This model was retired on 2026-04-02. The pricing below is the last-known rate, kept for migration reference.

Qwen3 Next 80B A3B InstructDeprecated

AlibabaKnowledgeApr 2025
Tool useReasoningStructured output
Context
262K
Max output
262K
Serving providers
6
Cheapest input
$0.09 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Speed & latency
Output speed
182 t/s
tokens / second
Time to first token
2.14s
latency
Headline indices
Intelligence Index
13.8
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%default
EvalComputeProxy0.7default
GPQA Diamond74%default
Humanity's Last Exam8%default
IFBench40%default
LiveCodeBench68%default
Long-Context Reasoning52%default
MMLU-Pro82%default
Omniscience-59.5default
Omniscience Accuracy0.2default
Omniscience Non Hallucination0.1default
SciCode31%default
TerminalBench Hard8%default
τ²-bench22%default

Pricing by serving provider

last-known · per 1M tokens · click a provider to expand
Serving providerInput /1MOutput /1MEndpoints
DeepInfra$0.09$1.101
OpenRouter$0.10$1.101
Dashscope$0.15$1.201
Together AI$0.15$1.501
Novita$0.15$1.501
Fireworks AI$0.90$0.901

Price history

input + output $/1M since we started tracking
Input Output
Input down 36% since first tracked
$0.000$0.500$1.00$1.50Sep 26Jun 22Jul 25Aug 28$0.900$0.090

Cost calculator

estimate your monthly spend on this model
$106
estimated / month

Model IDs

copy the exact identifier for your platform
deepinfra/Qwen/Qwen3-Next-80B-A3B-Instructqwen/qwen3-next-80b-a3b-instructdashscope/qwen3-next-80b-a3b-instructtogether_ai/Qwen/Qwen3-Next-80B-A3B-Instructnovita/qwen/qwen3-next-80b-a3b-instructfireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-instruct

Frequently asked questions

Qwen3 Next 80B A3B Instruct pricing, context and availability

Is Qwen3 Next 80B A3B Instruct still available?

Qwen3 Next 80B A3B Instruct was retired on 2026-04-02. The pricing on this page is the last-known rate, kept for migration reference.

How much did Qwen3 Next 80B A3B Instruct cost?

Qwen3 Next 80B A3B Instruct's last-known pricing, before it was retired on 2026-04-02, was $0.09 per 1M input tokens and $0.90 per 1M output tokens.

What was the context window of Qwen3 Next 80B A3B Instruct?

Qwen3 Next 80B A3B Instruct had a 262K token context window and could return up to 262K output tokens.

What could Qwen3 Next 80B A3B Instruct do?

Qwen3 Next 80B A3B Instruct supported tool use, reasoning and structured output.

Other Alibaba models

compare pricing across the Alibaba lineup
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI