Create an API key

Hy4 preview API: toman pricing and code

tencent/hy4-preview

Tool callingReasoningJSON output
Create a keyTry it
Input · per 1M tokens
288,747 toman
Output · per 1M tokens
865,895 toman
One 1,000-word request ≈
1,501 toman

You are billed for the usage the request actually reported. Prices follow the market. Cached input: 14,541 toman per 1M tokens.Pricing and top-ups

Hy4 preview example: tool calling

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-…")

tools = [{
    "type": "function",
    "function": {
        "name": "check_stock",
        "description": "Returns the stock level of a product",
        "parameters": {
            "type": "object",
            "properties": {"sku": {"type": "string"}},
            "required": ["sku"],
        },
    },
}]

messages = [{"role": "user", "content": "How many of the Nike NK-42 shoe are in stock?"}]
first = client.chat.completions.create(model="tencent/hy4-preview", messages=messages, tools=tools)
call = first.choices[0].message.tool_calls[0]

# you run the function yourself — the model never touches the database
args = json.loads(call.function.arguments)
result = {"sku": args["sku"], "qty": 7}

messages += [first.choices[0].message, {"role": "tool", "tool_call_id": call.id, "content": json.dumps(result)}]
final = client.chat.completions.create(model="tencent/hy4-preview", messages=messages, tools=tools)
print(final.choices[0].message.content)
import OpenAI from "openai";

const client = new OpenAI({ baseURL: "https://api.uttapen.ir/v1", apiKey: "sk-up-…" });

const tools = [{
  type: "function",
  function: {
    name: "check_stock",
    description: "Returns the stock level of a product",
    parameters: { type: "object", properties: { sku: { type: "string" } }, required: ["sku"] },
  },
}];

const messages = [{ role: "user", content: "How many of the Nike NK-42 shoe are in stock?" }];
const first = await client.chat.completions.create({ model: "tencent/hy4-preview", messages, tools });
const call = first.choices[0].message.tool_calls[0];

const args = JSON.parse(call.function.arguments);
const result = { sku: args.sku, qty: 7 };

messages.push(first.choices[0].message, { role: "tool", tool_call_id: call.id, content: JSON.stringify(result) });
const final = await client.chat.completions.create({ model: "tencent/hy4-preview", messages, tools });
console.log(final.choices[0].message.content);
curl https://api.uttapen.ir/v1/chat/completions \
  -H "Authorization: Bearer sk-up-…" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "tencent/hy4-preview",
    "messages": [{"role": "user", "content": "How many of the Nike NK-42 shoe are in stock?"}],
    "tools": [{
      "type": "function",
      "function": {
        "name": "check_stock",
        "parameters": {"type": "object", "properties": {"sku": {"type": "string"}}, "required": ["sku"]}
      }
    }]
  }'

What is Hy4 preview good for?

Hy4 preview is one of Tencent's models. Put "tencent/hy4-preview" in the model field and the rest of your code stays as it is. Hy4 preview keeps 1,048,576 tokens in view at once, and that number is what caps the conversation history in your product. A single response can run to 64,000 tokens. On price it sits in the "mid-range" band — cheaper than 159 and dearer than 239 of the other paid models in the catalogue.

Capabilities available on this id: 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 1,501 toman per 1,000-word exchange (288,747 in, 865,895 out, per 1M tokens). It supports cached input: repeated context is billed at 14,541 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 Kimi K2 0905: Hy4 preview works out about 10% 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 67 thousand-word requests on Hy4 preview, and every 1,000 toman is about 666 words of round trip. A job with one million input tokens and one million output tokens comes to 1,154,642 toman in total. Filling this model's 1,048,576-token window costs 302,773 toman on the input side alone, which is the real reason to keep conversation history short.

Its nearest relative in the catalogue is "tencent/hy3", and choosing between those two is where most people hesitate. On a thousand-word request this variant works out about 5.1× more expensive (1,501 against 297 toman). The context windows differ too: 1,048,576 against 262,144 tokens. Maximum answer length differs as well: 64,000 against 128,000 tokens. On parameters, this one takes logprobs, parallel_tool_calls, top_logprobs.

Tencent has 8 models in our catalogue; the cheapest is Hy-MT2-1.8B at 99 toman per thousand words and the dearest Hy4 preview at 1,501. Among the less common parameters it accepts logit_bias, logprobs, max_completion_tokens, min_p, parallel_tool_calls, presence_penalty — all through the standard request body. By context size the nearest option from another provider is DeepSeek V4 Flash 0423 at 1,048,576 tokens.

What to use it for: product chatbots and internal assistants, where cost and quality have to balance, 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

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total. It is designed for coding agents, complex tool-use workflows, and productivity tasks that...

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 out779 toman
Summarising a ten-page document4,000 in + 600 out1,675 toman
Classifying a thousand short rows120,000 in + 20,000 out51,968 toman

Price history

DateInput (toman/1M)Output (toman/1M)
5 Nov 2026288,747865,895
4 Nov 2026259,872779,305
31 Oct 2026288,747865,895
29 Oct 2026259,872779,305
29 Oct 2026288,747865,895
28 Oct 2026259,872779,305
28 Oct 2026288,747865,895
27 Oct 2026259,872779,305
27 Oct 2026288,747865,895
26 Oct 2026259,872779,305
26 Oct 2026288,747865,895
25 Oct 2026259,872779,305

Every price change for this model is recorded. Toman figures use today's rate.

Frequently asked

How do I call Hy4 preview 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 "tencent/hy4-preview". Nothing else in your code changes.
What does Hy4 preview cost in toman?
288,747 toman per 1M input tokens and 865,895 toman per 1M output tokens; a 1,000-word request is around 1,501 toman. You pay for the usage that request actually reported, and a failed request costs nothing.
How much input does Hy4 preview take?
Up to 1,048,576 tokens per request, roughly 786k words. A single answer can reach 64,000 tokens.
Does Hy4 preview 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.