LLMtencent

Tencent: Hy3 (free)

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:...

Anyone in the Project can @-mention Tencent: Hy3 (free) with the team's shared context - pooled credits, one chat, one memory.

All models

Starter is free forever - 1 Project, 100 credits/month, 1 MCP. No card.

Verdict

Tencent's Hy3 offers a generous 262K token context window at zero cost, making it a practical choice for teams experimenting with long-document workflows or prototyping multi-turn applications without budget constraints. The lack of public benchmark data means you're trading proven performance metrics for free access to extended context. Reach for this when you need to test long-context ideas cheaply, but validate outputs carefully and plan a migration path to benchmarked models for production workloads.

Best for

Prototyping long-document applications
Budget-constrained experimentation
Multi-turn conversation testing
Educational and learning projects
Exploratory data analysis on large texts

Strengths

The 262K token context window handles full-length books, extensive codebases, or multi-document analysis in a single prompt. Zero-cost pricing removes financial friction from iteration cycles, letting teams test prompt strategies and workflow designs without metering anxiety. The extended context makes it viable for applications like meeting transcript summarization, legal document review prototypes, or RAG system development where you need to process large inputs during the build phase.

Trade-offs

No public benchmarks means you're flying blind on coding accuracy, reasoning depth, and factual reliability compared to models like GPT-4o or Claude Sonnet. Tencent's proprietary license limits transparency into training data and safety mitigations. Free tier models often come with rate limits or availability constraints that aren't documented upfront. Without performance data, you'll need to run your own evals before trusting this for anything beyond throwaway experiments or internal tooling.

Specifications

Provider: tencent
Category: llm
Context length: 262,144 tokens
Max output: 262,144 tokens
Modalities: text
License: proprietary
Released: 2026-07-06

Pricing

Input: $0.00/Mtok
Output: $0.00/Mtok
Model ID: tencent/hy3:free

Per-token prices show what the model costs upstream. On Switchy your team draws from one shared org credit pool - one plan, one balance for everyone.

Team cost calculator

Seats5 peopleMessages / seat / day80Avg turn size2 ktokOutput share30 %

Estimated monthly spend

Freeno token cost

17.6M tokens / month
5 seats · 80 msgs/day

Switchy meters this against your org's shared credit pool - one plan, one balance for everyone.

Providers

Provider-level routing data is not available yet for this model.

Performance

Performance snapshots are collected daily. Check back after the next ingestion run.

Benchmarks

Public benchmark scores are not available yet for this model. Check back after the next ingestion run.

Works well with

Top MCPs

Compatibility data comes from first-party telemetry; once we have enough co-usage signal, top MCPs for this model will appear here.

How Switchy teams use it

Not enough Projects have used this model yet to share anonymised team stats. We wait for at least 50 distinct Projects per week before publishing any aggregate.

Starter prompts

Summarize Long Transcript

Read this complete transcript and create a structured summary with three sections: key decisions made, action items with owners, and unresolved questions. Format as markdown with clear headings.

Open in a Project →

Compare Multiple Documents

I'm providing three policy documents below. Identify where they conflict, where they align, and flag any gaps in coverage. Present findings in a comparison table.

Open in a Project →

Extract Entities from Codebase

Analyze this codebase and generate a dependency graph showing which functions call which, including external library imports. Output as a mermaid diagram.

Open in a Project →

Synthesize Research Papers

I've included four research papers on the same topic. Synthesize the main findings, highlight where studies disagree, and suggest what questions remain unanswered.

Open in a Project →

Draft from Scattered Notes

Turn these scattered notes and email threads into a single project brief with background, objectives, success metrics, and next steps. Keep it under 500 words.

Open in a Project →