Qwen3.6 35B A3B API pricing
Updated
Among the 12 providers we checked (prices read 2026-11-14 to 2026-11-16), the lowest blended standard price for Qwen3.6 35B A3B is CoreWeave Forge at USD 0.10 per 1M input tokens and USD 0.89 per 1M output tokens. The median across 12 standard prices is USD 0.16 / USD 1.05. Alibaba Cloud's own API charges USD 0.375 / USD 2.25.
What does Alibaba Cloud charge for Qwen3.6 35B A3B?
- Input
- USD 0.375
- Cached input
- not published
- Output
- USD 2.25
- Blended 3:1
- USD 0.8438
USD per 1M tokens on Alibaba Cloud Model Studio, model qwen3.6-35b-a3b, standard tier. Source, checked 2026-11-14.
Is a host cheaper than Alibaba Cloud? Yes. CoreWeave Forge charges USD 0.10 input and USD 0.89 output per 1M tokens, 65% below Alibaba Cloud's own USD 0.375 / USD 2.25 on the 3:1 blend.
Qwen3.6 35B A3B model facts
Facts from Qwen's model card for Qwen/Qwen3.6-35B-A3B and the Hugging Face model API, read 2026-11-16. BroadNet did not verify them, and hosts may serve the model at a different precision. BroadRouter is BroadNet's site.
| Fact | As stated | Source |
|---|---|---|
| Open weights | Yes. The weights are in a public Hugging Face repository (Qwen/Qwen3.6-35B-A3B) with no access gate. | Hugging Face model API, checked 2026-11-16Quote“"private": false, "gated": false, 26 .safetensors files listed” |
| Licence | Apache 2.0 (apache-2.0) | Qwen model card metadata, checked 2026-11-16Quote“license: apache-2.0” |
| Total parameters | 35B | Qwen model card, checked 2026-11-16Quote“Number of Parameters: 35B in total and 3B activated” |
| Active parameters per token | 3B | Qwen model card, checked 2026-11-16Quote“Number of Parameters: 35B in total and 3B activated” |
| Context length | 262,144 tokens natively, extensible up to 1,010,000 | Qwen model card, checked 2026-11-16Quote“Context Length: 262,144 natively and extensible up to 1,010,000 tokens.” |
| Input and output | Image and text in, text out (the card's task tag is image-text-to-text) | Qwen model card metadata, checked 2026-11-16Quote“pipeline_tag: image-text-to-text” |
| Tool calling | Yes | Qwen model card, checked 2026-11-16Quote“Tool Use: To support tool use, you can use the following command.” |
| First published on Hugging Face (not necessarily the release date) | 2026-04-15 | Hugging Face model API, checked 2026-11-16Quote“"createdAt": "2026-04-15T05:59:19.000Z"” |
Qwen3.6 35B A3B price per provider
USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first; the dearest standard price is 2.8× the cheapest. Free rows, the maker's serving version and other service tiers follow, tagged and unranked.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | CoreWeave Forge cheapestQwen/Qwen3.6-35B-A3BNotes and source quote“Qwen3.6 35B A3B $0.10 $0.89 $0.035” | USD 0.10 | USD 0.035 | USD 0.89 | USD 0.2975 | 262,144 | not stated | CoreWeave Forge page checked 2026-11-15 re-checked 2026-11-16 |
| 2 | AkashML promoQwen/Qwen3.6-35B-A3BNotes and source quoteLabelled "Limited Trial" on AkashML. “Price (per 1M Tokens) Input Output Cache Read QWEN3.6 35B A3B $0.10 $0.90 $0.05” | USD 0.10 | USD 0.05 | USD 0.90 | USD 0.30 | 262,144 | not stated | AkashML page checked 2026-11-15 re-checked 2026-11-16 |
| 3 | DeepInfraQwen/Qwen3.6-35B-A3BNotes and source quote“$0.10 in $0.95 out $0.10 cached / 1M tokens” | USD 0.10 | USD 0.10 | USD 0.95 | USD 0.3125 | 262,144 | FP8 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| 4 | Veniceqwen3-6-35b-a3bNotes and source quoteBeta model. “| Qwen 3.6 35B A3B (Beta) | `qwen3-6-35b-a3b` | $0.10 | $1.00 | — | — | Private |” | USD 0.10 | not published | USD 1 | USD 0.325 | 256,000 | FP8 | Venice page checked 2026-11-15 re-checked 2026-11-16 |
