DatBot blends

Available Models:

• Fast Blend: This is a mix of amazing models that return >200 tokens/second at a minimum from our partners, targeting ChatGPT quality level.
• HQ Blend: This is our slower, but incredibly high quality blend, including a few of the best models out at any given time.
• Thinking Blend: We include thinking models here of a high quality from different frontier labs to ensure that different architectures collaborate on your answers.
• Perspective Cascade: Multiple models exploring different perspectives, synthesizing a more valuable final output than a single model could.
• Deep Reasoning: Long output reasoning - able to tackle longer projects with more complex needs.
• Deep Reasoning Flash: Blistering fast version of Deep Reasoning, matching long output reasoning with alacrity.

Importance

DatBot Blends and Perspective Cascade are, to my knowledge, the first time that “frontier” models have been put into a blended generation capacity in order to improve their performance. You can read more about this in the DatBot post about blends, here. No single origin here! Deep Reasoning and Deep Reasoning Flash were some of the first real successes at generating stronger long output - now reasoning models are getting better at this natively, and this takes top models to still another level.

OpenAI Models

Available Models:

Reasoning/Thinking Models:

• GPT-5: OpenAI’s latest and most advanced thinking model
• GPT-5 Low: Low reasoning effort variant of GPT-5 for faster responses
• GPT-5 High: High reasoning effort variant of GPT-5 for complex problems
• GPT-OSS-120b: OpenAI’s open-source thinking model with 120 billion parameters
• GPT-OSS-20b: Smaller open-source thinking model with 20 billion parameters
• GPT-5 Mini: Smaller, faster version of GPT-5
• GPT-5 Nano: Smallest GPT-5 variant, great for simple tasks
• o3: Previous generation reasoning model (now outdated but still available)
• o4-mini: Smaller reasoning model (now outdated but still available)

Non-Reasoning Models:

• GPT-5 Chat (ChatGPT Version): Non-thinking variant of GPT-5, exactly the same as ChatGPT
• GPT-4.1 Mini: Updated mini model, better than GPT-4o mini (now outdated)
• GPT-4.1 Nano: Smallest model in the 4.1 series (now outdated)
• GPT-4o: The model that ChatGPT uses (now outdated, use GPT-5 Chat instead)
• GPT-4o mini: Smaller version of GPT-4o (now outdated)
• GPT-3.5 Turbo: The original ChatGPT model, still available for legacy use and comparison to see how far we’ve come (now outdated)

Importance of OpenAI:

OpenAI’s models are at the bleeding edge of AI technology, pushing the boundaries of what AI can accomplish. They proved what’s possible. Closely partnered with Microsoft.

Cohere Models

Available Models:

• Command-A: Cohere’s current top model, very good at responding in certain formats

Anthropic Models

Available Models:

• Claude Opus 4 (Thinking): Claude’s most advanced model with thinking/reasoning capabilities
• Claude Opus 4: Non-thinking variant of Opus 4
• Claude Sonnet 4 (Thinking): Sonnet 4 with thinking capabilities for complex reasoning
• Claude Sonnet 4: Non-thinking variant, excellent for coding and general tasks
• Claude 3.5 Haiku: Lightning fast, better than GPT-4 in some tests, amazingly cheap

Importance:

The ‘Sonnet’ models tend to be the best price/performance - Sonnet 4 is an amazing coding model, for example (I use it all the time). Opus is often the best writer, at any price.

Meta Models

(In case you didn’t know… Meta owns Facebook, Instagram, Threads, WhatsApp, Oculus, etc. It’s just like Google is technically part of Alphabet alongside Waymo etc.)

Available Models:

• Llama 4 Scout: New price/performance champ, matching Gemini 2.0 Flash from Google
• Llama 4 Maverick: New best pound for pound contender - fast, reasonably priced, comparable to DeepSeek V3
• Llama 3.1 8b: Great price/performance ratio, matching GPT-3.5 Turbo quality but faster and cheaper. Largely the Gemini Flash series is a better price/performance champion now.
• Llama 3.3 70b: Pound-for-pound excellence, potentially as good as Llama 405b, according to Zuckerberg!
• Llama 3.1 405b: Meta’s flagship, comparable to GPT-4o or Sonnet 3.5.

