Portkey
AI gateway with observability, guardrails, and fallbacks. Routes traffic across providers with cost and latency tracking.
AI gateway with observability, guardrails, and fallbacks. Routes traffic across providers with cost and latency tracking.
TypeScript toolkit for building AI-powered apps. Unified interface for text generation, streaming, and structured outputs across any provider.
Unified API for 200+ LLMs. Route requests to the best model for cost, speed, or capability with an OpenAI-compatible interface.
Google DeepMind flagship model with 1M token context, native multimodality, and deep reasoning capabilities.
Meta latest open-weights model. State-of-the-art among open models, available in 8B and 70B parameter variants.
Alibaba open-source model family with strong multilingual and coding performance. Ranges from 0.5B to 72B parameters.
The original Mistral open model. Outperforms Llama 2 13B on most benchmarks while being faster and more efficient.