GTE Qwen2

by Qwen

Specifications

Input
Output
Context window: 8K tokens
Released: Jan 2026

Performance

Speed: 1175 t/s
TTFT: —
Latency: —
Intelligence: —

Pricing

Input: €0.06
Output: €0.00

About this model

Qwen2-based text embedding model optimized for semantic similarity and retrieval tasks.

Technical specifications

Capabilities
Input modalities
Output modalities
Reasoning: No

See also

Kimi K2.5

by Moonshot

MiniMax M2.5

by MiniMax

DeepSeek V4 Flash

by Deepseek