Which model should you pick?
Every AI tool now hands you a model menu. The names are noise. This page sorts the models I actually use by the job you are trying to do, and tells you where you will find each one.
Direct
The architect tier: plan the work, design the approach, then direct cheaper models to do it, picking the right one for each piece. Right now Claude Opus does this job for almost everything; Fable only adds a little edge on very big, long-running tasks. I expect that to flip again with the next Fable release.
3 models
Claude Opus
Almost everything: planning, deep reasoning, writing, research, and complex agentic coding. Fable only adds an edge on very big, long-running tasks.
- Context
- 1M tokens
- Price
- $4 / $20
- Speed
- Moderate
Claude Fable
Very big, long-running agentic tasks where a little extra edge over Opus 5.5 is worth two and a half times the price.
- Context
- 1M tokens
- Price
- $10 / $50
- Speed
- Slow
GPT-6 Astra
Work where the answer has to be right the first time and the token bill is not the constraint.
- Context
- 1.05M tokens
- Price
- $10 / $50
- Speed
- Moderate
| Model | Best for | Context | Pricein / out per M tokens | Speed | Where | Rating |
|---|---|---|---|---|---|---|
| Claude Opus Fabian's pick Anthropic | Almost everything: planning, deep reasoning, writing, research, and complex agentic coding. Fable only adds an edge on very big, long-running tasks. | 1M tokens | $4 / $20 | Moderate | Claude, Claude Code, Claude Cowork, Perplexity Computer, Poe | |
| Claude Fable Anthropic | Very big, long-running agentic tasks where a little extra edge over Opus 5.5 is worth two and a half times the price. | 1M tokens | $10 / $50 | Slow | Claude, Poe, Claude Code | |
| GPT-6 Astra OpenAI | Work where the answer has to be right the first time and the token bill is not the constraint. | 1.05M tokens | $10 / $50 | Moderate | ChatGPT, OpenAI Codex, Poe, OpenRouter |
Think
Strong reasoning for hard problems: strategy, analysis, the calls where the quality of the thinking decides everything downstream. Claude Opus is my default here and for almost everything else. GPT-6 belongs here at its Sol tier.
3 models · Why "think expensive, execute cheap" →
Claude Opus
Almost everything: planning, deep reasoning, writing, research, and complex agentic coding. Fable only adds an edge on very big, long-running tasks.
- Context
- 1M tokens
- Price
- $4 / $20
- Speed
- