Structured cards
Model database
Filter by provider, architecture family, or full-text search across descriptions.
Frontier models
Verified flagship models across major providers, curated for operational relevance.
Anthropic
Claude Fable 5
FrontierLatestAnthropic's highest-capability widely released Claude model, documented for deep reasoning, codebase-scale work, long-context enterprise workloads, and multimodal inputs.
OpenAI
GPT-5.5
FrontierLatestOpenAI's current flagship model for complex reasoning, coding, and professional work, documented in the OpenAI API model guide as the default starting point for high-complexity workloads.
Microsoft AI
MAI-Thinking-1
FrontierLatestMicrosoft AI's frontier reasoning model in the MAI family, announced for difficult prompts, science, math, and complex planning workloads, with Microsoft Foundry access documented as private preview.
Gemini 2.5 Pro
FrontierLatestGoogle's advanced Gemini model for complex tasks, with official Gemini API documentation calling out deep reasoning and coding capabilities.
Anysphere
Cursor Composer 2.5
FrontierLatestCursor's Composer 2.5 model, documented in the official Cursor changelog as a coding model used in the Auto routing flow.
xAI
Grok 4.3
FrontierLatestxAI's documented default for general chat workloads, described in xAI docs as the most intelligent and fastest Grok model for non-specialized use cases.
Mistral AI
Mistral Medium 3.5
FrontierLatestMistral's documented latest frontier-class multimodal model optimized for agentic and coding use cases.
DeepSeek
DeepSeek-V3.2
FrontierLatestDeepSeek's documented successor to the V3.2 experimental line, positioned in official DeepSeek API news as live on app, web, and API.
All models
Filter and paginate the full catalog. Tabs control lifecycle scope.
Anthropic
Claude 3.5 Haiku
LegacyClaude 3.5 Haiku is Anthropic’s fast, cost-efficient tier for high-volume classification, routing, and simple chat. It targets latency-sensitive paths and agent pre-processing before escalating to Sonnet-class models.
01.AI
Yi-34B
LegacyCatalog entry for this named release; see the provider’s official documentation for modalities, pricing, and context limits.
Alibaba
Qwen 2
LegacyCatalog entry for this named release; see the provider’s official documentation for modalities, pricing, and context limits.
Microsoft
Phi-3 Mini
LegacyCatalog entry for this named release; see the provider’s official documentation for modalities, pricing, and context limits.
Meta
Llama 3 8B
LegacyCatalog entry for this named release; see the provider’s official documentation for modalities, pricing, and context limits.
Meta
Llama 3 70B
LegacyCatalog entry for this named release; see the provider’s official documentation for modalities, pricing, and context limits.
OpenAI
GPT-4.1 nano
LegacyCatalog entry for this named release; see the provider’s official documentation for modalities, pricing, and context limits.
TII
Falcon 180B
LegacyCatalog entry for this named release; see the provider’s official documentation for modalities, pricing, and context limits.
Anthropic
Claude Opus 4.5
LegacyCatalog entry for this named release; see the provider’s official documentation for modalities, pricing, and context limits.
Anthropic
Claude Opus 4.6
LegacyCatalog entry for this named release; see the provider’s official documentation for modalities, pricing, and context limits.
Anthropic
Claude Sonnet 4.5
LegacyCatalog entry for this named release; see the provider’s official documentation for modalities, pricing, and context limits.
OpenAI
o1-mini
DeprecatedA smaller, faster o1-class model for STEM-style reasoning where full o1 latency or cost is prohibitive. Use it when you need better chain-of-thought style behavior than GPT-4o mini but not full o1 depth.
OpenAI
DALL·E 3
DeprecatedDALL·E 3 is OpenAI’s instruction-aligned image generation model exposed via the Images API, emphasizing prompt adherence and safety classifiers for consumer and enterprise creative workflows. It targets marketing visuals, product mockups, and storyboarding rather than photorealistic deception.
Recommended
Top current models by information quality score — good defaults when you are not sure where to start.
Sarvam AI
Sarvam 30B
CurrentLatestSarvam 30B is a 30B parameter Mixture-of-Experts chat and reasoning model from Sarvam AI, optimized for Indian languages, real-time conversation, high-throughput voice-agent pipelines, coding, and practical deployment. Sarvam documents 2.4B active parameters per token, 16T tokens of pre-training data, a 64K context window, Grouped Query Attention, Apache 2.0 open weights, and OpenAI-compatible chat completions.
Sarvam AI
Sarvam 105B
CurrentLatestSarvam 105B is Sarvam AI's flagship 105B+ parameter Mixture-of-Experts reasoning model for Indian-language and English chat, complex reasoning, coding, long-context document analysis, and agentic tool-use workflows. Sarvam documents it as a 128K-context OpenAI-compatible chat model with Multi-head Latent Attention, 12T tokens of pre-training data, Apache 2.0 open weights, and production use powering Indus. Its strongest fit is Indian-language enterprise assistants, multilingual reasoning, and agent workflows where native script, romanized, and code-mixed inputs matter.
Anthropic
Claude Opus 4.8
CurrentLatestAnthropic's current Opus-tier Claude model, documented for complex reasoning, coding, and multimodal enterprise workloads below the newer Fable tier.
OpenAI
GPT-5.4
CurrentLatestOpenAI's GPT-5.4 model, documented in the official OpenAI API model guide as part of the current GPT-5 family below the GPT-5.5 flagship lane.
Stability AI
Stable Diffusion XL
CurrentLatestStable Diffusion XL (SDXL) 1.0 is Stability AI's latent diffusion text-to-image model for native 1024x1024 generation. The base model can run standalone or feed an optional refiner for the final denoising steps, and the published weights support self-hosted Diffusers workflows.
Alibaba
Qwen 2.5 72B Instruct
CurrentLatestQwen 2.5 72B Instruct is a large multilingual open-weights model from Alibaba’s Qwen family with strong coding and general chat performance. Common in APAC deployments and on Hugging Face inference endpoints—check license terms for commercial use.
Missing a frontier release? Add a model (editors)