Hy3 API Benchmarks, Pricing & Provider Data
Compare Hy3 with another model
Choose a model to open its comparison page.
Hy3 benchmark, API pricing, and provider data cover 22 API providers, with prices starting at $0.0014/request. Hy3 free API options are available from 2 providers. The page also shows measured API speed and first-token latency.
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 configur...
Category Performance
Observed-capability estimates with uncertainty reported separately from independent benchmark families.
- Coverage
- 4 / 8
- Methodology
- V3.0
#1Coding57.6Provisional1/4 Measured dimensions
#2Reasoning56.8Estimated2/4 Measured dimensions
#3Agents52.3Provisional1/4 Measured dimensions
#4Knowledge47Provisional1/4 Measured dimensions
Specifications
Input and output token limits for this model, plus how it ranks on long-context understanding.
Features
Technical Details
- Input
- Output
- Released
- Jul 2026
- Tokenizer
- Other
- Architecture
- text->text
- Moderated
- No
- Supported parameters
- frequency_penaltyinclude_reasoninglogit_biasmax_tokensmin_ppresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_p
Rankings
Excels at
Falls behind in
Detailed scores
Updated: Aug 26, 2026Speed & latency
undefined metric} other undefined metrics}}
Output speed75.8 tok/s#46 / 75Time to first token1.80 s#54 / 75
Speed & latency
undefined metric} other undefined metrics}}
Pricing
undefined metric} other undefined metrics}}
Input price$0.136/M#18 / 179Output price$0.554/M#22 / 179
Pricing
undefined metric} other undefined metrics}}
Agents
V3.0undefined metric} other undefined metrics}} · Provisional
Score52.380% interval36.3–68.31/4 Measured dimensionsAA Agentic Index31.4#27 / 65GDPval-AA35.7#30 / 61
Agents
V3.0undefined metric} other undefined metrics}} · Provisional
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Score57.680% interval41.6–73.61/4 Measured dimensionsSciCode47.6%#31 / 204AA-SciCode47.6#36 / 108
Coding
V3.0undefined metric} other undefined metrics}} · Provisional
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Score56.880% interval46.0–67.52/4 Measured dimensionsGPQA89.7%#34 / 211HLE33.5%#44 / 208
Reasoning
V3.0undefined metric} other undefined metrics}} · Estimated
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Score4780% interval31.0–63.01/4 Measured dimensionsArtificial Analysis Intelligence Index42.2#33 / 111AA-GPQA Diamond89.7#32 / 108
Knowledge
V3.0undefined metric} other undefined metrics}} · Provisional
Math
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Math
V3.0undefined metric} other undefined metrics}} · No data
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Multilingual
V3.0undefined metric} other undefined metrics}} · No data
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
80% interval30.8–69.20/4 Measured dimensionsDesign Arena Website1194.0#50 / 75
Multimodal
V3.0undefined metric} other undefined metrics}} · No data
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
No data80% interval30.8–69.20/4 Measured dimensions
Instruction following
V3.0undefined metric} other undefined metrics}} · No data
OpenRouter endpoints
7 endpointsThird-party OpenRouter endpoint data, shown separately from LMSpeed measurements. Some 30-minute live performance fields only appear after syncing with an OpenRouter API key.
| Provider endpoint | Input | Output | 1d uptime | 30m latency | 30m throughput | Context / output |
|---|---|---|---|---|---|---|
AtlasCloud atlas-cloud/fp8 | $0.200/M | $0.800/M | 100.0% | — | — | undefined tokens / undefined tokens |
Baidu baidu/fp8 | $0.132/M | $0.528/M | 100.0% | — | — | undefined tokens / undefined tokens |
GMICloud gmicloud/bf16 | $0.126/M | $0.522/M | 99.9% | — | — | undefined tokens / undefined tokens |
Tencent tencent/fp8 | $0.132/M | $0.528/M | 99.7% | — | — | undefined tokens / undefined tokens |
Novita novita | $0.140/M | $0.580/M | 99.3% | — | — | undefined tokens / undefined tokens |
Phala phala | $0.150/M | $0.640/M | 98.2% | — | — | undefined tokens / undefined tokens |
DeepInfra deepinfra/fp8 | $0.140/M | $0.580/M | 94.2% | — | — | undefined tokens / undefined tokens |
Pricing Comparison
Compare Hy3 API pricing across 20 providers. Prices range from $0.0014/request to $375.00/M. 钠 API offers the lowest rate at $0.0014/request. 2 providers offer free API credits or a free tier.
