Alibaba Qwen: Qwen3 Next 80B A3B Instruct

Qwen3 Next 80B A3B Instruct is Alibaba Qwen's instruction-tuned chat model in the Qwen3-Next series, released 2025-09, designed for fast, stable responses without visible thinking traces. It targets complex reasoning, code generation, knowledge QA, and multilingual use, and reaches or approaches larger Qwen3 systems on several benchmarks. The model emphasizes higher throughput and stability on ultra-long inputs and multi-turn dialogues, suiting RAG, tool use, and agentic workflows that need consistent final answers.

Modalities
inTextoutText
Price / 1M
$0.45 / $1.80
Context
262K
Released
Sep 11, 2025
Knowledge cutoff
Sep 30, 2025

Channels

Every channel serves the same model, but they differ in price and stability. On each API key in the Platform, you pick a primary and a backup channel per vendor, and each billing line shows which channel served the request.

Provider
Discount
Input /M
Output /M
Cache read /M
Cache write 5m /M
Cache write 1h /M
Defaultstable
+89%
$0.45
$1.80
—
—
—

Context pricing

This model’s price depends on how much input context a request carries. The headline price is the cheapest band, and a longer prompt moves the whole request into a higher one.

Input context
Input /M
Output /M
standardBase
$0.45
$1.80

Capabilities

Tool useLong contextStructured output

Parameters

Request parameters this model accepts through the API.

frequency_penaltylogit_biaslogprobsmax_tokensmin_ppresence_penaltyrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p

Cost calculator

Pick a channel and a usage scenario, then drag the sliders to match your workload. Each scenario assumes a different prompt-cache hit rate.

Channel
Scenario
Unit $0.45 / $1.80 /1MDaily chat: 40% cache hit rate assumed · cache read $0.05 /1M
On MirAPI$114.05/ moCreate an API key

Benchmarks

bar = score (0–100) · ▏ median

Scores come from vendor reports and public leaderboards, not private evals.

Intelligence Index
General ability
9.6
#129
GPQA Diamond
Science QA
71.2
#95
τ-bench (airline)
Agentic tool use
47.0
#102

Showcase

Every chat model gets the same three fixed prompts. Outputs are archived verbatim, so you can copy a prompt and reproduce the result.

Task prompt · identical for all models
Build a single-file HTML page using three.js from a CDN: a low-poly planet with a tilted ring of ~200 orbiting particles, a soft key light plus rim light, slow auto-rotation, and drag-to-orbit controls. No build tools — one file only.
Archived output
Archive not published yet

Every model will run this exact prompt, and its output will appear here verbatim with token counts and the cost per run.

Quick start

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.mirapi.ai/v1",   # changed
    api_key=os.environ["MIRAPI_API_KEY"],   # changed
)

resp = client.chat.completions.create(
    model="qwen3-next-80b-a3b-instruct",
    messages=[{"role": "user", "content": "Hello"}],
)
Wire Qwen3 Next 80B A3B Instruct into your product

1M free tokens to start, no card required. It’s OpenAI-compatible, so you only change the base URL.

Start free