Global AI Token Comparison Hub
CN
Back to all plans

讯飞星辰

Multi-model access

Astron Coding Plan multi-model coding subscription—Worry-free unlimited requests, billed by call count

Coding PlanAstron Coding Plan
SubscriptionToken API
Official

Core models

Spark X2Spark-X2-FlashGLM-5.1GLM-5DeepSeek-V4-ProDeepSeek-V4-FlashDeepSeek-V3.2Kimi-K2.6Kimi-K2.5MiniMax-M2.5Qwen3.5-397B-A17BQwen3.6-35B-A3BQwen3.5-35B-A3BQwen3-Coder-Next-FP8GLM-4.7-Flash
Spark X2

xsparkx2—iFlytek deep-reasoning flagship for math and agents; available on High-efficiency tier.

Spark-X2-Flash

xsparkx2flash—value Spark line with stronger agent and coding skills.

GLM-5.1

xopglm51—newer Zhipu GLM for long-horizon engineering; High-efficiency tier.

GLM-5

xopglm5—Zhipu flagship for code and reasoning; Pro/High-efficiency tiers.

DeepSeek-V4-Pro

xopdeepseekv4pro—DeepSeek Pro flagship for complex agents.

See the official site for more models

Additional core model names still appear above, with full details on the latest official page.

Open official site

Plan details

无忧版

Unlimited
Price
¥19/mo
Unlimited requests
Monthly
¥19/mo
Auto quarterly
¥16.6/mo
12% off quarterly
Official
Usage
Worry-free’s hallmark is unlimited request count for batch light tasks, learning, and small edits—but only light modelIds like Qwen3.5-35B-A3B, Qwen3-Coder-Next-FP8, GLM-4.7-Flash—not unlimited heavy agents.
Models
Each question deducts actual model calls (simple ~3–10, complex 10–30+)—track usage on the MaaS subscription page.
Highlights
Suited to AI coding as support, not a primary workbench—upgrade to Pro or High-efficiency for long complex chains.
Same-tier stacking allowed—each purchase gets its own API key and quota; 31-day validity.
Best for
Students, indie developers, and lightweight batch-task users

专业版

Best valueRecommended
Price
¥39/mo
~1,200/5h · 9,000/wk · 18,000/mo
Monthly
¥39/mo
Auto quarterly
¥37/mo
5% off quarterly
Official
Usage
Pro at ¥39/mo: ~1,200/5h, 9,000/wk, 18,000/subscription-month request caps—for medium-frequency primary coding.
Models
Switch GLM-5, Kimi-K2.5, MiniMax-M2.5, DeepSeek-V3.2 plus light Qwen/GLM modelIds—more real coding models than Worry-free.
Highlights
Quotas start at payment: 5-hour window refreshes hourly, weekly resets 08:00 UTC+8, monthly spans 31 days.
Upgrade from Worry-free with prorated difference—no downgrade; peak throttling possible.
Best for
Medium-to-high-frequency developers using AI coding as a daily tool

高效版

Heavy
Price
¥199/mo
~6,000/5h · 45,000/wk · 90,000/mo
Monthly
¥199/mo
Auto quarterly
¥179.3/mo
10% off quarterly
Official
Usage
High-efficiency at ¥199/mo is ~5× Pro: 6,000/5h, 45,000/wk, 90,000/subscription-month—for heavy multi-project and long agent chains.
Models
Adds GLM-5.1, Spark X2, Kimi-K2.6, DeepSeek-V4, and more atop Pro’s pool—for higher engineering and output demands.
Highlights
If AI coding is a formal productivity system—not occasional support—this tier’s advantage over Pro becomes meaningful.
Same 31-day validity—upgrade from lower tiers supported; no downgrade or refund.
Best for
Heavy developers, high-frequency enterprise users, and multi-project teams

Quota

Product type
Coding Plan
Official product line
Astron Coding Plan
5-hour limit
Unlimited (Worry-free) / 1,200–6,000 calls/5h
Weekly limit
Unlimited (Worry-free) / 9,000–45,000 calls/wk
Monthly limit
Unlimited (Worry-free) / 18,000–90,000 calls/mo

Notes

  • Worry-free first buy ¥3.9/mo, repeat ¥19/mo; Pro ¥39/mo; High-efficiency ¥199/mo. Valid 31 days (not calendar month)—stacking and upgrades supported, no downgrade/refund.
  • Worry-free focuses on Qwen3.5-35B-A3B, Qwen3-Coder-Next-FP8, GLM-4.7-Flash; Pro adds GLM-5/Kimi/MiniMax/DeepSeek-V3.2; High-efficiency adds GLM-5.1/Spark X2—confirm modelIds on MaaS subscription page.
  • From 2026-06-18 off-peak coefficient: weekdays 08:00–22:00 at 1.0; nights/weekends/holidays at 0.8—off-peak use stretches caps (e.g. 6,000/5h ≈ 7,500 effective).
  • Use astron-code-latest (console model switch in 1–3 min) or any of 15 documented modelIds for live switching in tools.

Supported coding tools

Claude CodeCursorOpenCodeOpenClawCodex CLITRAE

Pricing and model data sourced from official vendor websites

FAQ

General·9
General
9 条