Tencent Hy3
TL;DR
Open-sourceFree sparse-MoE reasoning and agentic tool use through July 21, 2026.
Available on
Open-source models are available on every plan, including Go ($1/mo).
Switch with
Pick Tencent Hy3 from the selector.
Intelligence Index
Tencent Hy3 vs the top of the lineup
Claude Fable 5
GPT-5.6 Sol
Claude Opus 4.8
Tencent Hy3
Speed
~58
tokens / sec
Input
Free right now
per M tokens
Output
Free right now
per M tokens
Tencent Hy3 deal: Free
Free through July 21, 2026. Every request is billed $0. See the deal for details.
Tencent Hy3 in Command Code
Tencent Hy3 is Tencent's open-source model — sparse-MoE reasoning & agentic tool use. It runs in Command Code with a 262K-token context window, switchable any time with /model.
It scores 41.2 on the Intelligence Index — #22 of the 38 scored models in the Command Code lineup.
Tencent Hy3 specs at a glance
What Tencent Hy3 accepts, how much it can hold in context, and what you need to run it.
| Spec | Tencent Hy3 |
|---|---|
| Context window | 262K tokens |
| Input modalities | text |
| Reasoning | Yes |
| Release date | 2026-07-06 |
| Minimum plan | Go |
Tencent Hy3 vs the Command Code lineup
Tencent Hy3 alongside its nearest real alternatives in the lineup — every price straight from the billing tables.
| Model | Intelligence | Coding | Speed | Input $/M | Output $/M | Blended $/M | Context |
|---|---|---|---|---|---|---|---|
| Claude Fable 5 | 59.9 | 76.5 | ~62 tok/s | $10.00 | $50.00 | $20 | 1M |
| MiMo V2.5 Pro | 42.2 | 60.2 | ~56 tok/s | $0.435 | $0.87 | $0.5438 | 1M |
| Kimi K2.7 Code | 41.9 | 60.8 | ~46 tok/s | $0.95 | $4.00 | $1.7125 | 256K |
| Tencent Hy3 (this page) | 41.2 | 58.8 | ~58 tok/s | $0.00 | $0.00 | free | 262K |
| DeepSeek V4 Flash | 40.3 | 56.2 | ~106 tok/s | $0.14 | $0.28 | $0.175 | 1M |
| GLM-5.1 | 40.2 | 55.8 | ~81 tok/s | $1.40 | $4.40 | $2.15 | 200K |
| Step 3.5 Flash | 26 | — | ~207 tok/s | $0.10 | $0.30 | $0.15 | 1M |
What Tencent Hy3 is best for
Tencent Hy3 is a open-source model from Tencent, free right now, so it costs nothing to evaluate on your own workload. It trades speed for depth — better for batch and background work than rapid iteration.
The honest way to place it: run your own session with /model and compare against the lineup table above — the numbers on this page update as the registry and billing tables change.
When to switch away from Tencent Hy3
No single model wins every task. These are Tencent Hy3's computed nearest alternatives — one step up, one step down in cost, one for speed, one from the same family — each switchable mid-session with /model.
Switch to Kimi K2.7 Code
Kimi K2.7 Code scores 41.9 on the Intelligence Index to Tencent Hy3's 41.2 — the nearest genuine step up — at $1.7125 blended per million tokens versus free. Reach for it when a task keeps hitting Tencent Hy3's ceiling.
Switch to Step 3.5 Flash
Step 3.5 Flash streams ~207 tokens/sec to Tencent Hy3's ~58 at a comparable blended cost ($0.15 per million tokens). Use it when iteration speed matters more than squeezing out the last point of quality.
What you pay for Tencent Hy3
Tencent Hy3 is free right now — every request is billed $0 while the deal runs. The rates below are what billing actually charges today.
Blended cost (3:1 input:output, the shape of a typical coding session) works out to free per million tokens.
| Per 1M tokens | Input | Output | Cache read |
|---|---|---|---|
| All requests | $0.00 | $0.00 | $0.00 |
In Command Code: caching and taste-1
Open-source models are routed across multiple upstream providers for high availability. The price you see is the mean per-provider rate; the Usage page reflects what was actually charged.
