API PRICES

Qwen · qwen3.7-max

Provider prices, cheapest first

Browse all models

Price comparison

Official (cash)
Input 12 / output 36 CNY/million tokens阿里云百炼 ·
Lowest inference provider (cash)
Input 1.475 / output 4.425 USD/million tokensOpenRouter · Aggregator ·
Lowest relay (credit)
0.775 USD credit/million total tokensopenai.chatnewai.com "国产模型整合分组(回归) ¥0.48/刀" ·

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 · qwen3.7-max official price: input 12, output 36 CNY per million tokens (阿里云百炼, observed 2026-10-17). Cheapest inference provider: OpenRouter, input 1.475, output 4.425 USD per million tokens. Cheapest relay: openai.chatnewai.com, group "Chinese models combined group (returned) ¥0.48/dao [machine translation] (on site: 国产模型整合分组(回归) ¥0.48/刀)" 0.775 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-16). 125 sites have comparable prices; 222 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 2.2125 · median 2.2313 · highest 2.25 · 2 quotes USD / per million tokens

Relay USD credit prices · Lowest 0.775 · median 3.9758 · highest 60 · 52 quotes USD / per million tokens, site credit

Relay CNY credit prices · Lowest 1.25 · median 10.8 · highest 23.4 · 33 quotes CNY / per million tokens, site credit

Official price

ProviderInputOutputCache readCache writeUnitObservedConditions and source
阿里云百炼1236——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

ProviderInputOutputCache readCache writeUnitObservedConditions and sourcevs official
OpenRouter · Aggregator1.4754.4250.2951.8438USD / 1M tokens
Official source
Together AI1.54.50.3—USD / 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.

Searching…

Browse all providers

Blended price = input × 75% + output × 25%, without cache.

Price range: lowest 0.775 · median 3.9758 · highest 60 (52 quotes, USD credits per million total tokens)

sites have comparable prices125222 sites list this model; approximately 59 operators
Lowest input price0.2USD credits / 1M
Median of each provider’s lowest price2.6505USD credits / 1M

Relays

Prices below are in site credit, not cash.

#ProviderPlan / conditionsInput ↑USD credits / 1MOutput USD credits / 1MCache readUSD credits / 1MBlendedUSD credits / 1MDetails
Recent price
26aiapi.worldAsk or discussCollected:
Collected this cycle
View 1 plans
cmodels
cmodels
Operator pending verification
2.6017.803—3.9015Median price ÷ this price: 1×Full prices and sources
27api.xkj666.topAsk or discussCollected:
Collected this cycle
View 1 plans
Chinese models group [machine translation]Group on site: 国模分组
Covers all official Chinese models [machine translation]Original: 涵盖所有官方国产模型
Operator pending verification
2.78.10.544.05Median price ÷ this price: 1×Full prices and sources
28openoneapi.comAsk or discussCollected:
Collected this cycle
View 1 plans
Chinese models [machine translation]Group on site: 国模 Operator pending verification390.1254.5Median price ÷ this price: 0.9×Full prices and sources
29aigcbest.topAsk or discussCollected:
Collected this cycle
View 3 plans
2 more sites of the same company

Basis: 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
⭐ 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
3.129.360.6244.68Median price ÷ this price: 0.8×Full prices and sources
29hohoapi.comAsk or discussCollected:
Collected this cycle
View 1 plans
qwen

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
3.129.36—4.68Median price ÷ this price: 0.8×Full prices and sources
31oojj.topAsk or discussCollected:
Collected this cycle
View 3 plans
cnmodeapi029
Chinese models official KEY aggregated 0.29 [machine translation]Original: 国模官KEY聚合0.29
Operator pending verification
3.4810.440.4355.22Median price ÷ this price: 0.8×Full prices and sources
32shanyiapi.comAsk or discussCollected:
Collected this cycle
View 1 plans
vip_ch
Chinese mixed models [machine translation]Original: 国产混合模型
Operator pending verification
4.212.60.426.3Median price ÷ this price: 0.6×Full prices and sources
32tian-shu.netAsk or discussCollected:
Collected this cycle
View 1 plans
1 more site of the same company

Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.

qwen
{"zh-CN": "Tongyi Qianwen 3.7 · Alibaba(max / plus)", "zh-TW": "Tongyi Qianwen 3.7 · Alibaba(max / plus)", "en": "Qwen 3.7 (max / plus)", "fr": "Qwen 3.7 (max / plus)", "ja": "Qwen 3.7 (max / plus)", "ru": "Qwen 3.7 (max / plus)", "vi": "Qwen 3.7 (max / plus)", "es": "Q [machine translation]Original: {"zh-CN": "通义千问 3.7 · 阿里(max / plus)", "zh-TW": "通义千问 3.7 · 阿里(max / plus)", "en": "Qwen 3.7 (max / plus)", "fr": "Qwen 3.7 (max / plus)", "ja": "Qwen 3.7 (max / plus)", "ru": "Qwen 3.7 (max / plus)", "vi": "Qwen 3.7 (max / plus)", "es": "Q
Operator pending verification
4.212.60.426.3Median price ÷ this price: 0.6×Full prices and sources
34ai.sandboxai.topAsk or discussCollected:
Collected this cycle
View 1 plans
GLM 5.1
GLM 5.1
Operator pending verification
4.814.40.487.2Median price ÷ this price: 0.6×Full prices and sources
34aimoniker.topAsk or discussCollected:
Collected this cycle
View 1 plans
Chinese models - oai [machine translation]Group on site: 国产模型-oai
Includes the latest Chinese models: k3, glm-5.3 /flash, deepseek v4, etc.; supports OpenAI protocol; using cc requires enabling routing [machine translation]Original: 包含最新的国产模型,k3、glm-5.3 /flash、 deepseek v4等,支持OpenAI协议,使用cc需要开路由
Operator pending verification
4.814.40.967.2Median price ÷ this price: 0.6×Full prices and sources
34api.mooko.aiAsk or discussCollected:
Collected this cycle
View 1 plans
Chinese models-good · economical [machine translation]Group on site: 国产模型-优·省
Low-price Chinese models [machine translation]Original: 低价国产模型
Operator pending verification
4.814.4—7.2Median price ÷ this price: 0.6×Full prices and sources
34chatfire.cnAsk or discussCollected:
Collected this cycle
View 5 plans
lite
-60% lightweight or older-version models [machine translation]Original: -60% 轻量级or旧版本模型
Operator pending verification
4.814.40.087.2Median price ÷ this price: 0.6×Full prices and sources
34zen-ai.topAsk or discussCollected:
Collected this cycle
View 2 plans
Open source [machine translation]Group on site: 开源
Major Chinese open-source models, 40% of official price, 0.4 yuan per 1 dao (US dollar) [machine translation]Original: 国内主流开源模型, 官方4折, 0.4元1刀
Operator pending verification
4.814.40.487.2Median price ÷ this price: 0.6×Full prices and sources
34zl.wonderful.edu.kgAsk or discussCollected:
Collected this cycle
View 1 plans
[High rate multiplier] Chinese model collection [machine translation]Group on site: 【高倍率】国模集合分组
[Chinese models] supports more Chinese models [machine translation]Original: 【国模】支持更多国模
Operator pending verification
4.814.40.67.2Median price ÷ this price: 0.6×Full prices and sources
40tokenflux.cloudAsk or discussCollected:
Collected this cycle
View 1 plans
default
Default group [machine translation]Original: 默认分组
Operator pending verification
5150.57.5Median price ÷ this price: 0.5×Full prices and sources
41liangxinapi.topAsk or discussCollected:
Collected this cycle
View 2 plans
Low-price Chinese models [machine translation]Group on site: 低价国模
Low-price Chinese models, cache drops at peak hours [machine translation]Original: 低价国模渠道,高峰期掉缓存
Operator pending verification
5.2515.751.057.875Median price ÷ this price: 0.5×Full prices and sources
42api.aabao.topAsk or discussCollected:
Collected this cycle
View 3 plans
1 more site of the same company

Basis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.

