How are reasoning tokens billed on Hy4 preview?

Reasoning tokens are billed as output on Hy4 preview, at $2.5010 per 1,000,000 token. They are generated before the visible answer and count toward both latency and spend, so a higher reasoning setting costs more even when the final answer is short.

Does Hy4 preview have a free tier?

Hy4 preview is billed per use and the record publishes no free-tier allowance. The current published rates are input $0.8340 per 1M tokens and output $2.5010 per 1M tokens. Trial credit or promotional quota is tied to your account rather than to the model, so check the console before planning around a free tier.

Can you control the reasoning budget on Hy4 preview?

Hy4 preview is a reasoning model. Reasoning effort can be tuned per request. Lower effort settings cut reasoning tokens and cost for routine work; reserve higher settings for problems that need deeper search. Measure quality at two or three settings before fixing one in production.

What is the rate limit for Hy4 preview?

The current model record does not publish a numeric rate limit for Hy4 preview. Confirm the quota for your plan in the console, then run a short load test at your expected concurrency to establish the effective ceiling before production.

When was Hy4 preview released, and is it still maintained?

Hy4 preview was released on 2026-08-28. Its catalog status is stable. Check the model page for deprecation notices before you build a long-lived integration on it.

Model detail

Hy4 preview

Provided by Tencent

Pay-as-you-go

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 require planning, context continuity, and sustained multi-step execution.

Model specs

Model ID: hy4-preview

Context length: 1M
Max output: 64K
I/O modalities
Released: 2026-08

API endpoints

One MixRoute gateway, OpenAI-compatible

OpenAI-compatible /v1/chat/completions POST

Pricing

Flat rate, unit: /1M Tokens

Input

$0.8340 /1M Tokens

Completion

$2.5010 /1M Tokens

Cache read

$0.0420 /1M Tokens

Selection summary

Quickly judge whether it fits your workload

What is this model good for?

Tencent: Hy4 preview is a mixture-of-experts model from Tencent

Tencent: Hy4 preview is a mixture-of-experts model from Tencent, with 49B active parameters out of 770B total.

What should you check before using it?

1,000,000 context, 64,000 output tokens

Tencent model that supports reasoning, tool calling and structured output. Released 2026-08-28.

Why use it through MixRoute?

Hy4 preview cache reads cut repeated-prompt cost

Cached prefixes are billed at 0.0420 USD per 1M tokens instead of 0.8340 USD, so repeated system prompts cost less. MixRoute serves Hy4 preview on the OpenAI-compatible endpoint /v1/chat/completions; point your existing client at https://api.mixroute.ai/v1 with the model ID hy4-preview and re-run your integration tests.

Capabilities & compatibility

Unconfirmed capabilities stay "Unknown," no guesses

Tool calling

Hy4 preview supports function and tool calls.

EX Send a tools definition; the response returns tool_calls to execute and feed results back.

Structured output

Hy4 preview can produce JSON-formatted output on demand.

EX response_format: { type: "json_schema" } forces valid JSON output.

Streaming

Hy4 preview supports streamed responses.

EX stream: true streams tokens incrementally, so chat UIs render as they arrive.

Prompt caching

Hy4 preview supports prompt caching under supported routing conditions.

EX Keep the system prompt and tool definitions at the start of the request; repeated prefixes are automatically billed at the cache-read rate.

OpenAI SDK

Call Hy4 preview through MixRoute's OpenAI-compatible endpoint.

EX Change base_url to https://api.mixroute.ai/v1; everything else follows the OpenAI style.

Token cost estimator

Live estimate from this page's pricing, not an actual bill

Input tokens Max per request 1M

Output tokens Max per request 64K

Requests / month

Cache hit rate 0%

Share of the same prefix read repeatedly, up to 100%

FAQ

Yes. Hy4 preview is reachable through an OpenAI-compatible endpoint, so an existing OpenAI SDK client works after pointing the base URL at MixRoute and setting the model parameter to hy4-preview. Keep your current request and response handling.

Get started

01

Create an API key

Generate a key in the Console; one key calls every model.
02

Set the base URL

Fully OpenAI SDK-compatible; just swap the URL to connect.

https://api.mixroute.ai/v1
03

Specify the model ID

In the request's model field, enter:

hy4-preview

Create an API key

New users get $5 in free credits

Test this model and alternate routes with the same request format

Start from a real workload, then let quality, total cost, and failure conditions decide whether to send production traffic.

Create an API key View integration docs