| Provider | Health | Model Variant | Group | Input ($/M) | Output ($/M) | Speed (t/s) | First token | Audit |
|---|---|---|---|---|---|---|---|---|
L1 100% | hy3 | hunyuan-officially | -16%$0.114/M Cache read$0.029/M | -17%$0.457/M | — | — | — | |
L1 100% | Tencent/hy3 | default | $0.0014/request | - | — | — | — | |
L1 100% | Tencent-Hunyuan/Hy3 | default | $0.0014/request | - | — | — | — | |
L1 99% | hy3 | default | $0.490/M Cache read$0.122/M | $1.96/M | — | — | — | |
L1 99% | hy3 | default | $60.00/M | $60.00/M | — | — | — | |
L1 100% | hy3 | default | -93%$0.0096/M Cache read$0.0024/M | -93%$0.040/M | — | — | — | |
L1 100% | tencent/hy3:free | default | $375.00/M | $375.00/M | — | — | — | |
L1 100% | hy3-free | default | $375.00/M | $375.00/M | — | — | — | |
L1 99% | hy3 | 企业用户 | $75.00/M | $75.00/M | — | — | — | |
L1 99% | hy3 | default | $2.00/M Cache read$0.200/M | $10.00/M | — | — | — | |
Dext API Free | L1 19% | hy3 | 公益 | Free | Free | — | — | — |
L1 0% | tencent/hy3:free | default | $0.140/M | $0.559/M | — | — | — | |
L1 0% | Hy3 | default | $75.00/M | $75.00/M | — | — | — |
Alternatives & Similar Models
DeepSeek V4 Flash
deepseek-v4-flash
DeepSeek V4 Flash is a fast, cost-efficient language model in the DeepSeek V4 family, optimized for low-latency chat, coding assistance, and high-throughput API workloads while retaining strong reasoning quality.
Kimi K2.5
kimi-k2-5
Moonshot Kimi K2.5 is an open-weight multimodal agent model with native vision and text input, strong coding performance, and a 256K context window.
GLM-5.2
glm-5-2
Zhipu GLM-5.2 is Zhipu latest flagship coding and agentic model with a 1M-token context window, enhanced reasoning modes, and long-horizon software engineering capabilities.
DeepSeek V4 Pro
deepseek-v4-pro
DeepSeek V4 Pro is the professional-tier DeepSeek V4 model, targeting frontier reasoning, coding, and agent workflows with maximum capability.
GLM-5
glm-5
Zhipu GLM-5 is Zhipu flagship GLM series model with enhanced reasoning, agent capabilities, and strong performance on Chinese enterprise and coding scenarios.
MiniMax M2.7
minimax-m2-7
MiniMax M2.7 is a high-tier M2-series model tuned for complex reasoning, long-context dialogue, and production-grade API workloads.
Frequently Asked Questions
- What benchmark data does Hy3 include?
- LMSpeed shows Hy3 benchmark context, API price, output speed, first-token latency, and provider data across 22 providers when those signals are available.
- What is the Hy3 API price?
- Hy3 has pricing from 22 providers, ranging from $0.0014/request to $375.00/M. 钠 API has the lowest listed price.
- What does the Hy3 API pricing table include?
- The Hy3 API pricing table compares 22 providers by input price, output price, free tier status, speed, first-token latency, and recent health data when available.
- Which provider has the cheapest Hy3 API pricing?
- 钠 API currently has the lowest listed Hy3 price at $0.0014/request across 22 providers.
- Can I compare Hy3 API price and speed together?
- Yes. LMSpeed shows Hy3 API price, output speed, first-token latency, and provider health on the same page so you can compare cost and performance together.
- Is Hy3 API free?
- Yes, Hy3 free API options are available through 2 providerundefined other undefined} on LMSpeed, including Dext API, Zero API. These providers offer free API credits or a free tier with no per-token charges.
- Where can I get Hy3 free API access?
- LMSpeed currently lists 2 free API providerundefined other undefined} for Hy3: Dext API, Zero API. Check each provider row before using it because free tier limits can change.