uttapen

Claude Sonnet 5 (batch) API: toman pricing and code

anthropic/claude-sonnet-5:batch

visiontoolsreasoningjsonfiles
Input · per 1M tokens
290,125 toman
Output · per 1M tokens
1,450,625 toman
One 1,000-word request ≈
2,263 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 29,013 toman / 1M. Web search: 2,901.25 toman / request.Pricing and top-ups

Claude Sonnet 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-sonnet-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 Sonnet 5 (batch) good for?

The id for Claude Sonnet 5 (batch) in our API is "anthropic/claude-sonnet-5:batch", served from Anthropic. Context is 1,000,000 tokens; past that you have to summarise the history yourself. A single response can run to 128,000 tokens. On price it sits in the "mid-range" band — cheaper than 287 and dearer than 119 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 290,125 toman per 1M input tokens and 1,450,625 per 1M output tokens. A 1,000-word round trip on Claude Sonnet 5 (batch) lands near 2,263 toman. It supports cached input: repeated context is billed at 29,013 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 Gemini 2.5 Pro (batch): Claude Sonnet 5 (batch) works out roughly 1.1× 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 44 thousand-word requests on Claude Sonnet 5 (batch), and every 1,000 toman is about 442 words of round trip. A job with one million input tokens and one million output tokens comes to 1,740,750 toman in total. Filling this model's 1,000,000-token window costs 290,125 toman on the input side alone, which is the real reason to keep conversation history short.

This id gets confused with "anthropic/claude-sonnet-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 (2,263 against 4,526 toman). On parameters the other takes max_completion_tokens.

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 reasoning_effort, verbosity — all through the standard request body. It does not support temperature, 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 Nova 2 Lite at 1,000,000 tokens.

Good fits: product chatbots and internal assistants, where cost and quality have to balance, 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

Sonnet 5 is Anthropic's most capable Sonnet-class model, with frontier performance across coding, agents, and professional work. It supports adaptive thinking with selectable reasoning effort levels (low, medium, high, max,...

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 out1,015 toman
Summarising a ten-page document4,000 in + 600 out2,031 toman
Classifying a thousand short rows120,000 in + 20,000 out63,828 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-sonnet-52,901,2501,000,000

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

Frequently asked

How do I call Claude Sonnet 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-sonnet-5:batch". Nothing else in your code changes.
What does Claude Sonnet 5 (batch) cost in toman?
290,125 toman per 1M input tokens and 1,450,625 toman per 1M output tokens; a 1,000-word request is around 2,263 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Claude Sonnet 5 (batch) take?
Up to 1,000,000 tokens per request, roughly 750k words. A single answer can reach 128,000 tokens.
Does Claude Sonnet 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.