How much does Hy3 cost per million tokens?

Hy3 costs $0.132 per million input tokens and $0.528 per million output tokens at list price, and $0.033 per million cached input tokens.

What is the context window of Hy3?

Hy3 accepts up to 262,144 tokens of context and returns up to 128,000 output tokens.

How much do 1,000 chat messages cost with Hy3?

About $0.40, assuming 1,000 input + 500 output tokens per message.

Is there a cheaper alternative to Hy3?

In the same price range, OpenAI GPT-6 Luna Pro ($0.1 / $0.5), OpenAI GPT-6 Luna ($0.1 / $0.5), Qwen Qwen3.8 Omni Flash ($0.15 / $0.47) cost less per token. Quality differs: test on your own prompts.

Where can I buy Tencent API credits for less?

Discount credit books resell OpenRouter usage below face value within their depth, OpenRouter adds a 5.5% card fee, and Tencent sells its own credits at face value. The live table on this page ranks them for $100 of usage.

Tencent · live price

Hy3 API pricing

Hy3 is a 295B-parameter Mixture-of-Experts model from Tencent (21B active, 192 experts with top-8 routing) built for reasoning, agentic workflows, and real-world production use. It supports a configurable reasoning effort:...

Small and cheap (under $1 per 1M)Tool callingReasoning

Input: $0.132; per 1M tokens
Output: $0.528; per 1M tokens
Cached input: $0.033; per 1M tokens
Context: 262K; 128K max output

List price from OpenRouter, which passes Tencent's price through without markup. Refreshed hourly. Released July 6, 2026. Model id tencent/hy3.

What Hy3 costs in practice

At list price, before any batch or caching discount.

1,000 chat messages

$0.40

1,000 input + 500 output tokens each

1,000 RAG questions

$1.32

8,000 input + 500 output tokens each

100 coding-agent steps

$0.50

30,000 input + 2,000 output tokens each, no caching

Hy3 price history

No price change since we started tracking on 2026-10-01. We record prices daily; changes will show here.

Hy3 price by host

6 hosts serve this model. Prices are the same or higher than list; the cheapest are first.

Tencent$0.132 in · $0.528 out · 262K ctx · 99.8% uptime 24h
DeepInfra$0.13 in · $0.53 out · 262K ctx · 99.8% uptime 24h
Novita$0.14 in · $0.58 out · 262K ctx · 99.2% uptime 24h
GMICloud$0.14 in · $0.58 out · 262K ctx · 99.9% uptime 24h
Phala$0.15 in · $0.64 out · 262K ctx · 99.6% uptime 24h
AtlasCloud$0.2 in · $0.8 out · 262K ctx · 99.8% uptime 24h

Where to buy Tencent credits for less

Hy3 costs the same per token everywhere it's sold through OpenRouter. What changes is the price of the credits. Live quotes for $100 of usage:

#	Where you buy	You payYou pay for $100.00 of usage	vs list price	Price source
1	OrbioCardCheapest right now Credits from a discount book, plus a 5% platform fee and card processing, both included in the quote.	$85.10 incl. $2.60 card processing	-14.9%	live quote
2	smaaartCard Credits from a discount book, plus a 5% platform fee on face value. Card processing and taxes shown at checkout.	$95.00 + card processing and tax at checkout (not in this number)	-5.0%	live quote
3	Direct from the labCard Prepaid credits at face value (OpenAI, Anthropic, Google…). Taxes may apply.	$100.00 no top-up fee	list price	face value
4	OpenRouterCrypto 5% on crypto purchases. No markup on model prices.	$105.00 fees included	+5.0%	published fee
5	OpenRouterCard 5.5% on card purchases, $0.80 minimum. No markup on model prices.	$105.50 fees included	+5.5%	published fee

Disclosure: this site is run by the team behind smaaart, one of the options compared. Tables are ranked by price only, from live quotes and published fees, including when smaaart isn't first. How we compare

Hy3 cost calculator

Enter your monthly tokens to price your own usage.

Model$0.132 in / $0.528 out per 1M tokens · list price, liveInput tokens / month (millions)Output tokens / month (millions)

Usage at list price$11.88/ month(quotes below are for $12.00: purchases run from $5.00 to $10,000.00)

Cheaper alternatives to Hy3

Other labs' models in the same price range or the one below, cheaper per token.

Model	Input / 1M	Output / 1M	Blended 3:1	Context
OpenAI: GPT-6 Luna Pro	$0.1	$0.5	$0.2	1.1M
OpenAI: GPT-6 Luna	$0.1	$0.5	$0.2	1.1M
Qwen: Qwen3.8 Omni Flash	$0.15	$0.47	$0.23	1M
DeepSeek: DeepSeek V4.1 Flash	$0.03	$0.5	$0.147	1.0M
Qwen: Qwen3.8 Flash	$0.15	$0.47	$0.23	1M
Qwen: Qwen3.7 Flash	$0.03	$0.13	$0.055	1M

Other Tencent models

Model	Input / 1M	Output / 1M	Blended 3:1	Context
Hy-MT2-7B	$0.074	$0.295	$0.129	8K
Hy-MT2-30B-A3B	$0.074	$0.295	$0.129	8K
Hy-MT2-1.8B	$0.044	$0.177	$0.077	8K
Hy4 preview	$0.834	$2.50	$1.25	1.0M
Hy3 preview	$0.18	$0.6	$0.285	262K
Hunyuan A13B Instruct	$0.14	$0.57	$0.248	131K

All Tencent API prices