Qwen3 Next 80B A3B
qwen.qwen3-next-80b-a3bPricing
List prices at Amazon Bedrock, in US dollars per million tokens.
| Tier | Input / 1M | Output / 1M | |
|---|---|---|---|
| Standard | $0.15 | $1.20 | |
| Flex 53% off | $0.07 | $0.60 | 53% off |
| Priority 73% more | $0.26 | $2.10 | 73% more |
What it costs a month
At Amazon Bedrock 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
1 host serve Qwen3 Next 80B A3B. The comparison is on blended price, 3 parts input to 1 part output.
| Host | In / out per 1M | Model id | |
|---|---|---|---|
Amazon BedrockCloud qwen.qwen3-next-80b-a3b | $0.15 / $1.20 | qwen.qwen3-next-80b-a3b |
Show 6 more listings: regions, snapshots and variantsHide regional listings
| Amazon Bedrock | |||||||
| ap-southeast-2 qwen.qwen3-next-80b-a3b | $0.154 / $1.24 +3% vs headline | qwen.qwen3-next-80b-a3b | |||||
| ap-south-1 qwen.qwen3-next-80b-a3b | $0.18 / $1.41 +18% vs headline | qwen.qwen3-next-80b-a3b | |||||
| eu-west-1 qwen.qwen3-next-80b-a3b | $0.18 / $1.41 +18% vs headline | qwen.qwen3-next-80b-a3b | |||||
| ap-northeast-1 qwen.qwen3-next-80b-a3b | $0.18 / $1.45 +21% vs headline | qwen.qwen3-next-80b-a3b | |||||
| sa-east-1 qwen.qwen3-next-80b-a3b | $0.18 / $1.45 +21% vs headline | qwen.qwen3-next-80b-a3b | |||||
| eu-west-2 qwen.qwen3-next-80b-a3b | $0.23 / $1.86 +55% vs headline | qwen.qwen3-next-80b-a3b | |||||
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
- Features
- Native structured output
- Open weights
- License: Apache-2.0Runtimes: 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
No host sells it for less than Amazon Bedrock.
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
- 10% less
- 15% less
- 36% less
- 37% less
Call it
Using Amazon Bedrock's API.
from litellm import completion
response = completion(
model="bedrock/qwen.qwen3-next-80b-a3b",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Quick answers
How much does Qwen3 Next 80B A3B cost?
On Amazon Bedrock, Qwen3 Next 80B A3B costs $0.15 per million input tokens and $1.20 per million output tokens.
Which APIs offer Qwen3 Next 80B A3B?
Qwen3 Next 80B A3B runs on 1 API: Amazon Bedrock.
What is Qwen3 Next 80B A3B's context window?
256K tokens, with up to 8K tokens in one reply.
Is Qwen3 Next 80B A3B being retired?
No retirement date is scheduled for it on any API we track.
What are cheaper alternatives to Qwen3 Next 80B A3B?
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 Qwen3.5 397B A17B on AIHubMix (10% less). Savings are on a mix of 3 input tokens to 1 output token.
What is Qwen3 Next 80B A3B's API model id?
Use qwen.qwen3-next-80b-a3b with Amazon Bedrock.
Sources
Raw catalog entry for qwen.qwen3-next-80b-a3b on Amazon Bedrock
{
"input_cost_per_token": 1.5e-7,
"input_cost_per_token_flex": 7e-8,
"input_cost_per_token_priority": 2.6e-7,
"litellm_provider": "bedrock_converse",
"max_input_tokens": 256000,
"max_output_tokens": 8000,
"mode": "chat",
"output_cost_per_token": 0.0000012,
"output_cost_per_token_flex": 6e-7,
"output_cost_per_token_priority": 0.0000021,
"source": "https://pricing.us-east-1.amazonaws.com/offers/v1.0/aws/AmazonBedrock/current/index.json",
"supports_audio_input": false,
"supports_function_calling": true,
"supports_system_messages": true,
"supports_native_structured_output": true,
"supports_response_schema": true,
"supports_vision": false
}