All models
DeepSeek V3
DeepSeek
Claude 3.5 Sonnet Claude 3.7 Sonnet Claude 3.7 Sonnet (high output) Claude 3.7 Sonnet (thinking) Claude 3.5 Haiku Claude Opus o1 o3-mini o3-mini-high o1-mini

DeepSeek V3

The latest DeepSeek model hosted securely in the USA

Model Specifications

Context window 65,536 tokens
Max output 8,192 tokens
Knowledge cutoff February 2024
Multipart messages No
Vision capabilities No

Default Parameters

Temperature 0.3
Top P 1.0
Frequency penalty 0.0
Presence penalty 0.0
Top K 50
Try on Simtheory

Supported Parameters

Temperature

Supported

Controls randomness: Lower values make output more deterministic, higher values more creative.

Range: 0.0 - 1.0 Default: 0.3

More models from DeepSeek

DeepSeek V3 0324

DeepSeek V3 0324

DeepSeek's updated V3 model released on 03/24/2025 hosted securely in the USA

Context: 131,072 Output: 30,000
DeepSeek-R1

DeepSeek-R1

Deep reasoning model from DeepSeek hosted securely in the USA

Context: 131,072 Output: 8,192
DeepSeek-R1 (Groq)

DeepSeek-R1 (Groq)

The deep reasoning DeepSeek-R1 running on Groq

Context: 131,072 Output: 8,192