Browse every model. Filter to yours.

Smaller, cheaper Realtime voice model for high-volume voice agents.

Anthropic's most capable model. Best-in-class for agentic coding and tool use.

Fast, low-cost model with frontier-level coding for its tier.

Balanced flagship: strong coding and agent performance at much lower cost than Opus.

Speech-to-speech model for low-latency voice agents. Native audio understanding and generation over the Realtime API.

Open MoE with hybrid thinking/non-thinking modes. Excellent price-to-performance.

OpenAI's flagship multimodal reasoning model with adaptive thinking depth.

Smaller, cheaper GPT-5 with most of the reasoning quality.

Ultra-fast, ultra-cheap GPT-5 variant for high-volume tasks.

Cheapest Gemini for high-volume classification, extraction, and translation.

Reasoning-first model with native tool use and real-time X search integration.

Top-tier multimodal model with very long context and native audio/video understanding.

Fast, cheap multimodal workhorse with controllable thinking budget.

Real-time speech-in / speech-out conversational model powering Gemini Live. Native audio with affective dialog and tool use.

Deliberate reasoning model that thinks before answering. Strong at math and science.

Open-weights mixture-of-experts multimodal model. 17B active / 400B total params.

Smaller open MoE (17B active / 109B total) with up to 10M-token context.

Enterprise-focused model optimized for RAG, tool use, and private deployment.

Flagship dense 123B model. Strong multilingual and code performance.