Hy3

Tencent's flagship open-weight Hunyuan model, released July 2026: a 295B-parameter MoE (21B active) under Apache 2.0 with three reasoning modes and a design emphasis on low hallucination rates.

Params: 295B, 21B active
Context: 262K tokens
Released: Jul 2026
License: Apache 2.0

Visit Tencent Compare vs other LLMs →

Hosted API price

List price via Tencent · per 1M tokens

USD

Input: $0.13 /1M
Output: $0.53 /1M
Hosted by: 3 providers

Hosted API pricing

How we price

Order

Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.

Prices

Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.

Cost

Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.

Transparency and funding

Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.

Every provider serving Hy3, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving Hy3, with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cached input /1M	Cost at 10M in + 2M out	Link
Tencent Creator Cheapest	$0.13	$0.53		$2.36	Visit website
GPUhub	$0.14	$0.56		$2.52	Visit website
Novita	$0.14	$0.58	$0.04	$2.56	Visit website

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Estimated cost to self-host

Hy3 needs about 170 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 8× RTX 4090 at about $2,534 a month.

That costs the same as roughly 13B tokens a month on Tencent's API. Self-hosting is more expensive below that volume.

Single node ≤ 8

What it costs to self-host Hy3 at each precision: the memory it needs, the cheapest rental that holds it, that rental's month and the API volume it pays off at
Precision	Memory	Cheapest fit (32K context)(Full 262K context)	Cost /mo	Break-even vs API
4-bit INT4 / FP4	170 GB250 GB	8× RTX 4090	$2,534$2,822	13B tokens /mo14B tokens /mo
8-bit FP8 / INT8	308 GB340 GB	8× A40	$2,822$5,472	14B tokens /mo28B tokens /mo
16-bit FP16 / BF16	603 GB678 GB	8× RTX PRO 6000	$12,730$12,730	65B tokens /mo65B tokens /mo

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. Break-even assumes a 5:1 input-to-output ratio. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.

Similarly priced models

The models nearest Hy3 by blended rate, each at its own cheapest provider.

Models priced nearest Hy3 per 1M tokens, each at its cheapest provider
Model	Blended /1M	Input /1M	Output /1M	Context	Cutoff	vs Hy3
Nemotron 3 Super 120B A12B Nvidia	$0.1583	$0.09	$0.50	1M	Jun 2025	−19%
Gemma 4 31B Google Cloud	$0.17	$0.13	$0.37	256K	Jan 2025	−14%
Qwen3-235B-A22B Instruct (2507) Alibaba Cloud	$0.1717	$0.09	$0.58	262K		−13%
Llama 3.3 70B Meta	$0.175	$0.13	$0.40	128K	Dec 2023	−11%
Qwen3.5-27B Alibaba Cloud	$0.19	$0.09	$0.69	262K		−3%
Hy3 This model Tencent	$0.1967	$0.13	$0.53	262K
Ministral 3 14B Mistral	$0.20	$0.20	$0.20	256K		+2%
Qwen3.8-Flash Alibaba Cloud	$0.2033	$0.15	$0.47	1M		+3%
Qwen3-VL-8B Alibaba Cloud	$0.2083	$0.15	$0.50	262K		+6%
Qwen-MT-Turbo Alibaba Cloud	$0.215	$0.16	$0.49	16K		+9%
Command R 08-2024 Cohere	$0.225	$0.15	$0.60	128K	Jun 2024	+14%

USD per 1M tokens at each model's cheapest listed provider. Blended is the cost of 10M input plus 2M output tokens, spread over the 12M.

Packet·ai

B200 @ $3.75/h on demand

No contract, no spot interrupts, no cluster minimums

Full root SSH, web dashboard, CI/CD ready

Reserve Now

Capabilities

What Hy3 accepts and can do, as published by Tencent.

Text Accepts and generates natural-language text.
Reasoning Thinks before it answers, always on or as a switchable mode.
Function calling Connect to external tools, APIs, and systems.
Structured output Return responses in structured formats like JSON.

Common questions

What is Hy3 good for?

General text tasks where you set reasoning effort from no-think up to high, and Tencent says it hallucinates rarely. Apache 2.0 weights allow commercial self-hosting, on a multi-GPU node.

When is Hy3 not a good fit?

Image or video input: it is text only, and no maximum output is published. Tencent's own API does not publish a split input and output rate.

What is the cheapest way to run Hy3?

Hosted, unless you push serious volume. Tencent charges $0.13 in / $0.53 out per 1M tokens. The cheapest rental that fits is 8x RTX 4090 at $2,534 a month, which costs the same as about 13B tokens a month on that API.

Can I self-host Hy3?

Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 170 GB of GPU memory, which starts at roughly $2,534 a month on the cheapest rental that fits.