Qwen3 Next 80B A3B Instruct
by Alibaba (Qwen) · qwen/qwen3-next-80b-a3b-instruct · #92 cheapest of 325 paid models
Prices updated Jul 22, 2026, 2:19 AM UTC · refreshed hourly
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...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5GPT-5.6 Sol
Pricing
Input
$0.10
per 1M tokens
Output
$1.10
per 1M tokens
Blended (3:1)
$0.35
3 input : 1 output
Cache read
$0.07
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for Qwen3 Next 80B A3B Instruct with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $0.35 | $0.0113 | — |
| 50% | $0.339 | $0.0098 | −13% |
| 90% | $0.33 | $0.0086 | −24% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates (available for OpenAI / Anthropic / Google — not flagged for this creator). Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.00038 | $0.38 |
| Document summary | 8,000 | 1,000 | $0.0019 | $1.90 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0052 | $5.20 |
| Long-context analysis | 150,000 | 5,000 | $0.0205 | $20.50 |
Performance
Intelligence Index
13.7
AA composite quality
Coding Index
—
Math Index
66.3
Agentic Index
—
Output speed
190 tok/s
median
Time to first token
1.02s
median
Time to first answer
1.02s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| MMLU-Pro | 81.9% |
| GPQA Diamond | 73.8% |
| Humanity's Last Exam | 7.3% |
| LiveCodeBench | 68.4% |
| SciCode | 30.7% |
| AIME 2025 | 66.3% |
| IFBench | 39.7% |
| AA-LCR (Long Context Reasoning) | 51.3% |
| Terminal-Bench Hard | 7.6% |
| τ²-Bench (Telecom) | 21.6% |
Specs
Context window
262K
tokens
Max output
262K
tokens
Input modalities
text
Tokenizer
Qwen3