Qwen3.6 35B A3B API pricing
Alibaba · Budget price tier · Apache 2.0 · released 2026-04. Prices in USD per 1 million tokens. Data snapshot: 2026-11-12.
A support ticket workload of 100K requests a month costs $60.00 on Qwen3.6 35B A3B; the next cheaper model in the Budget price tier for this workload, Qwen3 Coder Next, does it for $58.00. The price we quote for Qwen3.6 35B A3B has changed 7 times since 2026-08-15, most recently by -5.0% on 2026-10-28; it is now the 103rd cheapest of 160 models in the Budget price tier. Buying from PrimeIntellect rather than at the price we quote lowers the token price by about 88%, for a quantized fp8 build. No Arena score is published for it, so it carries no Efficiency score and cannot hold the FinOps Friendly badge.
- Input: $0.10 per 1M tokens
- Output: $0.90 per 1M tokens
- Batch API (in/out): Not published
- Prompt-cache read: $0.025 per 1M tokens
- Context window: 262K tokens
- Arena ELO: Not published
Market position
On blended price ($0.66 per 1M tokens at 30% input, 70% output) it is cheaper than 36% of models in the Budget price tier: 103rd cheapest of 160. Across every price tier it is cheaper than 66% of priced text models in the catalogue: 103rd cheapest of 303. No Arena score has been published for Qwen3.6 35B A3B, so this page does not rank it on quality and OptimNow's quality bars do not apply to it. 77 of the 160 models we list in the Budget price tier carry one. An unranked model is unmeasured, not poor: the benchmark needs votes, and a recent release has not had time to collect them.
Licence, size and capabilities
Qwen3.6 35B A3B 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 35B parameters. Listed capabilities: Text, Vision, Reasoning, Agents. Filling its 262K context window once costs $0.0262 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 10 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: PrimeIntellect at $0.012 input / $0.106 output per 1M tokens, 88% below the price we quote on the blended price (30% input, 70% output). It serves a quantized fp8 build, which is not the same product as the full-precision model. A support ticket workload at 100K requests a month costs $7.10 there against $60.00 at the price we quote, a difference of $52.90 a month. The dearest, SiliconFlow, charges 17.1x the cheapest.
| Host | Input $/1M | Output $/1M | Precision |
|---|---|---|---|
| PrimeIntellect | $0.012 | $0.106 | fp8 |
| Darkbloom | $0.05 | $0.70 | fp4 |
| CoreWeave (price we quote) | $0.10 | $0.89 | fp8 |
| AkashML (price we quote) | $0.10 | $0.90 | fp8 |
| Parasail (price we quote) | $0.10 | $0.90 | fp8 |
| DeepInfra | $0.10 | $0.95 | fp8 |
| DekaLLM | $0.10 | $1.00 | not declared |
| Venice | $0.10 | $1.00 | fp8 |
| AtlasCloud | $0.25 | $1.25 | fp8 |
| SiliconFlow | $0.24 | $1.80 | fp8 |
List prices as published on 2026-11-12, via OpenRouter. Negotiated rates, committed-use discounts and provisioned capacity are not shown. These hosts do not all serve the model at the same numeric precision, so the cheapest is not a like-for-like substitute for the dearest.
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 | $53 – $60 |
| Knowledge Q&A | 2,000 / 800 | $82 – $92 |
| Meeting Summary | 10,000 / 1,200 | $201 – $208 |
| Marketing Content | 2,500 / 1,800 | $183 – $187 |
| Coding Task | 3,000 / 2,000 | $199 – $210 |
| Invoice Processing | 1,500 / 600 | $66 – $69 |
| Call Summary | 2,000 / 700 | $82 – $83 |
| Agent Workflow | 6,000 / 3,000 | $299 – $330 |
Price history
Qwen3.6 35B A3B has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.15 input / $1.00 output per 1M tokens. The price we quote has changed 7 times since then, 3 of them a change of quoted host rather than a repricing. The latest change, on 2026-10-28, was -5.0% on the blended price (30% input, 70% output), to $0.10 input / $0.90 output. Net of all changes, the blended price is -11.4% against 2026-08-15.