DeepSeek-2
Self-deployed channel (0.5x rate multiplier) [machine translation]Original: 自部署渠道(0.5倍率)
Operator pending verification
617.51.28.875Median price ÷ this price: 0.4×Full prices and sources
439527.codesAsk or discussCollected:
Collected this cycle
View 1 plans
4 more sites of the same company

Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.

🇨🇳Chinese official models [machine translation]Group on site: 🇨🇳国产官方模型
Chinese models-official full-strength-Volcano official agent channel [machine translation]Original: 国产模型-官方满血-火山官方代理渠道
Operator pending verification
7.221.60.1210.8Median price ÷ this price: 0.4×Full prices and sources
44gptapi.asiaAsk or discussCollected:
Collected this cycle
View 1 plans
2 more sites of the same company

Basis: identical homepage assets, identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.

default
Default channel [machine translation]Original: 默认通道
Operator pending verification
9.628.8—14.4Median price ÷ this price: 0.3×Full prices and sources
45poloai.topAsk or discussCollected:
Collected this cycle
View 2 plans
2 more sites of the same company

Basis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.

qwen-new
qwen newly launched models [machine translation]Original: qwen最新上线模型
Operator pending verification
10.832.41.0816.2Median price ÷ this price: 0.2×Full prices and sources
46www.nuwaflux.comAsk or discussCollected:
Collected this cycle
View 2 plans
Chinese models dedicated line [machine translation]Group on site: 国产模型专线
deepseek/glm/kimi/seedance2.0
Operator pending verification
12362.418Median price ÷ this price: 0.2×Full prices and sources
46xiaoma.bestAsk or discussCollected:
Collected this cycle
View 2 plans
default
Default channel - best value for money, most recommended, has claude series models, no gpt or gemini [machine translation]Original: 默认渠道 - 性价比最高最推荐,有claude系列模型,没有gpt和gemini
Operator pending verification
12362.418Median price ÷ this price: 0.2×Full prices and sources
48gpt-agent.ccAsk or discussCollected:
Collected this cycle
View 4 plans
1 more site of the same company

Basis: identical quotes, same status-page name, logo or server address. Counted as one company in the ranking; this is not a legal finding.

default
Default group [machine translation]Original: 默认分组
Operator pending verification
20602.530Median price ÷ this price: 0.1×Full prices and sources
49ai-one.vipAsk or discussCollected:
Collected this cycle
View 1 plans
1 more site of the same company

Basis: identical quotes. Counted as one company in the ranking; this is not a legal finding.

China
Chinese models mixed group [machine translation]Original: 国产模型混合分组
Operator pending verification
21.664.82.1632.4Median price ÷ this price: 0.1×Full prices and sources
49ai.ufoai.onlineAsk or discussCollected:
Collected this cycle
View 2 plans
Chinese models [Alibaba direct connection] [machine translation]Group on site: 国产模型[阿里直连]
90% of official price; deepseek, glm, minimax and kimi [machine translation]Original: 官方9折,deepseek、glm、minimax和kimi
Operator pending verification
21.664.82.1632.4Median price ÷ this price: 0.1×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.

  • test or debug group: 1 rows
View all 1 rows →
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 364 recorded prices; 194 can be compared directly (193 ranked, 1 listed separately). Not comparable yet: price not parsed yet 109, tiered by rules (see Tiered prices) 22, ratio looks unset 16, display unit not confirmed 14, billed per request or another unit 7

119 recent · 5 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.

Full methodology →

Switch model

Sources not accepted this cycle and reasons

FAQ

Which API is cheapest for Qwen · qwen3.7-max?

openai.chatnewai.com, group "国产模型整合分组(回归) ¥0.48/刀 (Chinese models combined group (returned) ¥0.48/dao)", 0.775 USD credit per million total tokens, observed 2026-10-16. 125 sites have comparable prices.

What is the official price for Qwen · qwen3.7-max?

Input 12, output 36 CNY per million tokens, checked 2026-10-17. Lowest inference provider: OpenRouter, input 1.475, output 4.425 USD per million tokens.

How do I use Qwen · qwen3.7-max in Claude Code or Codex?

Install Grandet Skill, then say "Connect the cheapest Qwen · qwen3.7-max API to Claude Code for me". Install Skill →