Model Catalog
Every model. One meter.
Explore and compare 1,600+ AI models from all major providers. Find the perfect model for your use case.
17 models found
| Model | Provider | Context | Latency | Input /1M | Output /1M | |
|---|---|---|---|---|---|---|
GPT-4o Most advanced multimodal model with vision, audio, and text capabilities. Excellent for complex reasoning tasks. | OpenAI | 128K | ~800ms | $2.5 | $10 | |
GPT-4o Mini Affordable and fast multimodal model suitable for lightweight tasks and high-volume applications. | OpenAI | 128K | ~400ms | $0.15 | $0.6 | |
Claude Opus 4 Most capable reasoning model from Anthropic. Excels at complex analysis, coding, and creative tasks. | Anthropic | 200K | ~1200ms | $15 | $75 | |
Claude Sonnet 4 Best balance of performance and cost. Ideal for production workloads requiring strong reasoning. | Anthropic | 200K | ~600ms | $3 | $15 | |
Gemini 2.0 Pro Google's most capable model with strong multimodal understanding and long context support. | 2M | ~700ms | $1.25 | $5 | ||
Gemini 2.0 Flash Fast and efficient model optimized for high-throughput applications with competitive performance. | 1M | ~300ms | $0.075 | $0.3 | ||
DeepSeek R1 Advanced reasoning model with chain-of-thought capabilities. Strong performance on math and coding benchmarks. | DeepSeek | 64K | ~900ms | $0.55 | $2.19 | |
Qwen 2.5 Max Alibaba's flagship model with strong multilingual support and competitive performance across benchmarks. | Alibaba | 128K | ~600ms | $0.8 | $3.2 | |
Mistral Large Flagship model from Mistral AI with excellent reasoning and multilingual capabilities. | Mistral | 128K | ~500ms | $2 | $6 | |
Llama 3.3 70B Open-source model with strong performance across general tasks. Available through multiple providers. | Meta | 128K | ~450ms | $0.4 | $0.4 | |
Claude Sonnet 4 (Bedrock) Claude Sonnet 4 hosted on AWS Bedrock. Enterprise-grade with VPC integration, IAM auth, and no data leaving your AWS account. | AWS Bedrock | 200K | ~650ms | $3 | $15 | |
Llama 3.1 70B (Bedrock) Meta Llama 3.1 70B on AWS Bedrock. Run open-source models with enterprise security and compliance on AWS infrastructure. | AWS Bedrock | 128K | ~500ms | $0.72 | $0.72 | |
Amazon Titan Text Premier Amazon's flagship text model optimized for enterprise use cases with built-in responsible AI features. | AWS Bedrock | 32K | ~400ms | $0.5 | $1.5 | |
GPT-4o (Azure) GPT-4o deployed on Azure OpenAI Service. Enterprise-ready with Azure AD integration, private endpoints, and regional data residency. | Azure | 128K | ~800ms | $2.5 | $10 | |
GPT-4o Mini (Azure) GPT-4o Mini on Azure OpenAI Service. Cost-effective option with enterprise security and compliance features. | Azure | 128K | ~400ms | $0.15 | $0.6 | |
Text Embedding 3 Large High-quality text embedding model for semantic search, clustering, and classification tasks. | OpenAI | 8K | ~200ms | $0.13 | — | |
DALL-E 3 State-of-the-art image generation model capable of creating highly detailed and accurate images from text prompts. | OpenAI | 4K | ~5000ms | $40 | — |