Qwen3 Next 80B A3B Thinking API pricing
Updated
Among the 2 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest blended standard price for Qwen3 Next 80B A3B Thinking is Google Vertex AI at USD 0.15 per 1M input tokens and USD 1.20 per 1M output tokens. The median across 2 standard prices is USD 0.15 / USD 1.35. Each price is read from the provider's own pricing page.
Does Qwen sell Qwen3 Next 80B A3B Thinking directly?
Qwen publishes no price for Qwen3 Next 80B A3B Thinking on its own API that we could find, so this page compares hosts only.
Qwen3 Next 80B A3B Thinking model facts
Facts from Qwen's model card for Qwen/Qwen3-Next-80B-A3B-Thinking 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-Next-80B-A3B-Thinking) with no access gate. | Hugging Face model API, checked 2026-11-16Quote“"private": false, "gated": false, 41 .safetensors files listed” |
| Licence | Apache 2.0 (apache-2.0) | Qwen model card metadata, checked 2026-11-16Quote“license: apache-2.0” |
| Total parameters | 80B | Qwen model card, checked 2026-11-16Quote“Number of Parameters: 80B in total and 3B activated” |
| Active parameters per token | 3B | Qwen model card, checked 2026-11-16Quote“Number of Parameters: 80B 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 | Text in, text out (the card's task tag is text-generation) | Qwen model card metadata, checked 2026-11-16Quote“pipeline_tag: text-generation” |
| Tool calling | Yes | Qwen model card, checked 2026-11-16Quote“Qwen3 excels in tool calling capabilities.” |
| First published on Hugging Face (not necessarily the release date) | 2025-09-09 | Hugging Face model API, checked 2026-11-16Quote“"createdAt": "2025-09-09T15:45:31.000Z"” |
Qwen3 Next 80B A3B Thinking 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 18% above the cheapest.
| # | Provider | Input | Cached input | Output | Blended 3:1 | Context | Precision | Source |
|---|---|---|---|---|---|---|---|---|
| 1 | Google Vertex AI cheapestqwen3-next-80b-a3b-thinkingNotes and source quote“Qwen3-Next-80B-Thinking Input $0.15 … Output $1.20” | USD 0.15 | not published | USD 1.20 | USD 0.4125 | not stated | not stated | Google Vertex AI page checked 2026-11-14 re-checked 2026-11-16 |
| 2 | GMI CloudQwen/Qwen3-Next-80B-A3B-ThinkingNotes and source quoteNo cache-read price published. “Price (per 1M tokens) Input $0.15 Output $1.50” | USD 0.15 | not published | USD 1.50 | USD 0.4875 | 262,144 | FP8 | GMI Cloud page checked 2026-11-15 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.
- 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 Next 80B A3B Thinking 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) |
|---|---|---|---|
| Google Vertex AI | USD 35.10 | USD 54.00 | USD 378.00 |
| GMI Cloud | USD 40.50 | USD 58.50 | USD 405.00 |
For the support chatbot, the cheapest price (Google Vertex AI, USD 35.10 a month) saves USD 2.70 against the median (USD 37.80). For the coding agent the gap is USD 13.50 a month (3% lower).
Which Qwen3 Next 80B A3B Thinking provider is cheapest for your traffic?
Google Vertex AI has the lowest input price (USD 0.15) and the lowest output price (USD 1.20), 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 |
|---|---|---|---|
| Google Vertex AI (no cache price) | USD 0.4125 cheapest | USD 0.4125 cheapest | USD 0.4125 cheapest |
| GMI Cloud (no cache price) | USD 0.4875 | USD 0.4875 | USD 0.4875 |
USD per 1M tokens, 3 input tokens to 1 output token, each provider's cheapest standard row. 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.
None of the 2 providers publishes a cached-input discount for Qwen3 Next 80B A3B Thinking, so cache hits do not change the ranking.
GMI Cloud states a context window of 262,144 tokens; Google Vertex AI does not state one.
What does Qwen3 Next 80B A3B Thinking cost in other languages?
