uttapen

Claude Opus 4.5 (batch) API: toman pricing and code

anthropic/claude-opus-4.5:batch

visiontoolsreasoningjsonfiles
Input · per 1M tokens
725,313 toman
Output · per 1M tokens
3,626,563 toman
One 1,000-word request ≈
5,657 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 72,531 toman / 1M. Web search: 2,901.25 toman / request.Pricing and top-ups

Claude Opus 4.5 (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-4.5: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 4.5 (batch) good for?

Claude Opus 4.5 (batch) comes from Anthropic; in uttapen you reach it with the model id "anthropic/claude-opus-4.5: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 64,000 tokens. On price it sits in the "expensive" band — cheaper than 348 and dearer than 58 of the other paid models in the catalogue.

Capabilities available on this id: 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.

For a back-of-envelope figure: about 5,657 toman per 1,000-word exchange (725,313 in, 3,626,563 out, per 1M tokens). It supports cached input: repeated context is billed at 72,531 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 Premier 1.0: Claude Opus 4.5 (batch) works out roughly 1× more expensive, 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 18 thousand-word requests on Claude Opus 4.5 (batch), and every 1,000 toman is about 177 words of round trip. A job with one million input tokens and one million output tokens comes to 4,351,875 toman in total. Filling this model's 200,000-token window costs 145,063 toman on the input side alone, which is the real reason to keep conversation history short.

This id gets confused with "anthropic/claude-opus-4.5", 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 (5,657 against 11,315 toman). On parameters the other takes max_completion_tokens, top_k.

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. Among the less common parameters it accepts verbosity — all through the standard request body. 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.

What to use it for: 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 4.5 is Anthropic’s frontier reasoning model optimized for complex software engineering, agentic workflows, and long-horizon computer use. It offers strong multimodal capabilities, competitive performance across real-world coding and...

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 out2,539 toman
Summarising a ten-page document4,000 in + 600 out5,077 toman
Classifying a thousand short rows120,000 in + 20,000 out159,569 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-4.57,253,125200,000

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

Frequently asked

How do I call Claude Opus 4.5 (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-4.5:batch". Nothing else in your code changes.
What does Claude Opus 4.5 (batch) cost in toman?
725,313 toman per 1M input tokens and 3,626,563 toman per 1M output tokens; a 1,000-word request is around 5,657 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Claude Opus 4.5 (batch) take?
Up to 200,000 tokens per request, roughly 150k words. A single answer can reach 64,000 tokens.
Does Claude Opus 4.5 (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.