API PRICES
Qwen · qwen3.8-max
Provider prices, cheapest first
Price comparison
- Official (cash)
- Input 12 / output 36 CNY/million tokens阿里云百炼 ·
- Lowest inference provider (cash)
- Input 1.65 / output 4.951 USD/million tokensDeepInfra ·
- Lowest relay (credit)
- 0.75 CNY credit/million total tokensoai2api.com "china_modal" ·
Official and inference-provider prices are cash; relay prices are site credit (USD credit or CNY credit), a different unit, compared separately. Relay prices are per million total tokens at 75% input and 25% output.
Qwen · qwen3.8-max official price: input 12, output 36 CNY per million tokens (阿里云百炼, observed 2026-10-17). Cheapest inference provider: DeepInfra, input 1.65, output 4.951 USD per million tokens. Cheapest relay: oai2api.com, group "china_modal" 0.75 CNY_CREDIT per million total tokens (credit price, not cash, observed 2026-10-16). 160 sites have comparable prices; 289 sites list this model.Relay blended price uses 75% input and 25% output.
Price ranges per million tokens
Official cash prices · Lowest 18 · median 18 · highest 18 · 1 quotes CNY / per million tokens
Inference provider cash prices · Lowest 2.4753 · median 2.7376 · highest 3 · 2 quotes USD / per million tokens
Relay CNY credit prices · Lowest 0.75 · median 1.275 · highest 1.8 · 2 quotes CNY / per million tokens, site credit
Official price
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|
| 阿里云百炼 | 12 | 36 | — | — | CNY / 1M tokens | Official source |
Official prices are the vendor's cash prices. Inference providers also list cash prices and can be compared directly. Relays list prices in site credit; what you actually pay depends on each site's top-up rate, so they cannot be compared with official prices directly.
Inference providers
| Provider | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source | vs official |
|---|---|---|---|---|---|---|---|---|
| DeepInfra | 1.65 | 4.951 | 0.206 | — | USD / 1M tokens | Official source | ||
| Novita AI | 2 | 6 | 0.25 | — | USD / 1M tokens | Official source |
Unit: CNY credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.
Price range: lowest 0.75 · median 1.275 · highest 1.8 (2 quotes, CNY credits per million total tokens)
Relays
Prices below are in site credit, not cash.
| # | Provider | Plan / conditions | Input ↑CNY credits / 1M | Output CNY credits / 1M | Cache readCNY credits / 1M | BlendedCNY credits / 1M | Details |
|---|---|---|---|---|---|---|---|
| Recent price | |||||||
| 01 | oai2api.comAsk or discussCollected: Collected this cycle View 2 plans | china_modal Intelligence not discounted, more considerate cost, Chinese models at 0.03x rate multiplier of the domestic official price, some low cache! [machine translation]Original: 智力不打折，成本更贴心，国模国内官方价的0.03x倍率，部分低缓！ Operator pending verification | 0.5 | 1.5 | 0.0625 | 0.75Median price ÷ this price: 1.7× | Full prices and sources |
| 02 | oai2api.comAsk or discussCollected: Collected this cycle View 2 plans | china_modal_hight Stability-seeking group, Chinese models at a 0.09x rate multiplier of the domestic official price, high cache! [machine translation]Original: 求稳分组，国模国内官方价的0.09x倍率，高缓！ Operator pending verification | 1.2 | 3.6 | 0.15 | 1.8Median price ÷ this price: 0.7× | Full prices and sources |
Special groups · 1 rows · not ranked
These plans are marked as test, internal, disabled, gated by top-up or membership, or have a near-zero ratio. They may not be purchasable or stable, so they are listed separately and left out of the ranking and statistics.
- near-zero-ratio group: 1 rows
- ai.kdysite.cloud · Chinese models-perk [machine translation]Group on site: 国模-福利 · qwen3.8-max · Input 0.42 / Output 1.23 CNY credits / 1M
How this ranking works
All per-token prices: 97,455 prices from 871 sites (about 765 companies). 89,631 are ranked, from 861 sites (about 755 companies); 7,824 more are listed separately and not ranked. Prices collected up to 2026-10-17.
This model has 504 recorded prices; 260 can be compared directly (248 ranked, 12 listed separately). Not comparable yet: price not parsed yet 145, tiered by rules (see Tiered prices) 39, ratio looks unset 23, billed per request or another unit 18, display unit not confirmed 7, scope of the official doc price not confirmed 5
2 recent · 0 stale (older than 10 days, or not updated by this refresh) · 0 unverified timestamps. Minimum and median only count recent paid prices; older prices stay in the table. 0 zero-valued pairs are separately unverified, without proof of free eligibility. Timing does not verify payment, upstream identity or quality.
Prices are converted to site credits using each site’s published ratio. What you actually pay depends on its top-up rate. Input, output and cache prices in each row come from the same plan. Several sites run by the same company take one place in the ranking: its cheapest plan, with the other sites listed under it. We judge “same company” by identical prices, status pages or homepage code; this is not a legal finding. To see every site’s prices, choose “All plans” or filter by provider.
“Self-declared unofficial channel” means the plan name itself says “reverse-engineered” or similar. We have not verified their source or quality. Minimum and median only count regular plans.
Sources not accepted this cycle and reasons
FAQ
Which API is cheapest for Qwen · qwen3.8-max?
oai2api.com, group "china_modal", 0.75 CNY credit per million total tokens, observed 2026-10-16. 160 sites have comparable prices.
What is the official price for Qwen · qwen3.8-max?
Input 12, output 36 CNY per million tokens, checked 2026-10-17. Lowest inference provider: DeepInfra, input 1.65, output 4.951 USD per million tokens.
How do I use Qwen · qwen3.8-max in Claude Code or Codex?
Install Grandet Skill, then say "Connect the cheapest Qwen · qwen3.8-max API to Claude Code for me". Install Skill →