Models/Qwen3-Max-Thinking

Qwen3-Max-ThinkingActive · Cloud

DeepInfra · Released Feb 2026 · Apache-2.0

Qwen3-Max-Thinking is the flagship reasoning model in the Qwen3 series, designed for high-stakes cognitive tasks that require deep, multi-step reasoning. By significantly scaling model capacity and reinforcement learning compute, it...

Context
256K
Max output
0
Input
$1.20
Output
$6.00
Cached in
$0.24
Latency
-

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

Details

ProviderDeepInfra
ReleasedFeb 2026
LicenseApache-2.0
InputText
OutputText
Throughput-
Availability100%

Related models