The same text needs a different number of tokens in each language. With the Qwen3 32B tokenizer, sending 1M characters costs this much at the cheapest standard input price we found for Qwen3 Next 80B A3B Thinking:
| Content | Input per 1M characters | Cheapest provider |
|---|---|---|
| English | USD 0.033 | GMI Cloud |
| Arabic MSA | USD 0.058 | GMI Cloud |
| Hindi | USD 0.140 | GMI Cloud |
| Chinese | USD 0.096 | GMI Cloud |
| Code | USD 0.039 | GMI Cloud |
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.
Estimate your own bill
- LLM API cost calculator with Qwen3 Next 80B A3B Thinking preloaded: your traffic and cache rate, against any of 431 models.
- Qwen3 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 Next 80B A3B Thinking compare with other Qwen models?
The Qwen models whose cheapest standard price is closest to Qwen3 Next 80B A3B Thinking's (USD 0.4125 blended):
| Model | Cheapest input | Cheapest output | Max context | Providers |
|---|---|---|---|---|
| Qwen3 235B A22B FP8 | USD 0.17 | USD 1.09 | 32,768 | 2 |
| Qwen3 Coder 480B A35B | USD 0.25 | USD 1 | 262,144 | 6 |
| Qwen-MT Plus | USD 0.25 | USD 0.75 | 16,384 | 2 |
| Qwen2.5-72B-Instruct | USD 0.36 | USD 0.40 | 32,768 | 3 |
| Qwen3 VL 235B A22B Instruct | USD 0.20 | USD 0.88 | 262,144 | 4 |
| Qwen3.5 35B A3B | USD 0.14 | USD 1 | 262,144 | 7 |
Priced closest from other makers: MiniMax M3 (MiniMax, USD 0.4125) · MiMo V2.6 Pro (Xiaomi, USD 0.4078) · DeepSeek V3.1 (DeepSeek, USD 0.425).
Compare Qwen3 Next 80B A3B Thinking with
- Qwen3 Next 80B A3B Thinking vs Qwen3 Next 80B A3B: API price side by side
Also compared: vs Qwen3 Next 80B A3B Instruct.
Every Qwen3 Next 80B A3B Thinking 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 Next 80B A3B Thinking API cost per token?
From USD 0.15 per 1M input tokens (USD 0.00000015 per token) and USD 1.20 per 1M output tokens (USD 0.0000012 per token) at the lowest standard prices we found. The median of 2 standard prices is USD 0.15 input and USD 1.35 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 Next 80B A3B Thinking?
Among the 2 providers we checked (prices read 2026-11-14 to 2026-11-15), the lowest is Google Vertex AI, ranked on a blend of 3 input tokens to 1 output token (USD 0.4125 per 1M). For input alone the lowest price is USD 0.15 (Google Vertex AI and 1 other, tied); for output alone, USD 1.20 (Google Vertex AI). Batch, flex, priority and fast tiers are shown in the table but not ranked.
Does Qwen sell Qwen3 Next 80B A3B Thinking on its own API?
Qwen publishes no price for Qwen3 Next 80B A3B Thinking on its own API that we could find, so there is no maker price to compare. The lowest-priced host we checked is Google Vertex AI at USD 0.15 / USD 1.20 per 1M tokens.
Does Qwen3 Next 80B A3B Thinking have cached input pricing?
None of the 2 standard prices includes a cached-input price, so budget repeated prompts at the full input price.
What is the Qwen3 Next 80B A3B Thinking context window?
262,144 tokens on every provider that states it.
How much does a coding agent cost per month on Qwen3 Next 80B A3B Thinking?
For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 378.00 a month at Google Vertex AI, USD 391.50 at the median price and USD 405.00 at GMI Cloud. Try your own numbers.
Is Qwen3 Next 80B A3B Thinking free to use through an API?
No provider in our data lists a free price for Qwen3 Next 80B A3B Thinking as of 2026-11-15. 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 Next 80B A3B Thinking open source, with open weights, and what is its licence?
Qwen publishes the weights on Hugging Face as Qwen/Qwen3-Next-80B-A3B-Thinking, 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 Next 80B A3B Thinking have?
Total parameters, as the Qwen model card states them: 80B. Active parameters per token: 3B. (checked 2026-11-16; BroadNet did not verify these figures.)
Does Qwen3 Next 80B A3B Thinking support tool calling?
Yes, according to the Qwen model card: “Qwen3 excels in tool calling capabilities.” (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.