A new generation of Qwen3-based open-source thinking mode models. This version offers improved instruction following and streamlined summary responses over the previous iteration (Qwen3-235B-A22B-Thinking-2507).
A new generation of Qwen3-based open-source thinking mode models. This version offers improved instruction following and streamlined summary responses over the previous iteration (Qwen3-235B-A22B-Thinking-2507).
Qwen3 Next 80B Thinking is an AI model from Qwen, available on ZeroTwo. It costs $0.15 per million input tokens and $1.20 per million output tokens, has a 131,072-token context window, can return up to 32,768 output tokens, and has a knowledge cutoff of Mid-2025.
Intelligence
Fair
Speed
Medium
Price
$0.15 • $1.20
Input • Output
Input
Text
Output
Text
A new generation of Qwen3-based open-source thinking mode models. This version offers improved instruction following and streamlined summary responses over the previous iteration (Qwen3-235B-A22B-Thinking-2507).
131,072 context window
32,768 max output tokens
Mid-2025 knowledge cutoff
Reasoning token support
Pricing
Pricing is based on the number of tokens used. For tool-specific models, like search and computer use, there's a fee per tool call. See details in the pricing page.
Text tokens
Per 1M tokens
∙
Batch API price
Input
$0.15
Cached input
Output
$1.20
Quick comparison
Input
Cached input
Output
Qwen3 Next 80B Thinking
$0.15
Modalities
Text
Input and output
Image
Not supported
Audio
Not supported
Endpoints
Chat Completions
v1/chat/completions
Responses
v1/responses
Batch
v1/batch
Realtime
v1/realtime
Assistants
v1/assistants
Fine-tuning
v1/fine-tuning
Embeddings
v1/embeddings
Image Generation
v1/images/generations
Image Edit
v1/images/edits
Speech Generation
v1/audio/speech
Transcription
v1/audio/transcriptions
Translation
v1/translations
Moderation
v1/moderations
Completions (legacy)
v1/completions
Features
Streaming
Supported
Function calling
Supported
Structured outputs
Not supported
Fine-tuning
Not supported
Distillation
Not supported
Fast response
Not supported
Cost efficient
Not supported
Tools
Tools supported by this model when using the Responses API.
Web search
Not supported
Code interpreter
Not supported
File search
Not supported
Image generation
Not supported
MCP
Not supported
Snapshots
Snapshots let you lock in a specific version of the model so that performance and behavior remain consistent. Below is a list of all available snapshots and aliases for Qwen3 Next 80B Thinking.
qwen3-next-80b-a3b-thinking
Questions
How much does Qwen3 Next 80B Thinking cost?
Qwen3 Next 80B Thinking is priced at $0.15 per million input tokens and $1.20 per million output tokens. On ZeroTwo it is included in your plan's credits rather than billed per token.
What is Qwen3 Next 80B Thinking's context window?
Qwen3 Next 80B Thinking accepts up to 131,072 tokens of context and can return up to 32,768 output tokens.
What is Qwen3 Next 80B Thinking's knowledge cutoff date?
Qwen3 Next 80B Thinking has a training knowledge cutoff of Mid-2025. For anything later than that, use a model with web search enabled.
Can I use Qwen3 Next 80B Thinking for free?
You can try Qwen3 Next 80B Thinking on ZeroTwo's free plan, which includes a monthly credit allowance across every model in the catalogue. Heavier use moves to a paid plan rather than a per-token bill.