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. $0.09 per million input tokens, $1.10 per million output tokens. 262,144 token context window, maximum output of 16,384 tokens. Higher uptime with 6 providers. Includes independent benchmarks from Artificial Analysis.
- Input / output price
- $0.09 / $1.10 per 1M
- Context
- 262K tokens
- Released
- Sep 11, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
5 providers, cheapest first, OpenRouter last, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Concentrate concentrate/qwen3-next-80b-a3b | $0.09/M | $1.10/M |
DeepInfra deepinfra/qwen3-next-80b-a3b-instruct | $0.09/M | $1.10/M |
IO.net ionet/qwen3-next-80b-a3b-instruct | $0.09925/M | $1.1825/M |
Parasail parasail/qwen3-next-80b-a3b-instruct | $0.10/M | $1.10/M |
OpenRouter openrouter/qwen3-next-80b-a3b-instruct | $0.10/M | $1.10/M |
Is a provider down? OpenRouter status
Pricing
Averaged across 5 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $0.10 per 1M
- Average output
- $1.12 per 1M
- Average cache read
- $0.06 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better14tokens/sacross providers
Response latency
Lower is better1.1sacross providers
Benchmarks
16 published scores from 2 sources, each linked to where it was published.
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MultiPL-Ehuggingface.co | 87.8% | huggingface.co | Sep 11, 2025 |
| LiveCodeBench v6 (25.02-25.05)huggingface.co | 56.6% | huggingface.co | Sep 11, 2025 |
| Aider-Polyglothuggingface.co | 49.8% | huggingface.co | Sep 11, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| BFCL-v3huggingface.co | 70.3% | huggingface.co | Sep 11, 2025 |
| TAU2-Retailhuggingface.co | 57.3% | huggingface.co | Sep 11, 2025 |
| TAU2-Airlinehuggingface.co | 45.5% | huggingface.co | Sep 11, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveBench 20241125huggingface.co | 75.8% | huggingface.co | Sep 11, 2025 |
| GPQAhuggingface.co | 72.9% | huggingface.co | Sep 11, 2025 |
| SuperGPQAhuggingface.co | 58.8% | huggingface.co | Sep 11, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| AIME25huggingface.co | 69.5% | huggingface.co | Sep 11, 2025 |
| HMMT25huggingface.co | 54.1% | huggingface.co | Sep 11, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| MMLU-Reduxhuggingface.co | 90.9% | huggingface.co | Sep 11, 2025 |
| IFEvalhuggingface.co | 87.6% | huggingface.co | Sep 11, 2025 |
| MMLU-Prohuggingface.co | 80.6% | huggingface.co | Sep 11, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| Arena-Hard v2huggingface.co | 82.7% | huggingface.co | Sep 11, 2025 |
| LMArena EloLMArena | 1399 Elo · #126 of 191 | LMArena | Nov 19, 2026 |
Apps
Use Qwen3 Next 80B A3B Instruct in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Qwen3 Next 80B A3B Instruct FAQ
Short answers, built from the data on this page.
Qwen3 Next 80B A3B Instruct is a model from Qwen, released on Sep 11, 2025. Qwen3-Next-80B-A3B-Instruct is an instruction-tuned chat model in the Qwen3-Next series optimized for fast, stable responses without “thinking” traces. $0.09 per million input tokens, $1.10 per million output tokens. 262,144 token context window, maximum output of 16,384 tokens. Higher uptime with 6 providers. Includes independent benchmarks from Artificial Analysis.
On the Respan gateway, input starts at $0.09 per 1M tokens on Concentrate and DeepInfra, and output starts at $1.10 per 1M tokens on Concentrate, DeepInfra, Parasail, and 1 more, after gateway discounts. Averaged across its 5 providers, it costs $0.10 per 1M input tokens and $1.12 per 1M output tokens.
Qwen3 Next 80B A3B Instruct is available through 5 providers: Concentrate, DeepInfra, IO.net, Parasail, and OpenRouter.
Qwen3 Next 80B A3B Instruct accepts up to 262K tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "qwen3-next-80b-a3b-instruct". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Qwen3 Next 80B A3B Instruct has 16 published benchmark scores, including MultiPL-E 87.8%, BFCL-v3 70.3%, and LiveBench 20241125 75.8%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.