepted through image_url, as a data URI or a public URL. Structured output through response_format works too.