Where supported by the upstream, prompt caching is on by default — cache reads are billed at $0.00 per million tokens versus $0.00 for fresh input.
taste-1 sits between the model and the agent loop, rewriting and reranking candidate edits to match your codebase conventions.
Plan availability
Tencent Hy3 is an open-source model, available on every plan including Go.
Command Code is a subscription with model usage at API rates. Each plan ships with monthly LLM credits; credits roll over and never expire, and auto top-up keeps you running if you go over.
| Plan | Price/mo | LLM credits | Models |
|---|---|---|---|
| Go | $1 | $10 | Open-source only |
| Pro | $15 | $30 | Open-source + premium |
| Provider | $15 | Pay as you go | Open-source + premium |
| Max 10× | $100 | $150 | Open-source + premium |
| Max 20× | $200 | $300 | Open-source + premium |
| Teams Pro | $40 / seat | $40 / seat | Open-source + premium |
| Enterprise | Custom | Custom | Custom pool, SSO, audit logs |
Free-tier billing in Command Code
Tencent Hy3 is billed at $0 for input, output, and cache-read tokens while the free tier is active. The Usage page still records token counts and request history, but these requests do not spend Command Code credits.
Switching models with /model
In an interactive Command Code session, run /model to open the model selector. Pick Tencent Hy3 and it applies to this session and to future sessions until you change it again. Premium models require Pro or higher; open-source models are available on every plan, including Go.
cmd # start an interactive session
/model # open the selector and pick Tencent Hy3All Command Code models, ranked by quality and speed
Quality is the Intelligence Index — an aggregate score across reasoning, math, coding, and knowledge evaluations. Speed is measured output tokens per second. Models without a published score are noted. This table is regenerated from the model registry, so it is always current.
| Model | Tier | Intelligence Index | Output speed |
|---|---|---|---|
| Claude Fable 5 | Premium | 59.9 | ~62 tok/s |
| GPT-5.6 Sol | Premium | 58.9 | ~77 tok/s |
| Claude Opus 4.8 | Premium | 55.7 | ~55 tok/s |
| GPT-5.6 Terra | Premium | 55 | ~155 tok/s |
| GPT-5.5 | Premium | 54.8 | ~81 tok/s |
| Grok 4.5 | Open-source | 53.8 | ~114 tok/s |
| Claude Opus 4.7 | Premium | 53.5 | ~52 tok/s |
| Claude Sonnet 5 | Premium | 53.4 | ~79 tok/s |
| GPT-5.4 | Premium | 51.4 | ~164 tok/s |
| GPT-5.6 Luna | Premium | 51.2 | ~234 tok/s |
| GLM-5.2 | Open-source | 51.1 | ~208 tok/s |
| Muse Spark 1.1 | Premium | 50.6 | ~130 tok/s |
| Gemini 3.5 Flash | Premium | 50.2 | ~236 tok/s |
| Claude Sonnet 4.6 | Premium | 47.2 | ~55 tok/s |
| Qwen 3.7 Max | Open-source | 46 | ~196 tok/s |
| MiniMax M3 | Open-source | 44.4 | ~113 tok/s |
| DeepSeek V4 Pro | Open-source | 44.3 | ~62 tok/s |
| GPT-5.3 Codex | Premium | 44.3 | ~106 tok/s |
| Kimi K2.6 | Open-source | 44.2 | ~43 tok/s |
| MiMo V2.5 Pro | Open-source | 42.2 | ~56 tok/s |
| Kimi K2.7 Code | Open-source | 41.9 | ~46 tok/s |
| Tencent Hy3 (this page) | Open-source | 41.2 | ~58 tok/s |
| DeepSeek V4 Flash | Open-source | 40.3 | ~106 tok/s |
| GLM-5.1 | Open-source | 40.2 | ~81 tok/s |
| Qwen 3.6 Max Preview | Open-source | 40 | ~46 tok/s |
| GPT-5.4 Mini | Premium | 40 | ~171 tok/s |
| Qwen 3.6 Plus | Open-source | 39.6 | ~53 tok/s |
| GLM-5 | Open-source | 39.5 | ~51 tok/s |
| Qwen 3.7 Plus | Open-source | 39 | ~52 tok/s |
| Kimi K2.5 | Open-source | 38.1 | ~51 tok/s |
| MiniMax M2.7 | Open-source | 38.1 | ~49 tok/s |
| Nemotron 3 Ultra | Open-source | 37.8 | ~204 tok/s |
| MiMo V2.5 | Open-source | 37.2 | ~88 tok/s |
