Qwen 3.6 Max Preview
TL;DR
Open-sourceOpen-source vibe coding and efficient agent execution.
Available on
Open-source models are available on every plan, including Go ($1/mo).
Switch with
Pick Qwen 3.6 Max Preview from the selector.
Intelligence Index
Qwen 3.6 Max Preview vs the Alibaba lineup
Qwen 3.7 Max
Qwen 3.6 Max Preview
Qwen 3.6 Plus
Qwen 3.7 Plus
Speed
~46
tokens / sec
Input
$1.30
per M tokens
Output
$7.80
per M tokens
Qwen 3.6 Max Preview in Command Code
Qwen 3.6 Max Preview is Alibaba's open-source model — vibe coding & efficient agent execution. It runs in Command Code with a 200K-token context window, switchable any time with /model.
It scores 40 on the Intelligence Index — #25 of the 38 scored models in the Command Code lineup.
Qwen 3.6 Max Preview specs at a glance
What Qwen 3.6 Max Preview accepts, how much it can hold in context, and what you need to run it.
| Spec | Qwen 3.6 Max Preview |
|---|---|
| Context window | 200K tokens |
| Input modalities | text |
| Reasoning | Yes |
| Release date | 2026-04-20 |
| Minimum plan | Go |
Qwen 3.6 Max Preview vs the Command Code lineup
Qwen 3.6 Max Preview 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 |
| Tencent Hy3 | 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 |
| Qwen 3.6 Max Preview (this page) | 40 | — | ~46 tok/s | $1.30 | $7.80 | $2.925 | 200K |
| GPT-5.4 Mini | 40 | 56.1 | ~171 tok/s | $0.75 | $4.50 | $1.6875 | 400K |
| Qwen 3.6 Plus | 39.6 | 54.5 | ~53 tok/s | $0.50 | $3.00 | $1.125 | 200K |
What Qwen 3.6 Max Preview is best for
Qwen 3.6 Max Preview is a open-source model from Alibaba, priced at $2.925 blended per million tokens. 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 Qwen 3.6 Max Preview
No single model wins every task. These are Qwen 3.6 Max Preview'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 GLM-5.1
GLM-5.1 scores 40.2 on the Intelligence Index to Qwen 3.6 Max Preview's 40 — the nearest genuine step up — at $2.15 blended per million tokens versus $2.925. Reach for it when a task keeps hitting Qwen 3.6 Max Preview's ceiling.
Switch to GPT-5.6 Luna
GPT-5.6 Luna runs about 23% cheaper blended ($2.25 versus $2.925 per million tokens) while scoring 51.2 on the Intelligence Index. Switch down for high-volume work where Qwen 3.6 Max Preview's edge isn't earning its rate.
Switch to Grok 4.5
Grok 4.5 streams ~114 tokens/sec to Qwen 3.6 Max Preview's ~46 at a comparable blended cost ($3 per million tokens). Use it when iteration speed matters more than squeezing out the last point of quality.
Switch to Qwen 3.6 Plus
Qwen 3.6 Plus is the nearest Alibaba sibling — same house style, lower price point ($1.125 versus $2.925 blended per million tokens). The natural swap when you want to stay in the family.
What you pay for Qwen 3.6 Max Preview
Qwen 3.6 Max Preview is billed per token at the rates below — the same billing tables the Usage page charges against, so this page cannot quote a different price than you pay.
Blended cost (3:1 input:output, the shape of a typical coding session) works out to $2.925 per million tokens.
| Per 1M tokens | Input | Output | Cache read |
|---|---|---|---|
| All requests | $1.30 | $7.80 | $0.26 |
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 $0.26 per million tokens versus $1.30 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
Qwen 3.6 Max Preview 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 |
Switching models with /model
In an interactive Command Code session, run /model to open the model selector. Pick Qwen 3.6 Max Preview 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 Qwen 3.6 Max PreviewAll 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 | 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 (this page) | 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
Qwen 3.6 Max Preview or GLM-5.1?
GLM-5.1 scores higher on the Intelligence Index (40.2 vs 40) at $2.15 blended per million tokens against Qwen 3.6 Max Preview's $2.925. Default to Qwen 3.6 Max Preview and switch up when a task keeps stalling.
Qwen 3.6 Max Preview or GPT-5.6 Luna?
GPT-5.6 Luna is about 23% cheaper blended ($2.25 vs $2.925 per million tokens), scoring 51.2 on the Intelligence Index. Use GPT-5.6 Luna for volume work and Qwen 3.6 Max Preview where its edge earns the difference.
How much does Qwen 3.6 Max Preview cost in Command Code?
$1.30 per million input tokens and $7.80 per million output tokens, with cache reads at $0.26. In an agent loop, cached context brings effective input to roughly $0.572 per million tokens.
What plan do I need for Qwen 3.6 Max Preview?
Qwen 3.6 Max Preview is available on every plan, including Go at $1/mo.
Does Qwen 3.6 Max Preview support image input and reasoning?
Qwen 3.6 Max Preview 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 Qwen 3.6 Max Preview 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.
Qwen 3.6 Max Preview or Qwen 3.7 Max?
3.7 Max is the current frontier Qwen — newer, with a 1M context and cheaper output. 3.6 Max Preview is the prior preview build, kept for teams that already validated it.
What does "Preview" mean here?
It is a preview build of the 3.6 Max model. It is fully routable in Command Code; the production successor is Qwen 3.7 Max.
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
- Qwen 3.6 Plus in Command Codeagentic coding & reasoning
- Qwen 3.7 Plus in Command Codeagentic coding & reasoning at lower cost
- Qwen 3.7 Max in Command Codefrontier coding & long-horizon agent execution
- GPT-5.4 Mini in Command Codefast, cost-effective model for everyday tasks
- 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.