All Models
DeepSeekactiveOpen Source
DeepSeek-R1
deepseek-r1Reasoning-focused model with chain-of-thought capabilities.
Context Window
131.1K
tokens
Max Output
8.2K
tokens
Input Price
$0.55
per 1M tokens
Output Price
$2.19
per 1M tokens
Details
Familydeepseek-r1
Parameters671B MoE
Training Cutoff2025-01-01
ReleasedJanuary 20, 2025
Evaluation Scores(6 benchmarks)
MATH-500
94.3%
HumanEval
85.5%
MMLU-Pro
79%
GPQA Diamond
65.6%
SWE-bench Verified
49.2%
Quick Access
curl pikaainews.com/api/models/deepseek-r1npx pika-models info deepseek-r1Get 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.