Models

DeepSeek's reasoning-focused API endpoint with strong analytical performance and very aggressive token pricing.

Zhipu's latest GLM flagship with long context, strong coding ability, and open-weight plus API access.

Original GPT-5 release entry, now superseded by newer GPT-5.3 and GPT-5.4 generation variants.

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

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

Earlier GPT-5 Codex release entry, superseded by newer GPT-5.3-Codex in the current lineup.

Earlier GPT-5.2 generation entry retained as historical context after GPT-5.3 and GPT-5.4.

Earlier GPT-5 Codex variant retained as historical context after GPT-5.3-Codex.

Earlier premium GPT-5.2 tier retained as historical context after GPT-5.4-Pro.

Fast everyday GPT-5 tier tuned for general work, coding, and lower-cost production usage.

Latest Codex-tuned GPT-5 model for repository-scale implementation, review, and agent workflows.

Current high-capability GPT-5 tier for difficult professional tasks, coding, and longer agent workflows.

Highest-capability GPT-5 tier for decision-ready analysis and the most demanding professional workflows.

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

xAI's latest model with improved reasoning and coding capabilities, building on Grok 4 with enhanced tool use and real-time data integration.

Moonshot's Kimi K2.5 is an open-weight long-context model focused on agentic reasoning and tool use.

MiniMax's latest open-weight reasoning model with 200K+ context and strong coding, tool-use, and productivity benchmarks.

Mistral's open 24B model balancing strong instruction quality with low API cost for production assistants.

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

Cost-effective reasoning model retained as a legacy reference after retirement from ChatGPT defaults.

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

Alibaba's Qwen3.5 generation extends the Qwen line with stronger open-weight reasoning and coding performance.

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.

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

Anthropic's balanced Claude model — strong reasoning and coding at moderate pricing, the default recommendation for most tasks.

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

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

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

Google's current high-end Gemini preview model for multimodal reasoning, agentic workflows, and long-context analysis.

Long-context multimodal model retained as a legacy reference after retirement from ChatGPT defaults.

Widely deployed multimodal model kept as a legacy reference after retirement from ChatGPT defaults.

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

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.

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

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

xAI's API image-generation model ID for Grok Imagine workflows.

Google's current Imagen 4 image generation tier for API-backed visual creation and design workflows.

Google's lower-latency Imagen 4 tier for faster image generation in Gemini API workflows.

xAI's API video-generation model ID for Grok Imagine video workflows.

OpenAI's current Sora generation for cinematic text/image-to-video creation in product and API workflows.

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

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

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

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

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

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