Qwen3-Next 80B-A3B Instruct
Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. It targets complex tasks across reasoning, code generation, knowledge QA, and multilingual use, while remaining robust on alignment and formatting. Compared with prior Qwen3 instruct variants, it focuses on higher throughput and stability on ultra-long inputs and multi-turn dialogues, making it well-suited for RAG, tool use, and agentic workflows that require consistent final answers rather than visible chain-of-thought.
The model employs scaling-efficient training and decoding to improve parameter efficiency and inference speed, and has been validated on a broad set of public benchmarks where it reaches or approaches larger Qwen3 systems in several categories while outperforming earlier mid-sized baselines. It is best used as a general assistant, code helper, and long-context task solver in production settings where deterministic, instruction-following outputs are preferred.
- Organization
- Alibaba
- Family
- qwen
- Providers
- 12
- Context
- 131,072
- Output limit
- 32,768
- Knowledge
- 2025-04
- Release
- 2025-09
- Updated
- 2025-09
- Weights
- Open
- Input
- text
- Output
- text
- Capabilities
- Tools, Temperature
Providers
Compare every cataloged offer for this model, including its provider, route, token limits, price, and capabilities.
| Provider | Model ID | Context | Output | Input / output · 1M | Reasoning | Tools | Structured | Details |
|---|---|---|---|---|---|---|---|---|
| Amazon Bedrock | qwen.qwen3-next-80b-a3b | 262,144 | 262,000 | $0.15 / $1.20 | No | Yes | Yes | View |
| Deep Infra | Qwen/Qwen3-Next-80B-A3B-Instruct | 262,144 | 32,768 | $0.09 / $1.10 | No | Yes | Yes | View |
| DevPass (LLM Gateway) | qwen3-next-80b-a3b-instruct | 131,072 | 32,768 | $0.15 / $1.20 | No | Yes | — | View |
| Eden AI | qwen/qwen3-next-80b-a3b-instruct | 131,072 | 32,768 | $0.15 / $1.20 | No | Yes | Yes | View |
| Jalapeno Cloud | Qwen3-Next-80B-A3B-Instruct | 129,024 | 32,768 | $0.15 / $1.50 | No | Yes | Yes | View |
| Kilo Gateway | qwen/qwen3-next-80b-a3b-instruct | 262,144 | 235,929 | $0.0975 / $0.78 | No | Yes | Yes | View |
| LLM Gateway | novita/qwen3-next-80b-a3b-instruct | 131,072 | 32,768 | $0.15 / $1.50 | No | Yes | No | View |
| LLM Gateway | vertex-openai/qwen3-next-80b-a3b-instruct | 131,072 | 32,768 | $0.15 / $1.20 | No | Yes | No | View |
| Merge Gateway | qwen/qwen3-next-80b-a3b-instruct | 131,072 | 32,768 | $0.144 / $0.574 | No | Yes | Yes | View |
| NanoGPT | qwen/qwen3-next-80b-a3b-instruct | 262,144 | 32,768 | $0.15 / $0.65 | No | Yes | Yes | View |
| Neon | qwen3-next-80b-a3b-instruct | 131,072 | 10,000 | $0.15 / $1.20 | No | Yes | Yes | View |
| Alibabavia OpenRouter | qwen/qwen3-next-80b-a3b-instruct unknown | 131,072 | 32,768 | $0.0975 / $0.78 | No | Yes | No | View |
| DeepInfravia OpenRouter | qwen/qwen3-next-80b-a3b-instruct fp8 | 262,144 | 16,384 | $0.09 / $1.10 | No | Yes | Yes | View |
| Googlevia OpenRouter | qwen/qwen3-next-80b-a3b-instruct unknown | 262,144 | 235,929 | $0.15 / $1.20 | No | Yes | Yes | View |
| Novitavia OpenRouter | qwen/qwen3-next-80b-a3b-instruct bf16 | 131,072 | 32,768 | $0.15 / $1.50 | No | Yes | No | View |
| Parasailvia OpenRouter | qwen/qwen3-next-80b-a3b-instruct fp8 | 262,144 | 235,929 | $0.10 / $1.10 | No | Yes | Yes | View |
| Vercel AI Gateway | alibaba/qwen3-next-80b-a3b-instruct | 262,114 | 262,114 | $0.15 / $1.20 | No | Yes | — | View |
Prices and limits apply to each offer. A dash means the value is not provided. OpenRouter offers show the hosting provider and routing channel separately.
Pricing
Compare token rates and cache charges across available routes and hosting configurations.