| 5 | DoublewordNotes and source quoteRealtime priority. “Qwen3.6 35B A3B $0.14 / $0.14 / $1.00 $0.11 / $0.11 / $0.75 $0.07 / $0.07 / $0.50” | USD 0.14 | USD 0.14 | USD 1 | USD 0.355 | not stated | not stated | Doubleword page checked 2026-11-16 |
| 6 | ParasailNotes and source quote“Qwen3.6 35B-A3B $0.15 $1.00 $0.05” | USD 0.15 | USD 0.05 | USD 1 | USD 0.3625 | not stated | not stated | Parasail page checked 2026-11-14 re-checked 2026-11-16 |
| 7 | NEAR AI CloudNotes and source quote“Qwen 3.6 35B A3B FP8 Text Provider NEAR AI Input $0.17 Output $1.1 Cache read $0.056 Context 262K Privacy tier Private TEE” | USD 0.17 | USD 0.056 | USD 1.10 | USD 0.4025 | 262,144 | FP8 | NEAR AI Cloud page checked 2026-11-16 |
| 8 | FeatherlessQwen/Qwen3.6-35B-A3BNotes and source quoteDeveloper plan (per-token billing, from 50 USD a month in credits). “PRICING: INPUT $0.186 / CACHED $0.032 / OUTPUT $1.1138” | USD 0.186 | USD 0.032 | USD 1.1138 | USD 0.4179 | 32,768 | FP8 | Featherless page checked 2026-11-15 re-checked 2026-11-16 |
| 9 | GMI CloudQwen/Qwen3.6-35B-A3BNotes and source quoteNo cache-read price published. “Price (per 1M tokens) Input $0.248 Output $1.485” | USD 0.248 | not published | USD 1.485 | USD 0.5573 | 262,144 | FP8 | GMI Cloud page checked 2026-11-15 re-checked 2026-11-16 |
| 10 | Novita AIqwen/qwen3.6-35b-a3bNotes and source quote“Qwen3.6 35B A3B 256K $0.248 /Mt $1.485 /Mt” | USD 0.248 | not published | USD 1.485 | USD 0.5573 | 262,144 | not stated | Novita AI page checked 2026-11-14 re-checked 2026-11-16 |
| 11 | SiliconFlowNotes and source quoteContext shown as 262K. “Qwen3.6-35B-A3B 262K $0.24 $0.15 $1.8” | USD 0.24 | USD 0.15 | USD 1.80 | USD 0.63 | 262,144 | not stated | SiliconFlow page checked 2026-11-14 re-checked 2026-11-16 |
| 12 | Alibaba Cloud makerqwen3.6-35b-a3bNotes and source quoteInternational (Singapore) deployment. Open-weight model. Prompts up to 256K tokens; same output price in thinking and non-thinking mode. “qwen3.6-35b-a3b International 0<Token≤256K $0.375 $2.25 $2.25” | USD 0.375 | not published | USD 2.25 | USD 0.8438 | not stated | not stated | Alibaba Cloud page checked 2026-11-14 re-checked 2026-11-16 |
| — | Doubleword batchNotes and source quoteBatch (24h) priority. “Qwen3.6 35B A3B $0.14 / $0.14 / $1.00 $0.11 / $0.11 / $0.75 $0.07 / $0.07 / $0.50” | USD 0.07 | USD 0.07 | USD 0.50 | USD 0.1775 | not stated | not stated | Doubleword page checked 2026-11-16 |
| — | Sail Research flex / spotQwen/Qwen3.6-35B-A3BNotes and source quoteFlex-only model: first turn may queue up to 1 hour; background requests only. Sail sells no Default-tier endpoint for it. “Qwen3.6 35B A3B Qwen/Qwen3.6-35B-A3B Flex $ 0.05 $ 0.02 $ 0.40” | USD 0.05 | USD 0.02 | USD 0.40 | USD 0.1375 | not stated | not stated | Sail Research page checked 2026-11-16 |
| — | DeepInfra flex / spotQwen/Qwen3.6-35B-A3BNotes and source quoteFlex service tier (0.8× standard). “Flex (0.8×) $0.08 $0.76 $0.08” | USD 0.08 | USD 0.08 | USD 0.76 | USD 0.25 | 262,144 | FP8 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
| — | Doubleword flex / spotNotes and source quoteAsync priority. “Qwen3.6 35B A3B $0.14 / $0.14 / $1.00 $0.11 / $0.11 / $0.75 $0.07 / $0.07 / $0.50” | USD 0.11 | USD 0.11 | USD 0.75 | USD 0.27 | not stated | not stated | Doubleword page checked 2026-11-16 |
| — | DeepInfra priorityQwen/Qwen3.6-35B-A3BNotes and source quotePriority service tier (1.5× standard). “Priority (1.5×) $0.15 $1.425 $0.15” | USD 0.15 | USD 0.15 | USD 1.425 | USD 0.4688 | 262,144 | FP8 | DeepInfra page checked 2026-11-14 re-checked 2026-11-16 |
- Ranked: standard-tier prices only, on (3 × input + output) ÷ 4. "Cached input: not published" means the provider's page shows no cache price; budget cached tokens at the input price.
