API PRICES
Qwen · Qwen3.5-35B-A3B
Provider prices, cheapest first
Price comparison
- Official (cash)
- Input 0.4 / output 3.2 CNY/million tokens阿里云百炼 ·
- Lowest inference provider (cash)
- Input 0.14 / output 1 USD/million tokensDeepInfra ·
- Lowest relay (credit)
- 0.182 USD credit/million total tokensapi2.aigcbest.top "通用大模型" ·
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 · Qwen3.5-35B-A3B official price: input 0.4, output 3.2 CNY per million tokens (阿里云百炼, observed 2026-10-17). Cheapest inference provider: DeepInfra, input 0.14, output 1 USD per million tokens. Cheapest relay: api2.aigcbest.top, group "General LLMs [machine translation] (on site: 通用大模型)" 0.182 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-16). 14 sites have comparable prices; 43 sites list this model.Relay blended price uses 75% input and 25% output.
Price ranges per million tokens
Official cash prices · Lowest 1.1 · median 2.75 · highest 4.4 · 4 quotes CNY / per million tokens
Inference provider cash prices · Lowest 0.355 · median 0.3625 · highest 0.6875 · 3 quotes USD / per million tokens
Inference provider cash prices · Lowest 4.4 · median 4.4 · highest 4.4 · 1 quotes CNY / per million tokens
Relay USD credit prices · Lowest 0.182 · median 0.4235 · highest 1.1 · 6 quotes USD / per million tokens, site credit
Relay CNY credit prices · Lowest 0.66 · median 2.5915 · highest 4.4 · 5 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 | 0.4 | 3.2 | — | — | CNY / 1M tokens | Official source | |
| 阿里云百炼 | 0.4 | 3.2 | — | — | CNY / 1M tokens | Official source | |
| 阿里云百炼 | 1.6 | 12.8 | — | — | CNY / 1M tokens | Official source | |
| 阿里云百炼 | 1.6 | 12.8 | — | — | 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 | 0.14 | 1 | 0.05 | — | USD / 1M tokens | Official source | ||
| OpenRouter · Aggregator | 0.15 | 1 | 0.05 | — | USD / 1M tokens | Official source | ||
| Novita AI | 0.25 | 2 | — | — | USD / 1M tokens | Official source | ||
| SiliconFlow | 1.6 | 12.8 | — | — | CNY / 1M tokens | Official source |
Unit: USD credits per 1M tokens. These are site-credit prices; actual cost depends on each site’s top-up rate.
Price range: lowest 0.182 · median 0.4235 · highest 1.1 (6 quotes, USD credits per million total tokens)
Relays
Prices below are in site credit, not cash.
| # | Provider | Plan / conditions | Input ↑USD credits / 1M | Output USD credits / 1M | Cache readUSD credits / 1M | BlendedUSD credits / 1M | Details |
|---|---|---|---|---|---|---|---|
| Recent price | |||||||
| 01 | kelaiapi.ccAsk or discussCollected: Collected this cycle View 1 plans | vip_ch Name on site: qwen3.5-35b-a3b Chinese mixed models [machine translation]Original: 国产混合模型 Operator pending verification | 0.1 | 0.8 | — | 0.275Median price ÷ this price: 1.5× | Full prices and sources |
| 02 | aigcbest.topAsk or discussCollected: Collected this cycle View 6 plans 2 more sites of the same companyBasis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding. | General LLMs [machine translation]Group on site: 通用大模型 Name on site: Qwen/Qwen3.5-35B-A3B ⭐ Special price | can only call some Chinese models and open-source models [machine translation]Original: ⭐ 特价 | 仅可调用部分国模和开源模型 Operator pending verification | 0.104 | 0.416 | — | 0.182Median price ÷ this price: 2.3× | Full prices and sources |
| 03 | llm.kagu.oneAsk or discussCollected: Collected this cycle View 2 plans | Hodgepodge [machine translation]Group on site: 大杂烩 Name on site: qwen/qwen3.5-35b-a3b Operator pending verification | 0.125 | 0.5 | — | 0.21875Median price ÷ this price: 1.9× | Full prices and sources |
| 04 | hohoapi.comAsk or discussCollected: Collected this cycle View 1 plans | qwen Name on site: qwen3.5-35b-a3b 站点写明为限时价格 Tongyi Qwen official channel (limited-time special) [machine translation]Original: 通义千问官方渠道（限时特惠） Operator pending verification | 0.208 | 1.664 | — | 0.572Median price ÷ this price: 0.7× | Full prices and sources |
| 05 | chatfire.cnAsk or discussCollected: Collected this cycle View 1 plans | alibailian Name on site: qwen3.5-35b-a3b -40% & enterprise high availability 🔥 Alibaba Cloud Bailian all models [machine translation]Original: -40%&企业高可用🔥阿里云百炼全模型 Operator pending verification | 0.36 | 1.8 | — | 0.72Median price ÷ this price: 0.6× | Full prices and sources |
| 06 | xinsuanai.comAsk or discussCollected: Collected this cycle View 4 plans | default Name on site: qwen3.5-35b-a3b Default group [machine translation]Original: 默认分组 Operator pending verification | 0.4 | 3.2 | — | 1.1Median price ÷ this price: 0.4× | Full prices and sources |
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 96 recorded prices; 34 can be compared directly. Not comparable yet: price not parsed yet 31, ratio looks unset 20, display unit not confirmed 6, tiered by rules (see Tiered prices) 3, billed per request or another unit 2
27 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 · Qwen3.5-35B-A3B?
api2.aigcbest.top, group "通用大模型 (General LLMs)", 0.182 USD credit per million total tokens, observed 2026-10-16. 14 sites have comparable prices.
What is the official price for Qwen · Qwen3.5-35B-A3B?
Input 0.4, output 3.2 CNY per million tokens, checked 2026-10-17. Lowest inference provider: DeepInfra, input 0.14, output 1 USD per million tokens.
How do I use Qwen · Qwen3.5-35B-A3B in Claude Code or Codex?
Install Grandet Skill, then say "Connect the cheapest Qwen · Qwen3.5-35B-A3B API to Claude Code for me". Install Skill →