ModelsDeepSeek R1
DeepSeek R1
by DeepSeek
Cost-effective
Best value for production workloads
Pricing
Input
$0.55
per 1M tokens
Output
$2.19
per 1M tokens
Cached
$0.14
per 1M tokens
Note: Released Jan 2025. Comparable to o1 at 3.6% of cost
Context & Output
Context Window128K tokens
Max Output32K tokens
Latency
Medium (reasoning)
Capabilities
Multimodal
Streaming
Function Calling
Prompt Caching
Key Strengths
What makes this model stand out
Reasoning model
27x cheaper than o1
MIT license
Similar Models in Cost-effective Tier
Other models with similar pricing and performance characteristics
Amazon Nova 2 Lite
Amazon
Input:TBD/M
Context:1M tokens
Amazon Nova 2 Sonic
Amazon
Input:TBD/M
Context:1M tokens
DeepSeek V3.1
DeepSeek
Input:$0.56/M
Context:128K tokens