Qwen3.5 397B A17B API pricing
Alibaba · Mid-range price tier · Apache 2.0 · released 2026-03. Prices in USD per 1 million tokens. Data snapshot: 2026-11-12.
A support ticket workload of 100K requests a month costs $270.00 on Qwen3.5 397B A17B; the next cheaper model in the Mid-range price tier for this workload, Kimi K2.6, does it for $268.00. The price we quote for Qwen3.5 397B A17B has changed 11 times since 2026-08-15, most recently on 2026-11-09 when the quoted host changed (+1.1%); it is now the 42nd cheapest of 113 models in the Mid-range price tier. Buying from Alibaba rather than at the price we quote lowers the token price by about 35%. It is rated a stable release but does not meet all four criteria of the FinOps Friendly badge.
- Input: $0.60 per 1M tokens
- Output: $3.60 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: $0.12 per 1M tokens
- Context window: 262K tokens
- Arena ELO: 1438 as of 2026-11-08
Market position
On blended price ($2.70 per 1M tokens at 30% input, 70% output) it is cheaper than 63% of models in the Mid-range price tier: 42nd cheapest of 113. Across every price tier it is cheaper than 33% of priced text models in the catalogue: 202nd cheapest of 303. Its Arena ELO of 1438 ranks 57th of the 160 models that carry one, tied with one other, above 64% of them. With an Arena score of 1438, Qwen3.5 397B A17B clears OptimNow's Standard working quality threshold: Standard (Arena 1420+), used for meeting summary, invoice processing and call summary. Each threshold is a distance below the best ranked model, which scores 1530 on Arena scores as of 8 Nov 2026.
Licence, size and capabilities
Qwen3.5 397B A17B is open source: its weights are published under Apache 2.0, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token. Its published size is 397B parameters. Listed capabilities: Text, Vision, Reasoning, Agents. Filling its 262K context window once costs $0.1572 in input tokens at list price.
Pricing by host
A host is a company that runs the model and sells it by the token: the model maker, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent host. One model, several hosts, and often several prices. This model is sold by 8 different hosts. The price we quote elsewhere on this page is marked. We quote one host's rate so that models stay comparable; it is not a recommendation to buy there.
Cheapest host: Alibaba at $0.39 input / $2.34 output per 1M tokens, 35% below the price we quote on the blended price (30% input, 70% output). A support ticket workload at 100K requests a month costs $175.50 there against $270.00 at the price we quote, a difference of $94.50 a month. The dearest, Venice, charges 1.9x the cheapest.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| Alibaba (model maker) | $0.39 | $2.34 | not declared |
| DeepInfra | $0.45 | $3.00 | fp8 |
| AtlasCloud | $0.55 | $3.50 | fp8 |
| Parasail | $0.50 | $3.60 | fp8 |
| StreamLake (price we quote) | $0.60 | $3.60 | not declared |
| GMICloud (price we quote) | $0.60 | $3.60 | fp8 |
| Novita (price we quote) | $0.60 | $3.60 | not declared |
| Venice | $0.75 | $4.50 | not declared |
List prices as published on 2026-11-12, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown.
Monthly cost at 100K requests, by business use case
From the after-discounts figure (prompt caching on the cached input share, batch API for async workloads, only where Alibaba publishes those rates), which assumes you implement both, to the list price. One figure means no discount is published.
| Use case | Tokens (in/out) | Monthly (after discounts – list) |
|---|---|---|
| Support Ticket | 1,500 / 500 | $227 – $270 |
| Knowledge Q&A | 2,000 / 800 | $341 – $408 |
| Meeting Summary | 10,000 / 1,200 | $984 – $1.0K |
| Marketing Content | 2,500 / 1,800 | $774 – $798 |
| Coding Task | 3,000 / 2,000 | $828 – $900 |
| Invoice Processing | 1,500 / 600 | $284 – $306 |
| Call Summary | 2,000 / 700 | $362 – $372 |
| Agent Workflow | 6,000 / 3,000 | $1.2K – $1.4K |
Price history
Qwen3.5 397B A17B has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.39 input / $2.34 output per 1M tokens. The price we quote has changed 11 times since then, 9 of them a change of quoted host rather than a repricing. The latest change, on 2026-11-09, was +1.1% on the blended price (30% input, 70% output), to $0.60 input / $3.60 output (quoted host changed, not a repricing). Net of all changes, the blended price is +53.8% against 2026-08-15.
| Date | Old price (in / out) | New price (in / out) | Blended change |
|---|---|---|---|
| 2026-11-09 | $0.50 / $3.60 | $0.60 / $3.60 | +1.1% (quoted host changed, not a repricing) |
| 2026-10-22 | $0.39 / $2.34 | $0.50 / $3.60 | +52.1% (quoted host changed, not a repricing) |
| 2026-10-20 | $0.50 / $3.60 | $0.39 / $2.34 | -34.3% (quoted host changed, not a repricing) |
| 2026-10-14 | $0.55 / $3.50 | $0.50 / $3.60 | +2.1% (quoted host changed, not a repricing) |
| 2026-10-09 | $0.45 / $3.00 | $0.55 / $3.50 | +17.0% (quoted host changed, not a repricing) |
6 earlier changes are not listed.
