Models

65B dense model built for agentic coding, with up to 1M tokens of context.

A version of the DeepSeek-R1 model that has been post trained to provide unbiased, accurate, and factual information by Perplexity.

AutoTrust’s decision models return choices, yes/no probabilities, and ratings for the questions you supply

A general-purpose model ranging from 3 billion parameters to 70 billion, suitable for entry-level hardware.

Nexus Raven is a 13B instruction tuned model for function calling tasks.

A commercial-friendly small language model by NVIDIA optimized for roleplay, RAG QA, and function calling.

Ready-to-go enthusiastic promoter

Apex schizo overloads every kek theme at once

Beam is an open model by Reflection designed to deliver strong performance for areas such as agentic tool use, coding and general reasoning with an emphasis on token efficient usage.

Saina Helm 3, natively multimodal: a 0.8B decision model that reads text, images and audio in one pass and answers typed questions (yes/no, choice, rating) with a probability per option. Scores 45.89 on Decision Index 0.3. Does not generate text.

Qwen3.6-35B-A3B MoE coding agent for Claude Code / Codex / opencode, 64K context, native tool-calling, honest tool use, safety guardrails intact

Microsoft FrogNano-4B: compact repository-level coding agent (Qwen3.5-4B, RL-only post-training). Thinks, MIT.

The 7B model released by Mistral AI, updated to version 0.3.

Phi-4-mini brings significant enhancements in multilingual support, reasoning, and mathematics, and now, the long-awaited function calling feature is finally supported.

The IBM Granite 2B and 8B models are designed to support tool-based use cases and support for retrieval augmented generation (RAG), streamlining code generation, translation and bug fixing.

A series of models from Groq that represent a significant advancement in open-source AI capabilities for tool use/function calling.

A model from NVIDIA based on Llama 3 that excels at conversational question answering (QA) and retrieval-augmented generation (RAG).

Phi 4 mini reasoning is a lightweight open model that balances efficiency with advanced reasoning ability.

The smallest model in Cohere's R series delivers top-tier speed, efficiency, and quality to build powerful AI applications on commodity GPUs and edge devices.

The IBM Granite Guardian 3.0 2B and 8B models are designed to detect risks in prompts and/or responses.