- Promo: the provider's page describes this price as promotional or discounted (AkashML). It ranks as published, but can end without notice; the row's notes give the list price or end date where the page states one.
- Other tiers (batch, flex / spot and priority): batch runs asynchronously within hours; flex and spot are best-effort and can be slow or refused at capacity; priority and fast cost more for reliability or speed. Shown, not ranked.
- Automated re-check 2026-11-16: a weekly job re-fetches each source page and looks for the recorded quote or prices. It is not a human review. "Re-checked" means it still found them. Rows with no re-check note show only the date the price was read.
- Precision is shown only where the provider states it; "not stated" is unknown, not full precision.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What does Qwen3.6 35B A3B cost for a real workload?
Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.
- Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
- RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
- Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
| Provider | Support chatbot | RAG over documents | Coding agent (one developer) |
|---|---|---|---|
| CoreWeave Forge | USD 21.51 | USD 32.67 | USD 160.65 |
| AkashML (promo) | USD 22.50 | USD 33.90 | USD 184.50 |
| DeepInfra | USD 26.10 | USD 38.25 | USD 265.50 |
| Venice | USD 27.00 | USD 39.00 | USD 270.00 |
| Doubleword | USD 30.60 | USD 48.60 | USD 342.00 |
| Parasail | USD 26.10 | USD 43.80 | USD 207.00 |
| NEAR AI Cloud | USD 28.94 | USD 49.09 | USD 230.58 |
| Featherless | USD 28.47 | USD 50.26 | exceeds context |
| GMI Cloud | USD 49.05 | USD 81.80 | USD 580.05 |
| Novita AI | USD 49.05 | USD 81.80 | USD 580.05 |
| SiliconFlow | USD 49.14 | USD 78.12 | USD 456.30 |
| Alibaba Cloud (maker) | USD 74.25 | USD 123.75 | USD 877.50 |
For the support chatbot, the cheapest price (CoreWeave Forge, USD 21.51 a month) saves USD 7.20 against the median (USD 28.71). For the coding agent the gap is USD 107.10 a month (40% lower).
Which Qwen3.6 35B A3B provider is cheapest for your traffic?
CoreWeave Forge has the lowest input price (USD 0.10) and the lowest output price (USD 0.89), so it is the cheapest standard price at every mix of input and output tokens, before cache discounts.
| Provider | No cache hits | 50% cached | 90% cached |
|---|---|---|---|
| CoreWeave Forge | USD 0.2975 cheapest | USD 0.2731 cheapest | USD 0.2536 cheapest |
| AkashML | USD 0.30 | USD 0.2813 | USD 0.2662 |
| DeepInfra | USD 0.3125 | USD 0.3125 | USD 0.3125 |
| Venice (no cache price) | USD 0.325 | USD 0.325 | USD 0.325 |
| Doubleword | USD 0.355 | USD 0.355 | USD 0.355 |
| Parasail | USD 0.3625 | USD 0.325 | USD 0.295 |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row; 6 dearer providers are in the price table above. A provider without a cached price bills cached input at the input price. Any charge for writing to the cache, which some providers add, is not included.
6 of 12 providers publish a cached-input price below the input price: CoreWeave Forge (65% off), AkashML (50% off), Parasail (67% off), NEAR AI Cloud (67% off), Featherless (83% off), SiliconFlow (38% off). Venice, GMI Cloud, Novita AI and Alibaba Cloud publish none, so cached tokens there bill at the input price. DeepInfra and Doubleword list cached prices equal to their input price.
Context windows differ: 262,144 tokens at CoreWeave Forge, AkashML, DeepInfra and 4 more; 256,000 tokens at Venice; 32,768 tokens at Featherless. Doubleword, Parasail and Alibaba Cloud do not state one. The cheapest row is not always the one that fits a long prompt.
What does Qwen3.6 35B A3B cost in other languages?
