AI Model Directory
Structured facts, compatibility notes, source freshness, and programmatic SEO fields.
Claude Haiku 3.5
Anthropic Claude model entry for fast, efficient, and targeted API workloads.
Claude Opus 4.7
Anthropic flagship Claude Opus 4.7 entry for advanced reasoning, adaptive thinking, agent teams, and complex planning.
Claude Sonnet 4.6
Anthropic Claude Sonnet 4.6 model for balanced intelligence, coding, writing, and complex task orchestration with 1M-token context.
DeepSeek V4 (Pro-Max / Flash-Max)
DeepSeek V4-series models including V4-Pro-Max and V4-Flash-Max for coding, reasoning, and agent workflows with competitive pricing.
DeepSeek-V3.2
DeepSeek-V3.2 reasoning model for math, coding, and tool-use workflows with cost-efficient pricing and OpenAI-compatible API.
Devstral 2
Mistral coding-agent model entry for software engineering tasks, coding workflows, and agentic development evaluation.
Gemini 2.5 Flash
Google Gemini model entry for low-latency, high-volume, multimodal, and agentic workloads.
Gemini 3.1 Pro
Google Gemini 3.1 Pro model for multimodal reasoning, breakthrough pattern recognition, Google ecosystem workflows, and search-grounded tasks with 1M-token context.
Gemini 3.5 Flash
Google Gemini 3.5 Flash lightweight model for low-latency generation, multimodal tasks, and cost-efficient Google ecosystem workflows.
Gemini Pro
Model entry for multimodal work, search grounding, and Google ecosystem integration, used for scenario-based recommendations.
GPT-5.5
OpenAI flagship GPT-5.5 model for coding, agentic tasks, reasoning workflows, and Responses API integrations with 400K-token context.
GPT-5.5 Codex
OpenAI coding-specialized GPT-5.5 Codex model for long-horizon agentic coding tasks, repository edits, and test generation.
gpt-oss-120b
OpenAI open-weight model entry for high-reasoning, agentic, and self-hosted deployment evaluation.
gpt-oss-20b
OpenAI open-weight model entry for lower-latency local, specialized, and cost-aware deployment paths.
Grok 4.3
xAI flagship model entry for agentic tool calling, instruction following, reasoning, and OpenAI-compatible Responses API integration.
Llama 4 Maverick
Meta Llama 4 Maverick model entry for multimodal open-weight workflows, multilingual text, code generation, and local or hosted deployment evaluation.
Mistral Large 3
Mistral Large 3 flagship model for multilingual tasks, general reasoning, and open-weight or API deployment with 256K-token context.
Mistral Medium 3.5
Mistral model entry for coding, agentic workflows, and multimodal use cases.
OpenAI o3 / o4-mini
OpenAI reasoning-optimized o-series models (o3 and o4-mini) for complex multi-step reasoning, math, science, and coding tasks.
Qwen3.6
Open-weight Qwen3.6 model family for hybrid thinking, multilingual tasks, coding, and OpenAI-compatible self-hosted serving with 128K context.