gpt-4o
by OpenAI · 128K context · 1,200 ms latency · quality 9.2
MultimodalReasoningVision
$5.00
per 1M tokens
Models
Available models
8 models
nemotron-ultra-550b
by NVIDIA · 128K context · 1,500 ms latency · quality 9.1
FoundationDynamoLocal
$2.40
per 1M tokens
claude-3.5-sonnet
by Anthropic · 200K context · 1,800 ms latency · quality 9
ReasoningLong context
$3.00
per 1M tokens
llama-3.1-70b
by Meta · 128K context · 2,300 ms latency · quality 8.7
Open SourceDedicatedOn-cluster
$0.80
per 1M tokens
deepseek-r1
by DeepSeek · 64K context · 3,200 ms latency · quality 8.4
ReasoningCoding
$0.70
per 1M tokens
qwen-2.5-72b
by Alibaba · 32K context · 2,500 ms latency · quality 8.1
GeneralCheap
$0.50
per 1M tokens
phi-3-medium
by Microsoft · 8K context · 2,000 ms latency · quality 7.8
EfficientFast
$0.40
per 1M tokens
stable-diffusion-3
by Stability AI · — context · 4,500 ms latency · quality 7.5
VisionImage
$0.30
per 1M tokens