Guide

High-effort o3 tier for difficult technical reasoning and careful answers

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...

Gemini 2.5 Pro Preview 06-05 from Google - text, image, audio, video, pdf input, 1,048,576 token context

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

DeepSeek-R1-0528 is a lightly upgraded release of DeepSeek R1 that taps more compute and smarter post-training tricks, pushing its reasoning and inference to the brink of flagship models like O3 and Gemini 2.5 Pro. It now tops math, programming, and logic leaderboards, showcasing a step-change in depth-of-thought. The distilled variant, DeepSeek-R1-0528-Qwen3-8B, transfers this chain-of-thought into an 8 B-parameter form, beating standard Qwen3 8B by +10 pp and tying the 235 B “thinking” giant on AIME 2024.

Safety model for policy screening, moderation, and risk-aware routing workflows

Safety model for policy screening, moderation, and risk-aware routing workflows

Image model for prompt-driven generation, editing, and visual design workflows

Image model for prompt-driven generation, editing, and visual design workflows

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active in an inference pass. Fully open-source model.

May 28th update to the [original DeepSeek R1](/deepseek/deepseek-r1) Performance on par with [OpenAI o1](/openai/o1), but open-sourced and with fully open reasoning tokens. It's 671B parameters in size, with 37B active...

Deepseek R1 05/28 from Fireworks AI - text input, 160,000 token context

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

DeepSeek reasoning model for multi-step analysis, math, coding, and tools

Claude Opus 4 is benchmarked as the world’s best coding model, at time of release, bringing sustained performance on complex, long-running tasks and agent workflows. It sets new benchmarks in...

Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...

Claude Opus 4 (latest) from Anthropic - text, image, pdf input, 200,000 token context

Claude Sonnet 4 from Anthropic - text, image, pdf input, 200,000 token context

Claude Opus 4 from Anthropic - text, image, pdf input, 200,000 token context

Claude Sonnet 4 (latest) from Anthropic - text, image, pdf input, 200,000 token context

Claude Opus 4 (US) from AWS Bedrock - text, image, pdf input, 200,000 token context

Claude Sonnet 4 from AWS Bedrock - text, image, pdf input, 200,000 token context

Claude Opus 4 from AWS Bedrock - text, image, pdf input, 200,000 token context

Balanced Claude model for coding, analysis, agent workflows, and cost control

Balanced Claude model for coding, analysis, agent workflows, and cost control

Balanced Claude model for coding, analysis, agent workflows, and cost control

Balanced Claude model for coding, analysis, agent workflows, and cost control

Balanced Claude model for coding, analysis, agent workflows, and cost control

Flagship Claude model for deep reasoning, coding, and long-horizon agents

Devstral-Small-2505 is a 24B parameter agentic LLM fine-tuned from Mistral-Small-3.1, jointly developed by Mistral AI and All Hands AI for advanced software engineering tasks. It is optimized for codebase exploration, multi-file editing, and integration into coding agents, achieving state-of-the-art results on SWE-Bench Verified (46.8%). Devstral supports a 128k context window and uses a custom Tekken tokenizer. It is text-only, with the vision encoder removed, and is suitable for local deployment on high-end consumer hardware (e.g., RTX 4090, 32GB RAM Macs). Devstral is best used in agentic workflows via the OpenHands scaffold and is compatible with inference frameworks like vLLM, Transformers, and Ollama. It is released under the Apache 2.0 license.

Venice.ai is a privacy-first, uncensored AI platform providing access to leading open-source models without data collection, content restrictions, or conversation logging. Key features include private access to multiple models (Llama, DeepSeek, StableDiffusion, GPT, Claude, Gemini), zero data retention with local chat history storage, decentralized GPU infrastructure preventing single-entity data access, uncensored text generation and image creation, web-enabled research and PDF analysis, and a private API with no logging. The platform serves over 1.3 million users and is integrating Web3 capabilities through partnerships like Warden Protocol for on-chain AI and censorship resistance. Venice offers both free and Pro tiers with mobile apps available, focusing on creative freedom and honest answers without guardrails while maintaining complete conversation privacy through decentralized processing.

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...

Gemma 3n E4B-it is optimized for efficient execution on mobile and low-resource devices, such as phones, laptops, and tablets. It supports multimodal inputs—including text, visual data, and audio—enabling diverse tasks...

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Gemini 2.5 Flash Preview 05-20 from Google - text, image, audio, video, pdf input, 1,048,576 token context

Gemma 3n 4B from Google - text input, 8,192 token context

Open Gemma instruction model for efficient chat and self-hosted deployments

General-purpose chat model for instruction following, writing, and analysis

Efficient model for low-latency assistance, extraction, and routine automation

Embedding model for semantic search, retrieval, clustering, and ranking pipelines

Video model for prompt-guided generation, editing, and motion workflows

codex-mini-latest is a fine-tuned version of o4-mini specifically for use in Codex CLI. For direct use in the API, we recommend starting with gpt-4.1.

Codex Mini from OpenAI - text input, 200,000 token context

DeepHermes 3 (Mistral 24B Preview) is an instruction-tuned language model by Nous Research based on Mistral-Small-24B, designed for chat, function calling, and advanced multi-turn reasoning. It introduces a dual-mode system that toggles between intuitive chat responses and structured “deep reasoning” mode using special system prompts. Fine-tuned via distillation from R1, it supports structured output (JSON mode) and function call syntax for agent-based applications. DeepHermes 3 supports a **reasoning toggle via system prompt**, allowing users to switch between fast, intuitive responses and deliberate, multi-step reasoning. When activated with the following specific system instruction, the model enters a *"deep thinking"* mode—generating extended chains of thought wrapped in `<think></think>` tags before delivering a final answer. System Prompt: You are a deep thinking AI, you may use extremely long chains of thought to deeply consider the problem and deliberate with yourself via systematic reasoning processes to help come to a correct solution prior to answering. You should enclose your thoughts and internal monologue inside <think> </think> tags, and then provide your solution or response to the problem.

Qwen omni model for text, vision, audio, and multimodal agent tasks

Mistral Medium 3 is a high-performance enterprise-grade language model designed to deliver frontier-level capabilities at significantly reduced operational cost. It balances state-of-the-art reasoning and multimodal performance with 8× lower cost...

Gemini 2.5 Pro is Google’s state-of-the-art AI model designed for advanced reasoning, coding, mathematics, and scientific tasks. It employs “thinking” capabilities, enabling it to reason through responses with enhanced accuracy...