All Models
Alibaba QwenactiveOpen Source
Qwen2.5-14B Instruct
qwen2.5-14b-instructWell-balanced 14B model for general-purpose tasks.
Context Window
131.1K
tokens
Max Output
8.2K
tokens
Input Price
$0.40
per 1M tokens
Output Price
$1.60
per 1M tokens
Details
Familyqwen2.5
Parameters14B
Training Cutoff2024-06-01
ReleasedSeptember 19, 2024
Capabilities
FunctionsStreamingJSON ModeCodeTool Use
Documentation
https://dashscope.aliyuncs.com/compatible-mode/v1/chat/completionsEvaluation Scores(3 benchmarks)
HumanEval
68.9%
MATH-500
57%
MMLU-Pro
52.4%
Quick Access
curl pikaainews.com/api/models/qwen-qwen2-5-14b-instructnpx pika-models info qwen-qwen2-5-14b-instructGet API Access
Third-Party Providers & Aggregators
Cerebras
Wafer-scale inference. 1000+ tokens/sec for select models.
DeepInfra
Lowest per-token rates for open-source models.
Fireworks AI
Fastest inference engine. Multimodal support, HIPAA/SOC2.
Groq
Ultra-fast LPU inference. Best latency for real-time apps.
OpenRouter
500+ models, one API key. Pay-per-token, no minimums.
SiliconFlow
China-optimized inference. Strong Qwen/DeepSeek support.
Together AI
Fast open-source model inference. Sub-100ms latency.