Qwen3-Next 80B-A3B (Thinking)
Efficient Qwen thinking model for local reasoning, math, and coding agents
Price changes
Cheapest list input/output only. Rates move rarely, so this is an event log. Down means cheaper. Showing the 8 latest changes.
- ↑ higherOutput $0.78 → $1.40
- ↑ higherInput $0.0975 → $0.14
Sources
Same model, different sources. Our first-party rate is listed first, then router and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| LiteLLMcheapestQwen/Qwen3-Next-80B-A3B-Thinking | N/A | $0.14 | $1.40 | $0.014 | N/A |
| LiteLLMcheapestQwen3-Next-80B-A3B-Thinking | N/A | $0.14 | $1.40 | $0.014 | N/A |
| LiteLLMcheapestdeepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking | N/A | $0.14 | $1.40 | $0.014 | N/A |
| models.devqwen3-next-80b-a3b-thinking | Alibaba / Qwen | $0.144 | $1.43 | $0 | 131K |
| models.devqwen3-next-80b-a3b-thinking | Qiniu | $0.1449 | $1.45 | $0 | 131K |
| models.devqwen/qwen3-next-80b-a3b-thinking | NanoGPT | $0.15 | $0.65 | $0.075 | 256K |
| models.devqwen/qwen3-next-80b-a3b-thinking | Merge Gateway | $0.15 | $1.20 | $0 | 131K |
| models.devalibaba/qwen3-next-80b-a3b-thinking | Vercel AI Gateway | $0.15 | $1.20 | $0 | 262K |
| models.devqwen.qwen3-next-80b-a3b | Amazon Bedrock | $0.15 | $1.20 | $0 | 262K |
| models.devqwen/qwen3-next-80b-a3b-thinking | Jiekou.AI | $0.15 | $1.50 | $0 | 66K |
| models.devQwen3-Next-80B-A3B-Thinking | Jalapeno Cloud | $0.15 | $1.50 | $0 | 262K |
| LiteLLMqwen3-next-80b-a3b-thinking | N/A | $0.15 | $1.20 | $0.015 | N/A |
| LiteLLMqwen.qwen3-next-80b-a3b | N/A | $0.15 | $1.20 | $0.015 | N/A |
| LiteLLMdashscope/qwen3-next-80b-a3b-thinking | N/A | $0.15 | $1.20 | $0.015 | N/A |
| LiteLLMnebius/Qwen/Qwen3-Next-80B-A3B-Thinking | N/A | $0.15 | $1.20 | $0.015 | N/A |
| LiteLLMqwen3-next-80b-a3b | N/A | $0.15 | $1.20 | $0.015 | N/A |
| LiteLLMqwen_ai_platform/qwen3-next-80b-a3b-thinking | N/A | $0.15 | $1.20 | $0.015 | N/A |
| LiteLLMqwencloud/qwen3-next-80b-a3b-thinking | N/A | $0.15 | $1.20 | $0.015 | N/A |
| LiteLLMqwen/qwen3-next-80b-a3b-thinking | N/A | $0.15 | $1.50 | $0.015 | N/A |
| LiteLLMnovita/qwen/qwen3-next-80b-a3b-thinking | N/A | $0.15 | $1.50 | $0.015 | N/A |
| LiteLLMtogether_ai/Qwen/Qwen3-Next-80B-A3B-Thinking | N/A | $0.15 | $1.50 | $0.015 | N/A |
| LiteLLMap-southeast-2/qwen.qwen3-next-80b-a3b | N/A | $0.1545 | $1.24 | $0.0155 | N/A |
| LiteLLMbedrock/ap-southeast-2/qwen.qwen3-next-80b-a3b | N/A | $0.1545 | $1.24 | $0.0155 | N/A |
| LiteLLMap-south-1/qwen.qwen3-next-80b-a3b | N/A | $0.18 | $1.41 | $0.018 | N/A |
| LiteLLMbedrock/ap-south-1/qwen.qwen3-next-80b-a3b | N/A | $0.18 | $1.41 | $0.018 | N/A |
| LiteLLMeu-west-1/qwen.qwen3-next-80b-a3b | N/A | $0.18 | $1.41 | $0.018 | N/A |
| LiteLLMap-northeast-1/qwen.qwen3-next-80b-a3b | N/A | $0.18 | $1.45 | $0.018 | N/A |
| LiteLLMbedrock/ap-northeast-1/qwen.qwen3-next-80b-a3b | N/A | $0.18 | $1.45 | $0.018 | N/A |
| LiteLLMsa-east-1/qwen.qwen3-next-80b-a3b | N/A | $0.18 | $1.45 | $0.018 | N/A |
| LiteLLMbedrock/eu-west-2/qwen.qwen3-next-80b-a3b | N/A | $0.23 | $1.86 | $0.023 | N/A |
| LiteLLMeu-west-2/qwen.qwen3-next-80b-a3b | N/A | $0.23 | $1.86 | $0.023 | N/A |
| models.devqwen3-next-80b-a3b-thinking | Alibaba / Qwen | $0.5 | $6 | $0 | 131K |
| LiteLLMaccounts/fireworks/models/qwen3-next-80b-a3b-thinking | N/A | $0.9 | $0.9 | $0.09 | N/A |
| LiteLLMfireworks_ai/accounts/fireworks/models/qwen3-next-80b-a3b-thinking | N/A | $0.9 | $0.9 | $0.09 | N/A |
Capabilities
- Reasoning
- Tool calling
- Structured output
- Open weights
- In: text
- Out: text
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Hover or tap the i next to any score for its source. Full boards on /benchmarks.
- AA intelligence11.2i
- AA coding17.4i
- AA agentic0i
Arena rows are community-vote Elo from Arena AI, Artificial Analysis indices arrive via OpenRouter, and launch-eval figures are collected from vendor announcements, analyst writeups, and community benchmarks. Full boards and credits on /benchmarks.
See what this model costs you
The app reads the sessions your tools already wrote and prices this model's tokens at the published API rate. Free on your computer.