All Models
DeepSeekactiveOpen Source
DeepSeek-V3.2
deepseek-v3.2Latest DeepSeek V3 with native multimodal support, image understanding, and enhanced reasoning.
Context Window
131.1K
tokens
Max Output
16.4K
tokens
Input Price
$0.27
per 1M tokens
Output Price
$1.10
per 1M tokens
Details
Familydeepseek-v3
Parameters685B MoE
Training Cutoff2025-12-01
ReleasedFebruary 24, 2026
Capabilities
VisionFunctionsStreamingJSON ModeCodeReasoningTool UseMultimodal
Documentation
https://api.deepseek.com/chat/completionsEvaluation Scores(5 benchmarks)
HumanEval
86.7%
MATH-500
85.2%
MMLU-Pro
79.4%
GPQA Diamond
56.8%
SWE-bench Verified
42%
Quick Access
curl pikaainews.com/api/models/deepseek-v3-2npx pika-models info deepseek-v3-2Get 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.