--- title: "Tencent: Hy3 — price, capability and what beats it · Undominated.ai" canonical: https://undominated.ai/models/tencent__hy3/ description: "Tencent: Hy3: $0.132/M in, $0.528/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements." --- # Tencent: Hy3 — price, capability and what beats it · Undominated.ai > Tencent: Hy3: $0.132/M in, $0.528/M out. Independent capability scores, and alternatives compared under recorded workload and capability requirements. [Check base rates for this workload](/check/tencent__hy3/) [Cheaper alternatives](/alternatives/tencent__hy3/) [Family](/families/hunyuan/) [Compare models](https://undominated.ai/compare/?models=tencent%2Fhy3) Comparison context Choose up to three standard models in Compare. Requirements and prompt length apply in Compare. This page keeps its stated price basis and workload controls. MODEL PROOF # Hy3 Tencent · 06 Jul 2026 Balanced Summarise Chat Code gen Agentic BETTER VALUE OPTION ## A stored alternative has an equal-or-higher measured score and an equal-or-lower price. **$0.231** / 1M tokens Balanced · 3 tokens in per 1 out Standard-window rate shown; discount 16:00–24:00 UTC every day: $0.083 in · $0.330 out. · Serving precision differs between offers. [DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) · Δ score 21.8 points · 21% lower measured price · $0.182 / 1M tokens [Gemma 4 31B](/models/google__gemma-4-31b-it/) is a further stored option with these losses: 128K → 16K max output Evidence as of 06 Oct 2026 [openrouter/models](https://openrouter.ai/api/v1/models) [LMArena · cc-by-4.0](https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset) Independent LMArena score 1,440.7 ± 6.5 · 10,476 votes Context window 262.14K Maximum output 128K Input modalities text Output modalities text Published input price $0.132 / 1M tokens Published output price $0.528 / 1M tokens Pricing kind fixed Inspect [complete billing conditions](#billing-details) and endpoint terms below. Price from Tencent: the cheapest offer that is serving, at standard delivery and at the maker’s precision or better, at its standard rate. Cheaper right now: $0.230/M at DeepInfra — 4-bit It does not pass the like-for-like test, so it never sets a rank. Every price dimension · USD per million tokens | Input | $0.132 /M | | --- | --- | | Output | $0.528 /M | | Cached input | $0.033 /M | | Cache write | Unknown /M | | Cache write 1h | Unknown /M | | Reasoning | Unknown /M | **Price varies by time of day. The headline is the standard rate**, $0.132 in · $0.528 out. Discount window 16:00–24:00 UTC every day: $0.083 in · $0.330 out. The discount is 38% off input. The windows come from the tencent/fp8 endpoint in the upstream endpoints feed, not from the time this page was built. ### Who sells it The same weights, different shops. Cheapest is not like-for-like when serving precision differs. Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.140/M from GMICloud. 6 provider offers · rates, limits and conditions Rates are USD per million tokens. Endpoint terms can differ even when the quoted price and precision match. A listed parameter is a provider declaration, not a task-success test. | Seller | Input | Output | Precision | Uptime (1d) | | --- | --- | --- | --- | --- | | Seller DeepInfra deepinfra/fp4 Endpoint terms Cached input /M $0.033 Context limit 262,144 tokens Output limit 131,072 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.130 | Output $0.530 | Precision fp4 | Uptime (1d) 99.81% | | Seller Tencent tencent/fp8 Endpoint terms Cached input /M $0.033 Context limit 262,144 tokens Output limit 128,000 tokens Tools Listed by endpoint Reasoning Listed by endpoint Time windows Standard-window rate shown. Discount 16:00–24:00 UTC every day: $0.083 in · $0.330 out. Promotional discount None reported Uptime · last 30 minutes 99.93% | Input $0.132 | Output $0.528 | Precision fp8 | Uptime (1d) 99.81% | | Seller GMICloud gmicloud/bf16 Endpoint terms Cached input /M $0.035 Context limit 262,144 tokens Output limit 235,929 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.140 | Output $0.580 | Precision bf16 | Uptime (1d) 99.91% | | Seller Novita novita Endpoint terms Cached input /M $0.035 Context limit 262,144 tokens Output limit 235,929 