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.

alibaba/qwen3-next-80b-a3b-instruct
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.

17 offers · USD per million tokens
ProviderModel IDContextOutputInput / output · 1MReasoningToolsStructuredDetails
Amazon Bedrock
qwen.qwen3-next-80b-a3b
262,144262,000$0.15 / $1.20NoYesYes
View
Deep Infra
Qwen/Qwen3-Next-80B-A3B-Instruct
262,14432,768$0.09 / $1.10NoYesYes
View
DevPass (LLM Gateway)
qwen3-next-80b-a3b-instruct
131,07232,768$0.15 / $1.20NoYes—
View
Eden AI
qwen/qwen3-next-80b-a3b-instruct
131,07232,768$0.15 / $1.20NoYesYes
View
Jalapeno Cloud
Qwen3-Next-80B-A3B-Instruct
129,02432,768$0.15 / $1.50NoYesYes
View
Kilo Gateway
qwen/qwen3-next-80b-a3b-instruct
262,144235,929$0.0975 / $0.78NoYesYes
View
LLM Gateway
novita/qwen3-next-80b-a3b-instruct
131,07232,768$0.15 / $1.50NoYesNo
View
LLM Gateway
vertex-openai/qwen3-next-80b-a3b-instruct
131,07232,768$0.15 / $1.20NoYesNo
View
Merge Gateway
qwen/qwen3-next-80b-a3b-instruct
131,07232,768$0.144 / $0.574NoYesYes
View
NanoGPT
qwen/qwen3-next-80b-a3b-instruct
262,14432,768$0.15 / $0.65NoYesYes
View
Neon
qwen3-next-80b-a3b-instruct
131,07210,000$0.15 / $1.20NoYesYes
View
Alibabavia OpenRouter
qwen/qwen3-next-80b-a3b-instruct
unknown
131,07232,768$0.0975 / $0.78NoYesNo
View
DeepInfravia OpenRouter
qwen/qwen3-next-80b-a3b-instruct
fp8
262,14416,384$0.09 / $1.10NoYesYes
View
Googlevia OpenRouter
qwen/qwen3-next-80b-a3b-instruct
unknown
262,144235,929$0.15 / $1.20NoYesYes
View
Novitavia OpenRouter
qwen/qwen3-next-80b-a3b-instruct
bf16
131,07232,768$0.15 / $1.50NoYesNo
View
Parasailvia OpenRouter
qwen/qwen3-next-80b-a3b-instruct
fp8
262,144235,929$0.10 / $1.10NoYesYes
View
Vercel AI Gateway
alibaba/qwen3-next-80b-a3b-instruct
262,114262,114$0.15 / $1.20NoYes—
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.

USD per million tokens
Input from$0.09Per 1M input tokens
Output from$0.574Per 1M output tokens
Available offers17Across 12 providers

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.

Endpoint price comparisonLatest observed snapshot · 5 lowest-priced configurations
InputOutput
DeepInfradeepinfra/fp8
$0.09$1.10
Alibabaalibaba
$0.0975$0.78
Parasailparasail/fp8
$0.10$1.10
Googlegoogle-vertex/global
$0.15$1.20
Novitanovita/bf16
$0.15$1.50
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
EndpointInput / 1MOutput / 1MCache read / 1MCache 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.

Latest 30-minute observation

Time to first token · milliseconds

Latency distributionRolling 30-minute snapshot · 5 endpoints
P50P75P90P99
Alibabaalibaba
445–1,488.04 ms
DeepInfradeepinfra/fp8
598–6,195.13 ms
Googlegoogle-vertex/global
471.5–1,438 ms
Novitanovita/bf16
846–11,719.24 ms
Parasailparasail/fp8
578–2,617.12 ms
All latency percentiles 5 endpoints
EndpointP50P75P90P99
Alibabaalibaba445 ms512 ms645 ms1,488.04 ms
DeepInfradeepinfra/fp8598 ms988 ms1,512.6 ms6,195.13 ms
Googlegoogle-vertex/global471.5 ms552 ms734.8 ms1,438 ms
Novitanovita/bf16846 ms1,502 ms4,869.4 ms11,719.24 ms
Parasailparasail/fp8578 ms949 ms1,489 ms2,617.12 ms

Output throughput · tokens per second

Throughput distributionRolling 30-minute snapshot · 5 endpoints
P50P75P90P99
Alibabaalibaba
85.5–107 t/s
DeepInfradeepinfra/fp8
147–312.56 t/s
Googlegoogle-vertex/global
112–352.4 t/s
Novitanovita/bf16
118–229.8 t/s
Parasailparasail/fp8
128.5–219.07 t/s
All throughput percentiles 5 endpoints
EndpointP50P75P90P99
Alibabaalibaba85.5 t/s92.75 t/s100 t/s107 t/s
DeepInfradeepinfra/fp8147 t/s202 t/s248.4 t/s312.56 t/s
Googlegoogle-vertex/global112 t/s129.5 t/s178 t/s352.4 t/s
Novitanovita/bf16118 t/s164 t/s182 t/s229.8 t/s
Parasailparasail/fp8128.5 t/s174.25 t/s198 t/s219.07 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.

Successful requests by window
Availability by endpointCurrent overlapping windows · 5 endpoints
Endpoint5 minutes30 minutes24 hours
Alibabaalibaba
DeepInfradeepinfra/fp8
Googlegoogle-vertex/global
Novitanovita/bf16
Parasailparasail/fp8

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.

External evaluations

Sources: Artificial Analysis and Design Arena, via OpenRouter. Scores retain their original scales and are not OpenAI Suite ratings.

Detailed evaluations

Evaluation scoresAccuracy or item F1 · higher is better
gpqa diamondQwen: Qwen3 Next 80B A3B Instruct
70.918%
tau bench verified airlineQwen: Qwen3 Next 80B A3B Instruct
46.963%
EvaluationConfigurationSourceResultsDetails
gpqa diamondQwen: Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct-2509OpenRouter70.918%
Details
tau bench verified airlineQwen: Qwen3 Next 80B A3B Instructqwen/qwen3-next-80b-a3b-instruct-2509OpenRouter46.963%
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.

Current route specifications
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
Base URLhttps://openrouter.ai/api/v1
Model IDqwen/qwen3-next-80b-a3b-instruct
Version IDqwen/qwen3-next-80b-a3b-instruct-2509
Weights IDQwen/Qwen3-Next-80B-A3B-Instruct

Supported parameters

  • frequency_penalty
  • logit_bias
  • logprobs
  • max_tokens
  • min_p
  • presence_penalty
  • repetition_penalty
  • response_format
  • seed
  • stop
  • structured_outputs
  • temperature
  • tool_choice
  • tools
  • top_k
  • top_logprobs
  • top_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