Importance:

Meta is the standardbearer of quasi-open source AI (there are some limits to their license, but not meaningful unless you’re a many-billion dollar company).

Google Models

Available Models:

Thinking Models:

• Gemini 2.5 Pro (Thinking): Google’s most advanced thinking model, best in class for many tasks
• Gemini 2.5 Flash (Thinking): High-speed thinking model from Google

Non-Thinking Models:

• Gemini 2.5 Flash: Google’s best high-speed model without thinking
• Gemini 2.0 Flash: Excellent price-performance ratio
• Gemini 2.0 Flash Lite: Super speedy lightweight model

Importance:

Google’s … well, Google. They make both closed source Gemini models that compete at the frontier, and open weight models (Gemma) anyone can run.

xAI Models

Available Models:

• Grok 4 (Thinking): xAI’s latest thinking model, competitive with GPT-5 and Claude Opus 4
• Grok 3 Mini (Thinking): Smaller thinking model from xAI
• Grok 3 Mini High Effort: High reasoning effort variant of Grok 3 Mini

Importance:

xAI and Elon Musk have a rivalry with OpenAI that’s heating up. With xAI buying X (formerly Twitter), they have a unique source of training data like Facebook or Google have, and they are investing rapidly in GPUs. Expect good models here.

Qwen Models

Available Models:

• Qwen 3 235b (Thinking): Alibaba’s largest thinking model with 235 billion parameters
• Qwen 3 235b Instruct: Non-thinking variant of the 235b model
• Qwen 3 32b (Thinking): 32 billion parameter thinking model
• Qwen 3 30b MoE: Budget-friendly 30 billion parameter Mixture of Experts model with thinking capabilities

Importance:

Alibaba’s Qwen models provide excellent performance across various sizes, with the Qwen 3 series representing their latest advancements in large language models.

Mistral AI Models

Available Models:

• Mistral Small V3.2: Super fast, very competitive, a real price/performance champion like Gemini 2.0 Flash

Importance

Europe’s great hope for AI competitiveness, this French company is pretty neat.

Z-AI Models (Zhipu AI)

Available Models:

• GLM 4.5 (Thinking): Z-AI’s flagship thinking model, excellent performance
• GLM 4.5 Air (Thinking): Lightweight thinking variant, great value

Importance:

Z-AI (Zhipu AI) is a Chinese AI company making great value models with strong reasoning.

Moonshot AI Models

Available Models:

• Kimi K2: Moonshot’s flagship non-thinking model, think ChatGPT default

Importance:

Moonshot AI’s Kimi models are new flagships, marking their entry.

Deepseek Models

• Deepseek Chat (V3): Great and inexpensive model from Deepseek, an amazing Chinese AI lab. Comparable to Sonnet 3.7, Llama 4 Maverick or GPT-4o/4.1 - a small step below GPT-5. We use more expensive providers that do not train on output, instead of DeepSeek itself (which does train on your output).
• Deepseek R1 (new version) (Thinking): Reasoning model competing with GPT-5. We use the more expensive providers that do not train on outputs, for privacy reasons.

MiniMax Models

Available Models:

• MiniMax-01: MiniMax’s flagship model

Importance:

MiniMax is another upstart Chinese AI company making great models.

Image/Audio/Video Models:

We use a combination of models that update as we find new price/performance champions for different aspects of the site

These may include models like: Flux (Kontext, Krea etc.) SeeDance/SeeDream Veo/Imagen GPT-Image ElevenLabs models The current state of the art speech-to-text and text-to-speech models

These get frequently updated, like our blends,

Looking for non-LLM Integrations?

• We have a web scraper built in, and can scrape any website you want, either through our RAG knowledge map implementation - or through our chat interface.