The same text needs a different number of tokens in each language. With the Qwen3.8 27B tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for Qwen3.6 35B A3B:
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 0.022 | CoreWeave Forge |
| Arabic MSA | USD 0.031 | CoreWeave Forge |
| Hindi | USD 0.042 | CoreWeave Forge |
| Chinese | USD 0.058 | CoreWeave Forge |
| Code | USD 0.028 | CoreWeave Forge |
From BroadRouter's real cost by language dataset, which covers 15 languages and content types for every model we could match to a measured tokenizer.
Published benchmark results
BroadNet did not run these benchmarks; results are as published by the Qwen model card and Epoch AI and may use different settings. BroadRouter is BroadNet's site.
| Benchmark | Result | Setting or note | Source |
|---|---|---|---|
| GPQA | 86.0 | not stated | Qwen model card, checked 2026-11-16 |
| MMLU-Pro | 85.2 | not stated | Qwen model card, checked 2026-11-16 |
| SWE-bench Verified | 73.4 | not stated | Qwen model card, checked 2026-11-16 |
| LiveCodeBench v6 | 80.4 | not stated | Qwen model card, checked 2026-11-16 |
| GPQA Diamond | 0.838 | Setting as listed by Epoch (no suffix); Epoch run qwen3.6-35b-a3b, mean score on a 0 to 1 scale | Epoch AI, checked 2026-11-16 |
Epoch AI rows: Epoch AI, Capabilities & benchmarking, licensed CC BY 4.0, shown as the mean score on a 0 to 1 scale, rounded to three decimals (hover a value for the exact figure in Epoch's data file).
Estimate your own bill
- LLM API cost calculator with Qwen3.6 35B A3B preloaded: your traffic and cache rate, against any of 431 models.
- Qwen token counter: count the tokens in your real prompts. Tokenizers differ, so the same text costs a different number of tokens on different models.
- Prompt caching calculator: what a higher cache-hit rate saves.
How does Qwen3.6 35B A3B compare with other Qwen models?
The Qwen models whose cheapest standard price is closest to Qwen3.6 35B A3B's (USD 0.2975 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| Qwen3-VL 8B | USD 0.18 | USD 0.68 | 262,144 | 2 |
| Qwen3 Coder Next | USD 0.12 | USD 0.80 | 32,768 | 3 |
| Qwen3.8 27B | USD 0.039 | USD 1.25 | 1,000,000 | 19 |
| Qwen3 Next 80B A3B Instruct | USD 0.09 | USD 1.10 | 262,144 | 5 |
| Qwen3.5 35B A3B | USD 0.14 | USD 1 | 262,144 | 7 |
| Qwen2.5-72B-Instruct | USD 0.36 | USD 0.40 | 32,768 | 3 |
Priced closest from other makers: Ripple-65B Preview (Ricursive AI, USD 0.30) · DeepSeek-V3.2-Exp (DeepSeek, USD 0.305) · GLM 4.5 Air (Z.ai, USD 0.31).
Compare Qwen3.6 35B A3B with
- Gemma 4 26B A4B vs Qwen3.6 35B A3B: API price side by side
- gpt-oss-20b vs Qwen3.6 35B A3B: API price side by side
- DeepSeek V4.1 Flash vs Qwen3.6 35B A3B: API price side by side
- Qwen3.6 35B A3B vs Qwen3.5 35B A3B: API price side by side
- Qwen3.6 35B A3B vs Qwen3.6 27B: API price side by side
Also compared: vs Gemma 4 26B A4B · vs GPT OSS 20B · vs DeepSeek V4.1 Flash · vs Qwen3.5 35B A3B · vs Qwen3.6 27B.
Every Qwen3.6 35B A3B price comparison · All model-vs-model price comparisons
All 431 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log
Questions
How much does the Qwen3.6 35B A3B API cost per token?
From USD 0.10 per 1M input tokens (USD 0.0000001 per token) and USD 0.89 per 1M output tokens (USD 0.00000089 per token) at the lowest standard prices we found. The median of 12 standard prices is USD 0.16 input and USD 1.05 output. Each price was read from the provider's own pricing page; the source is linked in its row.
Which provider is cheapest for Qwen3.6 35B A3B?
Among the 12 providers we checked (prices read 2026-11-14 to 2026-11-16), the lowest is CoreWeave Forge, ranked on a blend of 3 input tokens to 1 output token (USD 0.2975 per 1M). For input alone the lowest price is USD 0.10 (CoreWeave Forge and 3 others, tied); for output alone, USD 0.89 (CoreWeave Forge). Batch, flex, priority and fast tiers are shown in the table but not ranked.
