Last verified
FRONTIER MoE256K CONTEXTTEXTOPEN WEIGHTPROMPT CACHING

Hunyuan Hy3 API Pricing

Hunyuan Hy3 is Tencent's newest Hunyuan flagship - a hybrid fast/slow-thinking 295B/21B MoE released July 6, 2026. Tencent Cloud's TokenHub lists Y1.00/M input, Y4.00/M output, and Y0.25/M cached input, which AI//COST stores as $0.141/M, $0.563/M, and $0.035/M at Y7.1/USD. Pulled directly from cloud.tencent.com.

Input - per 1M tokens
$0.14/M
Original Y1.00/M CNY source
Output - per 1M tokens
$0.56/M
Original Y4.00/M CNY source
Cached input - 75% off
$0.04/M
Original Y0.25/M -75%
Effective - agentic blend
$0.09/M
92/8 split - 82% cache
§ 01 / TERMINAL

Run the numbers.

Live calculator pre-loaded with Hunyuan Hy3's current TokenHub rate. Tweak the workload mix and cache hit rate; share the URL to share the calculation.

$ /mo
Workload split
Prompt cache hit rate
Tokens you can process
Words equivalent (English)
Effective rate
Open full calculator (all models · share URL · CSV) →
§ 02 / SCENARIOS

Real-world presets.

§ 03 / TOKENIZER

Paste text. See tokens. See cost.

Calibrated · measured on the vendor's tokenizer · 2026-06-10 Auto-counts as you type

Counts use a chars-per-token calibration measured on the vendor's own published tokenizer (tencent/Hunyuan-A13B-Instruct, 2026-06-10). English prose is typically within a few percent; code and non-Latin scripts tokenize heavier. For billing-exact counts use the vendor's count-tokens API.

Characters 757
Words 114
Tokens (estimated) 145 tokens
Cost as input · uncached $0.000020 USD
Cost as output · uncached $0.000082 USD
Cost as cached input $0.000005 USD
§ 04 / SHELF

Up against the shelf.

All models →
Model Input /M Output /M Effective blended Context Best for
Hunyuan Hy3 Current $0.14 cache $0.04 $0.56 $0.09 agentic 92/8 256K Tencent's newest flagship - agentic coding
Hunyuan 2.0 Think $0.56 $2.24 $0.70 pricier reasoning tier 128K Deep-thinking reasoning
Hunyuan 2.0 Instruct $0.45 $1.12 $0.50 pricier instruct tier 128K Broader Tencent instruction work
Hunyuan T1 $0.14 $0.56 $0.17 no cache discount 64K Reasoning without cache pricing
Hunyuan TurboS $0.11 $0.28 $0.13 fast general tier 131K Fast general-purpose chat
Hunyuan A13B $0.07 $0.28 $0.09 similar blended cost 131K Low-cost Tencent traffic
DeepSeek V4 Flash $0.14 cache $0.00 $0.28 $0.05 cross-vendor budget benchmark 1M Cheap reasoning and coding

Frequently asked.

Practical Hunyuan Hy3 pricing questions, with the official TokenHub CNY table separated from calculator assumptions.

Q · 01 What is Hunyuan Hy3 priced at today? +
Tencent Cloud's TokenHub lists Hunyuan Hy3 at Y1.00/M input, Y4.00/M output, and Y0.25/M cached input. AI//COST stores that as $0.141/M, $0.563/M, and $0.035/M using the queue's Y7.1/USD conversion rate.
Q · 02 Does Hy3 have a cache-hit discount? +
Yes. TokenHub lists a cached-input rate of Y0.25/M (about $0.035/M), roughly 75% below the fresh-input rate. This is a flat single-rate row - the separate Hy3 preview row on TokenHub is input-length tiered and is not this general-availability model.
Q · 03 Is Hunyuan Hy3 open weight? +
Yes. Tencent released Hy3 under the commercially friendly Apache 2.0 license on Hugging Face and ModelScope from day one, alongside the hosted API on Tencent Cloud TokenHub. It is a 295B-total / 21B-active Mixture-of-Experts model.
Q · 04 What is the context window? +
Hy3 supports a 256K-token context window and is a hybrid fast/slow-thinking model (interleaved thinking) aimed at coding agents, document automation, and multi-step tool calling.
Q · 05 How does Hy3 compare with Hunyuan T1? +
Hunyuan T1 carries the same Y1.00/Y4.00 list rate but has no cache discount, so Hy3's Y0.25/M cached input makes it cheaper on cache-heavy agentic workloads. Hy3 is also newer, larger, and has a longer 256K context.
Q · 06 Does this page include tax or enterprise discounts? +
No. AI//COST stores Tencent's public pre-tax list price and converts it to USD for cross-vendor comparison. TokenHub subscription plans, contract discounts, and region-specific billing are outside this page.