Qwen3.6 35B A3B API Pricing
Alibaba · Budget · Qwen · released 2026-04. Prices in USD per 1 million tokens. Data snapshot: 2026-09-28.
The price we publish for Qwen3.6 35B A3B has changed 3 times since 2026-08-15, most recently on 2026-09-21 when the reference host changed (+12.9%); it is now the 94th cheapest of 142 Budget models. Buying from Darkbloom rather than at the rate quoted here lowers the token price by about 32%, for a quantized fp4 build. No Arena score is published for it, so it carries no Efficiency score and cannot hold the FinOps Friendly badge.
- Input: $0.15 per 1M tokens
- Output: $1.00 per 1M tokens
- Batch API (input/output): not published
- Prompt-cache read: $0.05
- Context window: 262K
Qwen3.6 35B A3B market position
On blended price ($0.745 per 1M tokens at 30% input, 70% output) it is cheaper than 34% of Budget models: 94th cheapest of 142. Across every category it is cheaper than 67% of priced text models in the catalogue: 94th cheapest of 281.
Qwen3.6 35B A3B licence, size and capabilities
Qwen3.6 35B A3B is open weights, which is not the same as open source: the weights are published, but under Qwen, a licence that restricts some uses. Read it before self-hosting commercially. Its published size is 35B parameters. Listed capabilities: Text, Vision, Reasoning, Code, Agents. Filling its 262K context window once costs $0.04 in input tokens at list price.
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 the provider 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 | $64 – $73 |
| Knowledge Q&A | 2,000 / 800 | $96 – $110 |
| Meeting Summary | 10,000 / 1,200 | $260 – $270 |
| Marketing Content | 2,500 / 1,800 | $213 – $217 |
| Coding Task | 3,000 / 2,000 | $230 – $245 |
| Invoice Processing | 1,500 / 600 | $78 – $83 |
| Call Summary | 2,000 / 700 | $98 – $100 |
| Agent Workflow | 6,000 / 3,000 | $348 – $390 |
Qwen3.6 35B A3B pricing by host
A host is a company that runs the model and sells it by the token — the lab that made it, a cloud platform like Amazon Bedrock, Azure or Vertex, or an independent provider. One model, several sellers, and often several prices. This model is sold by 10 different hosts. The price quoted above is the one we publish so that models stay comparable; it is not necessarily the cheapest way to buy this model. List prices as published on 2026-09-28 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.
Cheapest host: Darkbloom at $0.05 input / $0.70 output per 1M tokens, 32% below the price we publish on a blended basis (30% input, 70% output). It serves a quantized fp4 build, which is not the same product as the full-precision model. The dearest, SiliconFlow, charges 2.6x the cheapest.
| Host | Input $/1M | Output $/1M |
|---|---|---|
| Darkbloom — fp4 | $0.05 | $0.70 |
| AkashML — fp8 | $0.10 | $0.90 |
| DeepInfra — fp8 | $0.10 | $0.95 |
| Reka | $0.10 | $1.00 |
| Venice — fp8 | $0.10 | $1.00 |
| Parasail (the price shown above) — fp8 | $0.15 | $1.00 |
| AtlasCloud — fp8 | $0.19 | $1.11 |
| Phala | $0.20 | $1.27 |
| CoreWeave — fp8 | $0.25 | $1.25 |
| SiliconFlow — fp8 | $0.24 | $1.80 |
Qwen3.6 35B A3B 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 publish has changed 3 times since then, 1 of them a change of reference host rather than a repricing. The latest change, on 2026-09-21, was +12.9% on the blended price (30% input, 70% output), to $0.15 input / $1.00 output (reference host changed, not a repricing). Net of all changes, the blended price is back where it started on 2026-08-15.
| Date | Old price (in / out) | New price (in / out) | Blended change |
|---|---|---|---|
| 2026-09-21 | $0.10 / $0.90 | $0.15 / $1.00 | +12.9% (reference host changed, not a repricing) |
| 2026-08-27 | $0.14 / $1.00 | $0.10 / $0.90 | -11.1% |
| 2026-08-17 | $0.15 / $1.00 | $0.14 / $1.00 | -0.4% |
Alternatives to Qwen3.6 35B A3B
- Next cheaper Budget model: Qwen3 Coder Flash (Alibaba) at $0.741 blended, 1% less.
- Next more expensive: DeepSeek V3.1 Terminus (DeepSeek) at $0.781 blended, 5% more.
Common questions about Qwen3.6 35B A3B pricing
- How much does Qwen3.6 35B A3B cost?
- Qwen3.6 35B A3B costs $0.15 per million input tokens and $1.00 per million output tokens on the API.
- Does Qwen3.6 35B A3B offer batch or cached pricing?
- Prompt-cache reads cost $0.05/M input tokens. No batch pricing is published.
- What would Qwen3.6 35B A3B cost per month?
- For a support-ticket workload (1,500 input + 500 output tokens per request) at 100K requests/month, Qwen3.6 35B A3B costs about $73 at list prices.
- 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 publish has changed 3 times since then, 1 of them a change of reference host rather than a repricing. The latest change, on 2026-09-21, was +12.9% on the blended price (30% input, 70% output), to $0.15 input / $1.00 output (reference host changed, not a repricing). Net of all changes, the blended price is back where it started on 2026-08-15.
These are list prices: real cost also depends on caching, batching, negotiated discounts, marketplace agreements, and existing contracts. Get a FinOps review from OptimNow or compare all models.
Build the business case for Qwen3.6 35B A3B in the AI ROI Calculator: add your business value on top of these costs to get ROI, break-even and payback.
All models · Compare side by side · Cloud compute pricing · Price barometer · FinOps guides · API and MCP server