Lowest listed input and output prices across the offers above; they may belong to different providers. These are base rates, before conditional pricing, discounts or additional fees.
qwen/qwen3-next-80b-a3b-instructObserved - Input
- $0.10
- Output
- $1.10
- Cache read
- $0.07
Hosting prices through OpenRouter All endpoints and cache rates
| Endpoint | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M |
|---|---|---|---|---|
| Alibabaalibaba | $0.0975 | $0.78 | — | — |
| DeepInfradeepinfra/fp8 | $0.09 | $1.10 | — | — |
| Googlegoogle-vertex/global | $0.15 | $1.20 | — | — |
| Novitanovita/bf16 | $0.15 | $1.50 | — | — |
| Parasailparasail/fp8 | $0.10 | $1.10 | $0.07 | — |
Each row is a hosting configuration. Open an offer in Providers for its full pricing conditions and additional fees. Endpoint observations may differ from the routing catalog's base price.
Performance
Review reported latency and output-throughput percentiles from the latest observed rolling window.
Time to first token · milliseconds
All latency percentiles 5 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Alibabaalibaba | 445 ms | 512 ms | 645 ms | 1,488.04 ms |
| DeepInfradeepinfra/fp8 | 598 ms | 988 ms | 1,512.6 ms | 6,195.13 ms |
| Googlegoogle-vertex/global | 471.5 ms | 552 ms | 734.8 ms | 1,438 ms |
| Novitanovita/bf16 | 846 ms | 1,502 ms | 4,869.4 ms | 11,719.24 ms |
| Parasailparasail/fp8 | 578 ms | 949 ms | 1,489 ms | 2,617.12 ms |
Output throughput · tokens per second
All throughput percentiles 5 endpoints
| Endpoint | P50 | P75 | P90 | P99 |
|---|---|---|---|---|
| Alibabaalibaba | 85.5 t/s | 92.75 t/s | 100 t/s | 107 t/s |
| DeepInfradeepinfra/fp8 | 147 t/s | 202 t/s | 248.4 t/s | 312.56 t/s |
| Googlegoogle-vertex/global | 112 t/s | 129.5 t/s | 178 t/s | 352.4 t/s |
| Novitanovita/bf16 | 118 t/s | 164 t/s | 182 t/s | 229.8 t/s |
| Parasailparasail/fp8 | 128.5 t/s | 174.25 t/s | 198 t/s | 219.07 t/s |
Percentiles describe the observed request distribution. These are snapshots of a rolling window, not a historical time series.
Uptime
Compare successful request rates across the latest 5-minute, 30-minute, and 24-hour observations.
Reported by OpenRouter at the time of collection; rate-limited requests are excluded. A dash means no measurement was reported. This is not a live availability check.
Benchmarks
Review attributed evaluation results on each source's original scale.
Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.
Detailed evaluations
| Evaluation | Configuration | Source | Results | Details |
|---|---|---|---|---|
| gpqa diamond | Qwen: Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct-2509 | OpenRouter | 70.918% | Details |
| tau bench verified airline | Qwen: Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct-2509 | OpenRouter | 46.963% | Details |
Sources: Artificial Analysis, Design Arena and OpenRouter. Evaluation configurations and scales differ; results are not interchangeable. Updated Oct 4, 2026.
Technical details & API
Explore specifications, supported parameters, reasoning controls, and API identifiers for each OpenRouter route.
qwen/qwen3-next-80b-a3b-instructObserved - Context
- 262,144
- Maximum output
- 235,929
- Tokenizer
- Qwen3
- Input
- text
- Output
- text
- Moderation
- No
- Knowledge cutoff
- 2025-09-30
- Added to OpenRouter
- 2025-09-11
https://openrouter.ai/api/v1qwen/qwen3-next-80b-a3b-instructqwen/qwen3-next-80b-a3b-instruct-2509Qwen/Qwen3-Next-80B-A3B-InstructSupported parameters
frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Frequently asked questions
Answers based on the model metadata and serving offers currently in the catalog.
How much does Qwen3-Next 80B-A3B Instruct cost?
Listed rates start at $0.09 per million input tokens and $0.574 per million output tokens. Prices vary by provider and configuration; see Pricing for details.
Which providers offer Qwen3-Next 80B-A3B Instruct?
There are 17 cataloged offers across 12 providers. Compare model IDs, prices and limits in Providers.
What is the context window?
The cataloged model context is 131,072 tokens. Each serving endpoint may apply a different limit.
Does it support tools and structured output?
Tool calling: Yes. Structured output: Not reported. Support can vary by endpoint.
Resources
Catalog history · 2 recorded revisions
Metadata observations since this model was first cataloged. These are not model release versions.
- ·
e4580475b148 - ·
62044faaca27