API PRICES
Qwen · Qwen3.5-397B-A17B
Provider prices, cheapest first
Price comparison
- Official (cash)
- Input 1.2 / output 7.2 CNY/million tokens阿里云百炼 ·
- Lowest inference provider (cash)
- Input 0.45 / output 3 USD/million tokensDeepInfra ·
- Lowest relay (credit)
- 0.429 USD credit/million total tokensapi.ifopen.ai "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.
All official and inference price observations
Qwen · Qwen3.5-397B-A17B official price: input 1.2, output 7.2 CNY per million tokens (阿里云百炼, observed 2026-10-24). Cheapest inference provider: DeepInfra, input 0.45, output 3 USD per million tokens. Cheapest relay: api.ifopen.ai, group "General LLMs [machine translation] (on site: 通用大模型)" 0.429 USD_CREDIT per million total tokens (credit price, not cash, observed 2026-10-23). 22 sites have comparable prices; 56 sites list this model.Relay blended price uses 75% input and 25% output. Conditions: Context tier: PROMPT_LE_128K · Processing mode: 非思考模式 · section: Qwen3.5 · region: 华北2（北京） · output mode: 非思考模式
Price ranges per million tokens
Official cash prices · Lowest 2.7 · median 4.725 · highest 6.75 · 4 quotes CNY / per million tokens
Inference provider cash prices · Lowest 1.0875 · median 1.3125 · highest 1.35 · 4 quotes USD / per million tokens
Relay USD credit prices · Lowest 0.429 · median 3.0225 · highest 17.55 · 6 quotes USD / per million tokens, site credit
Official price
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|
| 阿里云百炼 | Standard | 1.2 | 7.2 | — | — | CNY / 1M tokens | Context tier: PROMPT_LE_128K · Processing mode: 非思考模式 · section: Qwen3.5 · region: 华北2（北京） · output mode: 非思考模式Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_LE_128K",
"processingMode": "非思考模式",
"conditionNotes": [
"section: Qwen3.5",
"region: 华北2（北京）",
"output mode: 非思考模式"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| 阿里云百炼 | Standard | 1.2 | 7.2 | — | — | CNY / 1M tokens | Context tier: PROMPT_LE_128K · Processing mode: 思考模式（思维链+回答） · section: Qwen3.5 · region: 华北2（北京） · output mode: 思考模式（思维链+回答）Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_LE_128K",
"processingMode": "思考模式（思维链+回答）",
"conditionNotes": [
"section: Qwen3.5",
"region: 华北2（北京）",
"output mode: 思考模式（思维链+回答）"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| 阿里云百炼 | Standard | 3 | 18 | — | — | CNY / 1M tokens | Context tier: PROMPT_GT_128K_LE_256K · Processing mode: 非思考模式 · section: Qwen3.5 · region: 华北2（北京） · output mode: 非思考模式Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_GT_128K_LE_256K",
"processingMode": "非思考模式",
"conditionNotes": [
"section: Qwen3.5",
"region: 华北2（北京）",
"output mode: 非思考模式"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| 阿里云百炼 | Standard | 3 | 18 | — | — | CNY / 1M tokens | Context tier: PROMPT_GT_128K_LE_256K · Processing mode: 思考模式（思维链+回答） · section: Qwen3.5 · region: 华北2（北京） · output mode: 思考模式（思维链+回答）Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_GT_128K_LE_256K",
"processingMode": "思考模式（思维链+回答）",
"conditionNotes": [
"section: Qwen3.5",
"region: 华北2（北京）",
"output mode: 思考模式（思维链+回答）"
],
"effectiveFrom": null,
"effectiveUntil": null
}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 | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source | vs official |
|---|---|---|---|---|---|---|---|---|---|
| DeepInfra | Standard | 0.45 | 3 | 0.22 | — | USD / 1M tokens | Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| OpenRouter · Aggregator | Standard | 0.5 | 3.6 | 0.3 | — | USD / 1M tokens | Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.0000003",
"input": "0.0000005",
"output": "0.0000036"
},
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Novita AI | Standard | 0.6 | 3.6 | — | — | USD / 1M tokens | Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | ||
| Together AI | Standard | 0.6 | 3.6 | 0.35 | — | USD / 1M tokens | Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Older official and inference provider prices
Earlier price observations and their original conditions
Official price
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|
| 阿里云百炼 | Standard | 1.2 | 7.2 | — | — | CNY / 1M tokens | Context tier: PROMPT_LE_128K · Processing mode: 非思考模式 · section: Qwen3.5 · region: 华北2（北京） · output mode: 非思考模式Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_LE_128K",
"processingMode": "非思考模式",
"conditionNotes": [
"section: Qwen3.5",
"region: 华北2（北京）",
"output mode: 非思考模式"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| 阿里云百炼 | Standard | 1.2 | 7.2 | — | — | CNY / 1M tokens | Context tier: PROMPT_LE_128K · Processing mode: 思考模式（思维链+回答） · section: Qwen3.5 · region: 华北2（北京） · output mode: 思考模式（思维链+回答）Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_LE_128K",
"processingMode": "思考模式（思维链+回答）",
"conditionNotes": [
"section: Qwen3.5",
"region: 华北2（北京）",
"output mode: 思考模式（思维链+回答）"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| 阿里云百炼 | Standard | 3 | 18 | — | — | CNY / 1M tokens | Context tier: PROMPT_GT_128K_LE_256K · Processing mode: 非思考模式 · section: Qwen3.5 · region: 华北2（北京） · output mode: 非思考模式Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_GT_128K_LE_256K",
"processingMode": "非思考模式",
"conditionNotes": [
"section: Qwen3.5",
"region: 华北2（北京）",
