All Models
DeepSeekactiveOpen Source
DeepSeek-R1-Distill-Llama-70B
deepseek-r1-distill-llama-70bR1 reasoning distilled into Llama 3.3 70B.
Context Window
131.1K
tokens
Max Output
8.2K
tokens
Input Price
—
per 1M tokens
Output Price
—
per 1M tokens
Details
Familydeepseek-r1
Parameters70B
Training Cutoff2024-12-01
ReleasedJanuary 20, 2025
Evaluation Scores(5 benchmarks)
MATH-500
84%
HumanEval
75%
MMLU-Pro
66.2%
GPQA Diamond
52.3%
Quick Access
curl pikaainews.com/api/models/deepseek-r1-distill-llama-70bnpx pika-models info deepseek-r1-distill-llama-70bGet 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.