Qwen3 Next 80B A3B Thinking

DeepinfraText

Qwen3 Next 80B A3B Thinking is a text model from Deepinfra with a context window of 262K tokens and max output of 262K tokens. Pricing starts at $0.14 per million input tokens and $1.40 per million output tokens (cheapest at Deepinfra).

Specifications

Model Keydeepinfra/Qwen/Qwen3-Next-80B-A3B-Thinking
ProviderDeepinfra
LiteLLM Providerdeepinfra
ModeText
Canonical Nameqwen-next-3-80b
Context Window262K tokens
Max Output262K tokens

Capabilities

Vision Function Calling Reasoning JSON Schema System Messages Web Search Prompt Caching Audio Input Audio Output

Pricing

TypePer 1K TokensPer 1M Tokens
Input Tokens$0.000140$0.140
Output Tokens$0.0014$1.40

Price Comparison by Provider

Compare prices for Qwen3 Next 80B A3B Thinking across different providers. The same model may be available through multiple providers at different price points.

Provider
Model Key
Input Price
Output Price
AWS Bedrockqwen.qwen3-next-80b-a3b$0.150$1.20
Deepinfradeepinfra/Qwen/Qwen3-Next-80B-A3B-Instruct$0.140$1.40

Similar Models

Models with similar capabilities and context window size.

Model
Provider
Mode
Input Price
Output Price
Context
Max Output
Vision
Functions
Devstral 2512:freeOpenRouterTextN/AN/A262K262Knoyes
Mimo V2 FlashNovitaText$0.100$0.300262K32Knoyes
Mimo V2 FlashOpenRouterText$0.090$0.290262K16Knoyes
Qwen3 1p7b Fp8 DraftFireworks AIText$0.100$0.100262K262Knono
Qwen3 235B A22b 2507OpenRouterText$0.071$0.100262K262Knoyes
Qwen3 235B A22B Instruct 2507DeepinfraText$0.090$0.600262K262Knono
Qwen3 235B A22b Thinking 2507OpenRouterText$0.110$0.600262K262Knoyes
Qwen3 4B Instruct 2507 GGUFLemonadeTextN/AN/A262K33Knoyes
Qwen3 Coder 30B A3B Instruct GGUFLemonadeTextN/AN/A262K33Knoyes
Qwen3 Coder:480B CloudOllamaTextN/AN/A262K262Knoyes