| Date | Old price (in / out) | New price (in / out) | Blended change |
|---|---|---|---|
| 2026-10-28 | $0.10 / $0.95 | $0.10 / $0.90 | -5.0% |
| 2026-10-20 | $0.15 / $1.00 | $0.10 / $0.95 | -6.7% |
| 2026-10-15 | $0.10 / $0.95 | $0.15 / $1.00 | +7.2% (quoted host changed, not a repricing) |
| 2026-10-11 | $0.15 / $1.00 | $0.10 / $0.95 | -6.7% (quoted host changed, not a repricing) |
| 2026-09-21 | $0.10 / $0.90 | $0.15 / $1.00 | +12.9% (quoted host changed, not a repricing) |
2 earlier changes are not listed.
Alternatives to Qwen3.6 35B A3B
Qwen3.6 35B A3B carries no Arena score, so this page cannot place it against models of comparable quality. The alternatives below are its nearest neighbours on price in the Budget price tier.
- Next cheaper model in the Budget price tier: MiniMax M2.7 (MiniMax) at $0.651 blended, 1% less.
- Next more expensive: Llama 3.3 70B Instruct (Meta) at $0.71 blended, 8% more.
Other models from Alibaba
The 8 nearest to Qwen3.6 35B A3B in price, of 39 other Alibaba models in the catalogue. Prices per 1M tokens, input then output.
- Qwen3 Coder Next: $0.12 / $0.80
- Qwen3 VL 8B Instruct: $0.25 / $0.75
- Qwen3 235B A22B Instruct 2507: $0.14 / $0.80
- Qwen-Plus: $0.26 / $0.78
- Qwen3 Coder Flash: $0.195 / $0.975
- Qwen3.5-35B-A3B: $0.14 / $1.00
- Qwen3 VL 30B A3B Thinking: $0.29 / $1.00
- Qwen3 Coder 480B A35B: $0.30 / $1.00
All 40 Alibaba models and prices
Common questions about Qwen3.6 35B A3B pricing
- How much does Qwen3.6 35B A3B cost?
- Qwen3.6 35B A3B costs $0.10 per 1M input tokens and $0.90 per 1M output tokens at CoreWeave, the host whose rate we quote. CoreWeave serves a quantized fp8 build, which is not the same product as the full-precision model. Prices as listed on 2026-11-12.
- Which host is cheapest for Qwen3.6 35B A3B?
- Cheapest host: PrimeIntellect at $0.012 input / $0.106 output per 1M tokens, 88% below the price we quote on the blended price (30% input, 70% output). It serves a quantized fp8 build, which is not the same product as the full-precision model. A support ticket workload at 100K requests a month costs $7.10 there against $60.00 at the price we quote, a difference of $52.90 a month. The dearest, SiliconFlow, charges 17.1x the cheapest. Host rates as listed on 2026-11-12.
- Does Qwen3.6 35B A3B offer batch or cached pricing?
- Yes, for prompt caching only. Cache reads cost $0.025 per 1M tokens, as listed on 2026-11-12. No batch pricing is published.
- What would Qwen3.6 35B A3B cost per month?
- With the Support Ticket profile (1,500 input and 500 output tokens per request), 100,000 requests a month cost about $60 on Qwen3.6 35B A3B at the list price quoted on 2026-11-12.
- Can Qwen3.6 35B A3B be self-hosted?
- Yes. Qwen3.6 35B A3B 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 Qwen3.6 35B A3B changed?
- Qwen3.6 35B A3B has been in our daily price archive since tracking began on 2026-08-15, when it listed at $0.15 input / $1.00 output per 1M tokens. The price we quote has changed 7 times since then, 3 of them a change of quoted host rather than a repricing. The latest change, on 2026-10-28, was -5.0% on the blended price (30% input, 70% output), to $0.10 input / $0.90 output. Net of all changes, the blended price is -11.4% 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