"output mode: 非思考模式"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| 阿里云百炼 | Standard | 3 | 18 | — | — | CNY / 1M tokens | Context tier: PROMPT_GT_128K_LE_256K · Processing mode: 思考模式（思维链+回答） · section: Qwen3.5 · region: 华北2（北京） · output mode: 思考模式（思维链+回答）Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": "PROMPT_GT_128K_LE_256K",
"processingMode": "思考模式（思维链+回答）",
"conditionNotes": [
"section: Qwen3.5",
"region: 华北2（北京）",
"output mode: 思考模式（思维链+回答）"
],
"effectiveFrom": null,
"effectiveUntil": null
}Official source |
Inference providers
| Provider | Tariff | Input | Output | Cache read | Cache write | Unit | Observed | Conditions and source |
|---|---|---|---|---|---|---|---|---|
| Together AI | Standard | 0.6 | 3.6 | 0.35 | — | USD / 1M tokens | Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| OpenRouter · Aggregator | Standard | 0.5 | 3.6 | 0.3 | — | USD / 1M tokens | Full price conditions{
"sourceUnit": "USD_PER_TOKEN",
"sourceAmounts": {
"cacheRead": "0.0000003",
"input": "0.0000005",
"output": "0.0000036"
},
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| Novita AI | Standard | 0.6 | 3.6 | — | — | USD / 1M tokens | Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}Official source | |
| DeepInfra | Standard | 0.45 | 3 | 0.22 | — | USD / 1M tokens | Full price conditions{
"sourceUnit": null,
"sourceAmounts": null,
"conditions": [],
"contextTier": null,
"processingMode": null,
"conditionNotes": [],
"effectiveFrom": null,
"effectiveUntil": null
}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 0.429 · median 3.0225 · highest 17.55 (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 | api.ifopen.aiAsk or discussCollected: Collected this cycle View 6 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 Name on site: Qwen/Qwen3.5-397B-A17B ⭐ 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 | 0.312 | 0.78 | — | 0.429Median price ÷ this price: 7× | Full prices and sources |
| 02 | api.ifopen.aiAsk or discussCollected: Collected this cycle View 6 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 Name on site: qwen3.5-397b-a17b ⭐ 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 | 0.78 | 4.68 | — | 1.755Median price ÷ this price: 1.7× | Full prices and sources |
| 03 | api.ifopen.aiAsk or discussCollected: Collected this cycle View 6 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. | default Name on site: Qwen/Qwen3.5-397B-A17B ⭐ Recommended | all-model automatic load optimization [machine translation]Original: ⭐ 推荐 | 全模型自动负载优化 Operator pending verification | 1.2 | 3 | — | 1.65Median price ÷ this price: 1.8× | Full prices and sources |
| 04 | api.ifopen.aiAsk or discussCollected: Collected this cycle View 6 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. | default Name on site: qwen3.5-397b-a17b ⭐ Recommended | all-model automatic load optimization [machine translation]Original: ⭐ 推荐 | 全模型自动负载优化 Operator pending verification | 3 | 18 | — | 6.75Median price ÷ this price: 0.4× | Full prices and sources |
| 05 | api.ifopen.aiAsk or discussCollected: Collected this cycle View 6 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. | All-model dedicated line channel [machine translation]Group on site: 全模型专线渠道 Name on site: Qwen/Qwen3.5-397B-A17B 👍 Highest concurrency guaranteed on all models | stable 24 hours [machine translation]Original: 👍 全模型最高并发保证 | 24小时稳定 Operator pending verification | 3.12 | 7.8 | — | 4.29Median price ÷ this price: 0.7× | Full prices and sources |
| 06 | api.ifopen.aiAsk or discussCollected: Collected this cycle View 6 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. | All-model dedicated line channel [machine translation]Group on site: 全模型专线渠道 Name on site: qwen3.5-397b-a17b 👍 Highest concurrency guaranteed on all models | stable 24 hours [machine translation]Original: 👍 全模型最高并发保证 | 24小时稳定 Operator pending verification | 7.8 | 46.8 | — | 17.55Median price ÷ this price: 0.2× | 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.
- Free declaration, listed separately: 1 rows
- zero-ratio group: 1 rows
- ai.38yun.cn · Professional free model channel [machine translation]Group on site: 专业免费模型通道 · qwen/qwen3.5-397b-a17b · Input 0 / Output 0 USD credits / 1M
How this ranking works
All per-token prices: 93,968 prices from 854 sites (about 751 companies). 84,786 are ranked, from 838 sites (about 736 companies); 9,182 more are listed separately and not ranked. Prices collected up to 2026-10-24.
This model has 121 recorded prices; 51 can be compared directly (50 ranked, 1 listed separately). Not comparable yet: price not parsed yet 37, ratio looks unset 16, display unit not confirmed 8, tiered by rules (see Tiered prices) 6, billed per request or another unit 1
6 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 · Qwen3.5-397B-A17B?
api.ifopen.ai, group "通用大模型 (General LLMs)", 0.429 USD credit per million total tokens, observed 2026-10-23. 22 sites have comparable prices.
What is the official price for Qwen · Qwen3.5-397B-A17B?
Input 1.2, output 7.2 CNY per million tokens, checked 2026-10-24. Lowest inference provider: DeepInfra, input 0.45, output 3 USD per million tokens.
How do I use Qwen · Qwen3.5-397B-A17B in Claude Code or Codex?
Install Grandet Skill, then say "Connect the cheapest Qwen · Qwen3.5-397B-A17B API to Claude Code for me". Install Skill →