Tencent Hy3: 295B MoE Hits SWE-Bench 78 — Free API Ends July 21

Tencent released Hy3, a 295B Mixture-of-Experts model with Apache 2.0 weights, achieving a 78.0 SWE-bench Verified score and leading open-weight models on tool and search benchmarks. A free API on OpenRouter is available until July 21, after which pricing will be $0.20 per million input tokens and $0.80 per million output tokens, offering a cost-effective alternative to proprietary models like Claude Sonnet 5.

Tencent dropped Hy3 on July 6 — a 295B Mixture-of-Experts model with Apache 2.0 weights, a 78.0 SWE-bench Verified score, and a free API on OpenRouter that expires July 21. If you’re choosing a coding agent backend or evaluating open-weight models for agentic workflows, you have 13 days to test it at zero cost. What the SWE-Bench Score Actually Means Hy3 hits 78.0 on SWE-bench Verified. That number deserves context before you act on it. GLM-5.2 https://byteiota.com/zcode-glm-52-china-data-risk/ scores 84.2 on the same benchmark. Claude Sonnet 5 leads the full BenchLM leaderboard at around 87 across agentic, coding, and reasoning tasks. So Hy3 is not the top coder — and Tencent doesn’t pretend it is. Where Hy3 leads is tool and search workloads: 84.2 on BrowseComp, 91.0 on DeepSearchQA, and 79.1 on MCP-Atlas tool orchestration — best in the open-weight field on all three. If your agent crawls the web, calls MCP servers, or does long-context retrieval, Hy3’s benchmark profile fits that workload better than its SWE-bench number suggests. Benchmark stability is also worth noting. Tencent tested Hy3 across KiloCode, Cline, and CodeBuddy scaffoldings and reported less than 4% accuracy variance. That kind of consistency across frameworks matters in production — a model that performs differently depending on your agent harness is a reliability problem. The Free API Closes July 21 OpenRouter’s tencent/hy3:free endpoint is live now. Cost: $0 per million tokens, input or output. On July 21, that flips to $0.20 per million input tokens and $0.80 per million output tokens. After the free window closes, Hy3 is still substantially cheaper than alternatives — Claude Sonnet 5 https://byteiota.com/claude-sonnet-5-migration-three-breaking-api-changes/ runs around $3/$15 per million tokens, making Hy3 roughly 15x cheaper at the post-July-21 rate. But you won’t get another free evaluation window. The time to test it is now. The API is OpenAI-compatible. Swap your base URL, change the model name, done: python from openai import OpenAI import os client = OpenAI api key=os.getenv "OPENROUTER API KEY" , base url="https://openrouter.ai/api/v1" response = client.chat.completions.create model="tencent/hy3:free", messages= {"role": "user", "content": "Review this function for bugs: ..."} , extra body={"reasoning effort": "high"} print response.choices 0 .message.content The reasoning effort parameter controls chain-of-thought depth: "no think" for fast direct responses, "low" for light reasoning, "high" for complex tasks like multi-step code review or debugging. Set it wrong and you’re either wasting tokens or missing accuracy. Apache 2.0 — No Regional Restrictions The April 2026 preview version excluded the EU, UK, and South Korea from its license. The July 6 official release fixes that. Hy3 is now Apache 2.0 with zero geographic exclusions — self-host it, fine-tune it, ship it in commercial products, anywhere. That matters more than it sounds. GLM-5.2 outperforms Hy3 on SWE-bench, but carries usage constraints that matter to enterprise deployments. Hy3 with a clean Apache 2.0 license at $0.20/$0.80 per million tokens post-July-21 is a different risk profile for teams that can’t accept third-party data egress or unclear regional terms. Self-Hosting: What You Actually Need The weights are on Hugging Face at tencent/Hy3 https://huggingface.co/tencent/Hy3 BF16 and tencent/Hy3-FP8 https://huggingface.co/tencent/Hy3-FP8 . Self-hosting a 295B MoE model isn’t casual — Tencent recommends 8 H20 GPUs or equivalent high-memory cards. For vLLM, the relevant flags are --tool-call-parser hy v3 and --reasoning-parser hy v3 with --enable-auto-tool-choice . SGLang uses --tool-call-parser hunyuan and --reasoning-parser hunyuan . Both support MTP speculative decoding for faster inference. Most teams will start with the OpenRouter API and self-host only if the use case justifies the GPU spend. That’s a reasonable progression. What to Do Before July 21 If you run agent workflows involving web search, MCP tools, or long-context retrieval: Hy3 is the right thing to test this week. Its SWE-bench score is real but not the whole picture — the tool and search benchmarks suggest a model tuned for exactly this class of workload. If you need the best pure coding performance in the open-weight tier: GLM-5.2 still wins. Hy3 is not that model. Start at OpenRouter’s free endpoint https://openrouter.ai/tencent/hy3:free . The weights are at github.com/Tencent-Hunyuan/Hy3 https://github.com/Tencent-Hunyuan/Hy3 . The free window closes July 21.