AI Models Directory

OpenRouter-style model index with deep metadata: pricing, context windows, architecture, and parameters.

Clear Filters

Showing 91 - 105 of 235 matching models from 548 total for query "reasoning"

Meta
Budget tiertext + image -> text

Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion...

1M+ contextTool callingVision
Context1.0M
Input$0.15 / 1M
Output$0.60 / 1M
Meta
Budget tiertext + image -> text

Llama 4 Scout 17B Instruct (16E) is a mixture-of-experts (MoE) language model developed by Meta, activating 17 billion parameters out of a total of 109B.

Long contextTool callingVision
Context328K
Input$0.08 / 1M
Output$0.30 / 1M
Microsoft
Budget tiertext -> text

Microsoft: Phi 4

Standard context

Microsoft Research Phi-4 is designed to perform well in complex reasoning tasks and can operate efficiently in situations with limited memory or where quick responses are needed.

Budget inputHugging FaceConfigurable API
Context16K
Input$0.07 / 1M
Output$0.14 / 1M
Minimax
Budget tiertext -> text

MiniMax: MiniMax M1

Ultra context

MiniMax-M1 is a large-scale, open-weight reasoning model designed for extended context and high-efficiency inference.

1M+ contextReasoningTool calling
Context1M
Input$0.40 / 1M
Output$2.20 / 1M
Minimax
Budget tiertext -> text

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows.

Long contextReasoningTool calling
Context197K
Input$0.26 / 1M
Output$1.00 / 1M
Minimax
Budget tiertext -> text

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development.

Long contextReasoningTool calling
Context197K
Input$0.27 / 1M
Output$0.95 / 1M
Minimax
Budget tiertext -> text

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.

Long contextReasoningTool calling
Context197K
Input$0.19 / 1M
Output$1.15 / 1M
Minimax
Budget tiertext -> text

MiniMax-M2.5 is a SOTA large language model designed for real-world productivity.

Long contextReasoningTool calling
Context197K
Input$0.00 / 1M
Output$0.00 / 1M
Minimax
Budget tiertext -> text

MiniMax-M2.7 is a next-generation large language model designed for autonomous, real-world productivity and continuous improvement.

Long contextReasoningTool calling
Context205K
Input$0.30 / 1M
Output$1.20 / 1M
Mistral AI
Standard tiertext -> text

Mistral Large

Long context

This is Mistral AI's flagship model, Mistral Large 2 (version `mistral-large-2407`).

Long contextTool callingConfigurable API
Context128K
Input$2.00 / 1M
Output$6.00 / 1M
Mistral AI
Standard tiertext -> text

Mistral Large 2407

Long context

This is Mistral AI's flagship model, Mistral Large 2 (version mistral-large-2407).

Long contextTool callingConfigurable API
Context131K
Input$2.00 / 1M
Output$6.00 / 1M
Mistral AI
Budget tiertext -> text

Devstral Medium is a high-performance code generation and agentic reasoning model developed jointly by Mistral AI and All Hands AI.

Long contextTool callingBudget input
Context131K
Input$0.40 / 1M
Output$2.00 / 1M
Mistral AI
Budget tiertext + image -> text

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost.

Long contextTool callingVision
Context131K
Input$0.40 / 1M
Output$2.00 / 1M
Mistral AI
Budget tiertext + image -> text

Mistral Medium 3.1 is an updated version of Mistral Medium 3, which is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at...

Long contextTool callingVision
Context131K
Input$0.40 / 1M
Output$2.00 / 1M
Mistral AI
Budget tiertext + image -> text

Mistral Small 3.1 24B Instruct is an upgraded variant of Mistral Small 3 (2501), featuring 24 billion parameters with advanced multimodal capabilities.

Long contextVisionBudget input
Context131K
Input$0.03 / 1M
Output$0.11 / 1M