| MiniMax M2.5 | Open-source | 33.7 | ~78 tok/s |
| Step 3.7 Flash | Open-source | 30.3 | ~407 tok/s |
| Step 3.5 Flash | Open-source | 26 | ~207 tok/s |
| Gemini 3.1 Flash Lite | Premium | 25 | ~300 tok/s |
| Claude Haiku 4.5 | Premium | 23.7 | ~103 tok/s |
| Kimi K3 | Open-source | Not yet scored | — |
| Kimi K2.7 Code HighSpeed | Open-source | Not yet scored | — |
| GLM-5.2 Fast | Open-source | Not yet scored | — |
| Inkling | Open-source | Not yet scored | — |
| Fugu Ultra | Premium | Not yet scored | — |
Frequently asked questions
Tencent Hy3 or Kimi K2.7 Code?
Kimi K2.7 Code scores higher on the Intelligence Index (41.9 vs 41.2) at $1.7125 blended per million tokens against Tencent Hy3's free. Default to Tencent Hy3 and switch up when a task keeps stalling.
How much does Tencent Hy3 cost in Command Code?
Tencent Hy3 is free right now — every request is billed $0 while the deal runs. Its regular rates apply once the deal ends; see the pricing table on this page.
What plan do I need for Tencent Hy3?
Tencent Hy3 is available on every plan, including Go at $1/mo.
How good is Tencent Hy3 at coding?
Tencent Hy3 scores 58.8 on the Coding Index — the Artificial Analysis sub-score most predictive of coding-agent performance — alongside 41.2 overall.
Does Tencent Hy3 support image input and reasoning?
Tencent Hy3 is text-only; paste code and logs rather than screenshots. It supports reasoning.
Which Command Code model should I use?
Claude Fable 5 currently leads the lineup on the Intelligence Index (59.9). Grok 4.5 (53.8) leads the open-weights tier, available on every plan. For fast lookups, Step 3.7 Flash streams ~407 tok/s. There is no single right answer — switch per session with /model and let the task pick the model.
Can I mix Tencent Hy3 with other models in a workflow?
Yes. Switch per session using /model. Common pattern: keep a default model and switch up for hard problems or down for quick lookups as the task calls for it.
Are open-source model prices fixed?
Open-source models are routed across multiple upstream providers for high availability. The price listed for each is the mean per-provider rate. Actual cost on a given request may vary slightly. The Usage page reflects the price charged.
Is Tencent Hy3 benchmarked?
Not yet in the current Intelligence Index. It is available in Command Code as a 295B sparse-MoE reasoning model with tool calling and a 256K context window.
Is Command Code free to try?
The Go plan starts at $1/mo with $10 in LLM credits. It covers open-source models only. Pro at $15/mo unlocks premium models with $30 in LLM credits.
Does Command Code train on my code?
No. Command Code does not train on your code or store your code snippets. taste-1 data is stored locally in your project directory.
Where can I track my usage?
The Usage page in Studio shows per-request cost, token counts, and which model ran. Settings > Billing lets you change plans, buy credits, or enable auto top-up.
Does Command Code replace my editor?
No. Command Code is editor-agnostic — it runs as a CLI and works alongside any editor (Cursor, VS Code, Zed, JetBrains, Neovim, etc.).
Related reading
- Kimi K2.7 Code in Command Codeimproved long-horizon coding with vision
- DeepSeek V4 Flash in Command Codefast hybrid-attention reasoning
- Every model, one referenceThe docs list of all Command Code models with ids and context windows.
- Pricing, limits, and dealsThe canonical price table, running deals, and usage estimates.
Ship code that matches your taste
Command Code is the AI coding agent that continuously learns your taste. Start for $1.