Models

Fast and efficient Claude tier for latency-sensitive assistant and automation workloads.

Anthropic's flagship Claude model for high-difficulty reasoning, coding, and long-running agent workflows.

DeepSeek's reasoning-focused API model offering strong analytical performance at highly competitive token pricing.

Balanced Claude tier for production reasoning, coding, and long-context assistant workflows.

Expressive voice model generation tier from ElevenLabs for high-quality speech output workflows.

Budget-oriented Gemini tier for large-scale assistant and automation workloads.

Fast Gemini tier balancing multimodal capability, latency, and cost for production assistants.

Google's high-end Gemini preview model with very large context and strong multimodal reasoning.

High-capability Gemini tier for long-context multimodal reasoning and advanced enterprise workflows.

Balanced multimodal model tier for long-context enterprise workflows and broad production use.

Lower-cost OpenAI speech-to-text tier for high-volume transcription pipelines.

OpenAI text-to-speech model for responsive, API-first voice output workflows.

Lower-cost GPT-4o tier for high-volume multimodal assistant and automation workloads.

OpenAI speech-to-text model tier for production transcription and voice pipeline workflows.

Cost-efficient GPT-5 variant for high-volume production workflows needing strong reasoning at lower cost.

OpenAI's general-purpose flagship model balancing frontier reasoning, coding strength, and production-ready cost-performance.

Production-grade multimodal model balancing quality, speed, and broad API usability.

Ultra-low-cost GPT-5 tier for high-throughput automation and lightweight reasoning tasks.

OpenAI's GPT-5 variant tuned for high-reliability coding, code review, and software engineering workflows.

OpenAI image generation model for prompt-driven creation and iterative editing workflows.

Google image generation model family for high-quality visual creation and iterative design workflows.

xAI's flagship Grok model focused on frontier reasoning, long context, and tool-oriented assistant workflows.

Open-weights Llama 4 tier for teams needing customization, control, and self-hosting flexibility.

Efficiency-focused Llama 4 tier for customizable deployments with tighter compute budgets.

Google's music generation model tier for creative audio and soundtrack ideation workflows.

Mistral's flagship European multimodal model with long context and competitive enterprise API economics.

Cost-effective reasoning model for teams needing stronger analysis than baseline tiers at lower cost.

Alibaba's top Qwen API model for high-end multilingual reasoning, coding, and enterprise assistant workloads.

Google's advanced video generation model used in Flow and related creative AI workflows.

High-reasoning model optimized for difficult analysis, planning, and reliability-critical decisions.