Alternatives to Qwen3.5 397B A17B
2 of the 4 comparable models below cost less than Qwen3.5 397B A17B: GLM 4.6 undercuts it by 43%, and scores 2 Arena points higher.
- Next cheaper model in the Mid-range price tier: Kimi K2.7 Code (Moonshot) at $2.63 blended, 3% less.
- Next more expensive: Gemini 3.6 Flash (Google) at $2.85 blended, 6% more.
The nearest models in the Mid-range price tier on Arena ELO, each with its blended price and score difference against Qwen3.5 397B A17B.
- GLM 5V Turbo (Zhipu): $1.20 in / $4.00 out per 1M, Arena ELO 1438 (17% more expensive, same Arena ELO)
- GPT-5.2 Chat (OpenAI): $1.75 in / $14.00 out per 1M, Arena ELO 1439 (282% more expensive, 1 ELO point higher)
- GLM 4.6 (Zhipu): $0.50 in / $2.00 out per 1M, Arena ELO 1440 (43% cheaper, 2 ELO points higher)
- GLM 4.7 (Zhipu): $0.60 in / $2.20 out per 1M, Arena ELO 1435 (36% cheaper, 3 ELO points lower)
- Cheapest within 15 Arena points: Gemma 4 26B A4B (Google), 97% cheaper, 4 ELO points lower, out of 40 models in that band.
- Highest Arena ELO within 20% of this price: Gemini 3.8 Flash (Google), 6% more expensive, 62 ELO points higher, out of 13 models in that price band.
Other models from Alibaba
The 8 nearest to Qwen3.5 397B A17B in price, of 39 other Alibaba models in the catalogue. Prices per 1M tokens, input then output.
- Qwen3.5-122B-A10B: $0.26 / $2.08
- Qwen3.5-27B: $0.26 / $2.60
- Qwen3.6 27B: $0.32 / $3.20
- Qwen3 235B A22B Thinking 2507: $0.45 / $3.50
- Qwen3.7 Max: $1.475 / $4.425
- Qwen3.8 2.4T A95B: $2.00 / $6.00
- Qwen3.8 Max (0902): $2.00 / $6.00
- Qwen3.8 Max Prime: $4.00 / $12.00
All 40 Alibaba models and prices
Common questions about Qwen3.5 397B A17B pricing
- How much does Qwen3.5 397B A17B cost?
- Qwen3.5 397B A17B costs $0.60 per 1M input tokens and $3.60 per 1M output tokens at StreamLake, the host whose rate we quote. The model maker, Alibaba, lists it at $0.39 per 1M input tokens and $2.34 per 1M output tokens. Prices as listed on 2026-11-12.
- Which host is cheapest for Qwen3.5 397B A17B?
- Cheapest host: Alibaba at $0.39 input / $2.34 output per 1M tokens, 35% below the price we quote on the blended price (30% input, 70% output). A support ticket workload at 100K requests a month costs $175.50 there against $270.00 at the price we quote, a difference of $94.50 a month. The dearest, Venice, charges 1.9x the cheapest. Host rates as listed on 2026-11-12.
- Does Qwen3.5 397B A17B offer batch or cached pricing?
- Yes, for prompt caching only. Cache reads cost $0.12 per 1M tokens, as listed on 2026-11-12. No batch pricing is published.
- What would Qwen3.5 397B A17B cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $270 on Qwen3.5 397B A17B at the list price quoted on 2026-11-12.
- Can Qwen3.5 397B A17B be self-hosted?
- Yes. Qwen3.5 397B A17B is open source: its weights are published under Apache 2.0, an OSI-approved licence with no field-of-use limit, so it can be self-hosted as well as bought by the token.
- Has the price of Qwen3.5 397B A17B changed?
- Qwen3.5 397B A17B has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.39 input / $2.34 output per 1M tokens. The price we quote has changed 11 times since then, 9 of them a change of quoted host rather than a repricing. The latest change, on 2026-11-09, was +1.1% on the blended price (30% input, 70% output), to $0.60 input / $3.60 output (quoted host changed, not a repricing). Net of all changes, the blended price is +53.8% against 2026-08-15.
Its weights are published, which changes what you may run yourself: the cost gap between open weights and proprietary APIs.
These are list prices. Your real cost also depends on caching and batching, negotiated discounts, marketplace agreements, and the contracts you already have. OptimNow audits exactly that.
Build the business case · Get a FinOps review
LLM pricing · Models by maker · Cloud compute pricing · Compare models · Price barometer · FinOps guides · API and MCP server