Question 1

What is Qwen3 Next 80B A3B Thinking?

Accepted Answer

Qwen3 Next 80B A3B Thinking is a model from Qwen, released on Sep 11, 2025. Qwen3-Next-80B-A3B-Thinking is a reasoning-first chat model in the Qwen3-Next line that outputs structured “thinking” traces by default. It’s designed for hard multi-step problems; math proofs, code synthesis/debugging, logic, and agentic planning, and reports strong results across knowledge, reasoning, coding, alignment, and multilingual evaluations. Compared with prior Qwen3 variants, it emphasizes stability under long chains of thought and efficient scaling during inference, and it is tuned to follow complex instructions while reducing repetitive or off-task behavior. The model is suitable for agent frameworks and tool use (function calling), retrieval-heavy workflows, and standardized benchmarking where step-by-step solutions are required. It supports long, detailed completions and leverages throughput-oriented techniques (e.g., multi-token prediction) for faster generation. Note that it operates in thinking-only mode.

Question 2

How much does Qwen3 Next 80B A3B Thinking cost?

Accepted Answer

On the Respan gateway, input starts at $0.15 per 1M tokens on every provider, and output starts at $1.20 per 1M tokens on OpenRouter and Tera, after gateway discounts. Averaged across 3 providers, it costs $0.15 per 1M input tokens and $1.30 per 1M output tokens.

Question 3

Which providers serve Qwen3 Next 80B A3B Thinking on Respan?

Accepted Answer

3 providers serve Qwen3 Next 80B A3B Thinking: OpenRouter, Tera, and TogetherAI. Tera and TogetherAI require your own provider API key (BYOK).

Question 4

What is Qwen3 Next 80B A3B Thinking's context window?

Accepted Answer

Qwen3 Next 80B A3B Thinking accepts up to 262K tokens of context on its largest provider route.

Question 5

How do I use Qwen3 Next 80B A3B Thinking with the Respan gateway?

Accepted Answer

Point any OpenAI-compatible SDK at https://api.respan.ai/api/ with your Respan API key and set the model to "qwen3-next-80b-a3b-thinking". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Question 6

How fast is Qwen3 Next 80B A3B Thinking?

Accepted Answer

Over the last 30 days of requests through the Respan gateway, the fastest provider was OpenRouter at 108 tokens per second, and the lowest response latency was 1.3 seconds on OpenRouter. Speed varies with request size and provider.

Question 7

How does Qwen3 Next 80B A3B Thinking score on benchmarks?

Accepted Answer

Qwen3 Next 80B A3B Thinking has 16 published benchmark scores, including LiveCodeBench v6 (25.02-25.05) 68.7%, BFCL-v3 72%, and GPQA 77.2%. Each score links to where it was published; the data is collected by llmmetric.com.

Provider	Context	Input	Output
OpenRouter`openrouter/qwen/qwen3-next-80b-a3b-thinking`	262K	$0.15/M	$1.20/M
TeraBYOK only`tera/Qwen/Qwen3-Next-80B-A3B-Thinking`	262K	$0.15/M	$1.20/M
TogetherAIBYOK only`together_ai/Qwen/Qwen3-Next-80B-A3B-Thinking`	262K	$0.15/M	$1.50/M

Qwen3 Next 80B A3B Thinking

Providers

Certified where it counts.

Pricing

Cost by volume

Throughput and latency

Output speed

Response latency

Benchmarks

Coding2

Agents4

Reasoning3

Math2

Knowledge3

Arena2

Apps