Is Qwen3.6 35B A3B cheaper from a host than from Alibaba Cloud?
Yes. CoreWeave Forge charges USD 0.10 input and USD 0.89 output per 1M tokens, 65% below Alibaba Cloud's own USD 0.375 / USD 2.25 on the 3:1 blend.
Does Qwen3.6 35B A3B have cached input pricing?
8 of 12 standard prices include one. The lowest is USD 0.032 per 1M at Featherless; the median is USD 0.053. Providers without one bill cached input at the input price. What cached input means.
What is the Qwen3.6 35B A3B context window?
Up to 262,144 tokens. 2 standard prices come with less, down to 32,768 tokens (Featherless and Venice). Check the context column before you pick the cheapest row for long prompts. Context window calculator.
How much does a coding agent cost per month on Qwen3.6 35B A3B?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 160.65 a month at CoreWeave Forge, USD 267.75 at the median price and USD 877.50 at Alibaba Cloud. Try your own numbers.
Is there a batch, flex or priority price for Qwen3.6 35B A3B?
Yes: batch from Doubleword at USD 0.07 / USD 0.50; flex / spot from Sail Research at USD 0.05 / USD 0.40; priority from DeepInfra at USD 0.15 / USD 1.425 per 1M input / output tokens. These tiers trade speed or availability for price (batch runs within hours, flex and spot can be slow or refused at capacity, priority and fast cost more for speed or reliability), so they are shown but not ranked.
Is Qwen3.6 35B A3B free to use through an API?
No provider in our data lists a free price for Qwen3.6 35B A3B as of 2026-11-16. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model; all free LLM API models are on one page.
Is Qwen3.6 35B A3B open source, with open weights, and what is its licence?
Qwen publishes the weights on Hugging Face as Qwen/Qwen3.6-35B-A3B, in a public repository with no access gate. The licence, as the Qwen model card metadata states it: Apache 2.0 (apache-2.0). Open weights means you can download and run the model yourself; what you may do with it, including commercial use, is set by that licence, so read it in full (checked 2026-11-16). These facts come from Qwen's card and the Hugging Face model API; BroadNet did not verify them, and hosts may serve the model at a different precision.
How many parameters does Qwen3.6 35B A3B have?
Total parameters, as the Qwen model card states them: 35B. Active parameters per token: 3B. (checked 2026-11-16; BroadNet did not verify these figures.)
Does Qwen3.6 35B A3B support tool calling?
Yes, according to the Qwen model card: “Tool Use: To support tool use, you can use the following command.” (checked 2026-11-16). Whether the tools parameter works through an API also depends on the provider serving it, so check that provider's docs. BroadNet did not test it.
How do I call Qwen3.6 35B A3B with the OpenAI SDK?
BroadNet does not serve Qwen3.6 35B A3B. Use the OpenAI-compatible base URL of a provider that lists it: create the client with OpenAI(base_url=..., api_key=...) and pass that provider's model ID. Documented base URLs for providers on this page, in alphabetical order: Alibaba Cloud Model Studio (https://{WorkspaceId}.ap-southeast-1.maas.aliyuncs.com/compatible-mode/v1, model qwen3.6-35b-a3b) and DeepInfra (https://api.deepinfra.com/v1/openai, model Qwen/Qwen3.6-35B-A3B). Each provider page quotes the provider's docs with a check date.
How does Qwen3.6 35B A3B score on benchmarks?
As published, the Qwen model card reports 86.0 on GPQA and 85.2 on MMLU-Pro; Epoch AI measured 0.838 on GPQA Diamond in its own run, as a mean score on a 0 to 1 scale (checked 2026-11-16). BroadNet did not run these benchmarks, and sources may use different settings, so the figures are not directly comparable. Every published result we found, with its setting and source.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources
- AkashML: pricing (checked 2026-11-15)
- Alibaba Cloud: own API pricing (checked 2026-11-14)
- CoreWeave Forge: pricing (checked 2026-11-15)
- DeepInfra: pricing (checked 2026-11-14)
- Doubleword: pricing (checked 2026-11-16)
- Featherless: pricing (checked 2026-11-15)
- GMI Cloud: pricing (checked 2026-11-15)
- NEAR AI Cloud: pricing (checked 2026-11-16)
- Novita AI: pricing (checked 2026-11-14)
- Parasail: pricing (checked 2026-11-14)
- Sail Research: pricing (checked 2026-11-16)
- SiliconFlow: pricing (checked 2026-11-14)
- Venice: pricing (checked 2026-11-15)