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.
qwen3-next-80b-a3b-instructReleased 11 Sep 2025 (Sep 2025)Pricing
List prices at Alibaba DashScope, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.15 | $1.20 |
What it costs a month
At Alibaba DashScope list prices, 30 days.
- Chat assistant5,000 requests a day, 2K in / 0.5K out$135
- RAG over documents2,000 requests a day, 8K in / 0.6K out$115
- Coding agent1,000 requests a day, 40K in / 2K out$252
- Overnight batch20,000 requests a day, 4K in / 0.4K out$648
Where to run it
11 hosts serve Qwen3 Next 80B A3B Instruct. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Alibaba DashScopeLab API qwen3-next-80b-a3b-instruct | $0.15 / $1.20 | qwen3-next-80b-a3b-instruct | |
Qianwen AI PlatformLab API qwen3-next-80b-a3b-instruct | $0.15 / $1.20 | qwen3-next-80b-a3b-instruct | |
Qwen CloudLab API qwen3-next-80b-a3b-instruct | $0.15 / $1.20 | qwen3-next-80b-a3b-instruct | |
DeepInfraInference Qwen3-Next-80B-A3B-Instruct | $0.09 / $1.10 −17% vs headline | Qwen3-Next-80B-A3B-Instruct | |
| $0.14 / $1.20 −2% vs headline | qwen.qwen3-next-80b-a3b-instruct | ||
Vertex AICloud qwen3-next-80b-a3b-instruct-maas | $0.15 / $1.20 | qwen3-next-80b-a3b-instruct-maas | |
DatabricksCloud databricks-qwen3-next-80b-a3b-instruct | $0.15 / $1.20 | databricks-qwen3-next-80b-a3b-instruct | |
GMI CloudInference Qwen3-Next-80B-A3B-Instruct | $0.15 / $1.50 +18% vs headline | Qwen3-Next-80B-A3B-Instruct | |
Together AIInference Qwen3-Next-80B-A3B-Instruct | $0.15 / $1.50 +18% vs headline | Qwen3-Next-80B-A3B-Instruct | |
Novita AIInference qwen3-next-80b-a3b-instruct | $0.15 / $1.50 +18% vs headline | qwen3-next-80b-a3b-instruct | |
Fireworks AIInference qwen3-next-80b-a3b-instruct | $0.90 / $0.90 +118% vs headline | qwen3-next-80b-a3b-instruct |
Capabilities
Core
- Streaming
- Function calling
- JSON mode
- Structured outputs
Multimodal
- Vision
- Image input
- Audio
- Image generation
- Video
Advanced
- Reasoning
- Tool calling
- MCP
- Prompt caching
- Batch API
- Embeddings
- Takes in
- Text
- Produces
- Text
- Open weights
- License: Apache-2.0Runs in about 195.2 GB of GPU memoryRuntimes: Ollama, SGLang, llama.cpp, vLLM
Cheaper alternatives
Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.
Same model, cheaper host
- DeepInfra17% lessQwen3-Next-80B-A3B-Instruct$0.09 / $1.10
- Amazon Bedrock2% lessMantle$0.14 / $1.20
Smaller Alibaba Qwen models
No cheaper Alibaba Qwen model keeps its key capabilities.
Other frontier labs
- 52% less
- 52% less
- 36% less
Open-weight picks
- 5% less
- 10% less
- 15% less
- 36% less
Call it
Using Alibaba DashScope's API.
from litellm import completion
response = completion(
model="dashscope/qwen3-next-80b-a3b-instruct",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Qwen3 Next 80B A3B Instruct cost?
On Alibaba DashScope, Qwen3 Next 80B A3B Instruct costs $0.15 per million input tokens and $1.20 per million output tokens. The cheapest host is DeepInfra, at $0.09 per million input tokens and $1.10 per million output tokens.
Which APIs offer Qwen3 Next 80B A3B Instruct?
Qwen3 Next 80B A3B Instruct runs on 11 APIs: Alibaba DashScope, Qianwen AI Platform, Qwen Cloud, DeepInfra, Amazon Bedrock, Vertex AI, Databricks, GMI Cloud, Together AI and 2 more.
What is Qwen3 Next 80B A3B Instruct's context window?
262K tokens, with up to 66K tokens in one reply.
Is Qwen3 Next 80B A3B Instruct being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Qwen3 Next 80B A3B Instruct?
Models that cost less and keep most of what it can do: Claude Haiku 5.5 on Anthropic (52% less), GPT-6 Luna on OpenAI (52% less) and MiniMax M3 on EmpirioLabs AI (5% less). Qwen3 Next 80B A3B Instruct itself costs 17% less on DeepInfra. Savings are on a mix of 3 input tokens to 1 output token.
When was Qwen3 Next 80B A3B Instruct released?
Alibaba Qwen released it on 11 Sep 2025.
What is Qwen3 Next 80B A3B Instruct's API model id?
Use qwen3-next-80b-a3b-instruct with Alibaba DashScope. Other hosts use their own ids: Qwen3-Next-80B-A3B-Instruct on DeepInfra, qwen.qwen3-next-80b-a3b-instruct on Amazon Bedrock, qwen3-next-80b-a3b-instruct-maas on Vertex AI, databricks-qwen3-next-80b-a3b-instruct on Databricks.
Sources
- DeepInfra pricing
- GMI Cloud pricing
- Together AI pricing
- Databricks pricing
- Amazon Bedrock pricing
- Alibaba DashScope pricing
- Qianwen AI Platform pricing
- Qwen Cloud pricing
- Vertex AI pricing
- LiteLLM model map
Raw catalog entry for qwen3-next-80b-a3b-instruct on Alibaba DashScope
{
"input_cost_per_token": 1.5e-7,
"litellm_provider": "dashscope",
"max_input_tokens": 262144,
"max_output_tokens": 65536,
"mode": "chat",
"output_cost_per_token": 0.0000012,
"source": "https://www.alibabacloud.com/help/en/model-studio/model-pricing",
"supports_function_calling": true,
"supports_tool_choice": true
}