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.85% | Input $0.140 | Output $0.580 | Precision undeclared | Uptime (1d) 99.52% | | Seller Phala phala Endpoint terms Cached input /M $0.040 Context limit 262,144 tokens Output limit 235,929 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 99.91% | Input $0.150 | Output $0.640 | Precision undeclared | Uptime (1d) 99.81% | | Seller AtlasCloud atlas-cloud/fp8 Endpoint terms Cached input /M $0.050 Context limit 262,144 tokens Output limit 131,072 tokens Tools Listed by endpoint Reasoning Listed by endpoint Promotional discount None reported Uptime · last 30 minutes 100.00% | Input $0.200 | Output $0.800 | Precision fp8 | Uptime (1d) 99.92% | ### Independent scores | LMArena Elo | 1440.7 default | | --- | --- | LMArena Elo under CC BY 4.0. Absence of another board is not a score of zero. #### Best rankings by task - 3D #50 1184 - Code categories #60 1181 - Websites #65 1189 - UI components #67 1170 - Game development #71 1149 - Data visualisation #84 1132 Per-task Elo and rank from [Design Arena](https://designarena.ai), via OpenRouter’s model feed. The rank is the feed’s, and it counts models OpenRouter does not list. ### Capability | Context window | 262K | | --- | --- | | Max output | 128K | | Input modes | text | | Tool use | yes | | Reasoning | optional | | Open weights | Unknown | ### Provenance | Price source | [openrouter.ai](https://openrouter.ai/api/v1/models) | | --- | --- | | Fetched | 2026-10-06 | | Quality data | verified | 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:... ## Questions this page answers What does Hy3 cost? $0.132/M in, $0.528/M out in this catalogue, as of the fetch date on this page. That is the API row, not a subscription. Does Hy3 have an independent quality score? Hy3 has an LMArena score in this catalogue. What beats Hy3? DeepSeek V4.1 Flash has an equal-or-higher measured score and an equal-or-lower price. Does this page use Artificial Analysis scores for Hy3? No. Artificial Analysis figures are not published here. Quality on this page is LMArena Elo where a score exists; otherwise the row is unrated. Is the cheapest Hy3 endpoint the same product? Headline cheapest is a lower precision. Like-for-like at the best declared precision is $0.140/M from GMICloud. MODEL MONUMENT ## Save or share this proof Download proof card · 1200 × 630 Preview and more sharing options Tencent: Hy3. Balanced workload. Better value option available. Evidence as of 06 Oct 2026. Copy model link Download square card · 1080 × 1080 Copy landscape image Share landscape card ## Related - Both better and cheaper [DeepSeek V4.1 Flash](/models/deepseek__deepseek-v4.1-flash/) - Higher score and cheaper, with a named trade [Gemma 4 31B](/models/google__gemma-4-31b-it/) - Nearby on the capability axis [Qwen3.8 27B](/models/qwen__qwen3.8-27b/) - Same vendor [Hunyuan A13B Instruct](/models/tencent__hunyuan-a13b-instruct/) - Tencent models [Tencent](/providers/tencent/) - Where this model appears [wire](/wire/) - Nearby on the capability axis [GLM 4.6](/models/z-ai__glm-4.6/) - Same vendor [Hy-MT2-1.8B](/models/tencent__hy-mt2-1.8b/) - Where this model appears [spreads](/spreads/) - Nearby on the capability axis [Inkling](/models/thinkingmachines__inkling/) - Same vendor [Hy-MT2-30B-A3B](/models/tencent__hy-mt2-30b-a3b/) - Where this model appears [traps](/traps/) ## Badge The verdict as one SVG, for a README or a docs page. It states this model's dominance status at the balanced workload on the LMArena lens, with the date it was computed, and it is rebuilt with the catalogue — so it changes when the verdict changes, including to one you would rather it did not. Markdown Copy [![Hy3 — Undominated.ai dominance verdict](https://undominated.ai/badge/tencent__hy3.svg)](https://undominated.ai/models/tencent__hy3/) HTML Copy Hy3 — Undominated.ai dominance verdict Direct file: [https://undominated.ai/badge/tencent__hy3.svg](https://undominated.ai/badge/tencent__hy3.svg) — a static SVG, written by scripts/build-badges.mjs on every build, so the copy you embed is never older than the last deploy. ## Continue your investigation - [Explore model families](/families/) - [Compare a shortlist](/compare/) - [Check a model](/check/) - [Understand the evidence](/methodology/)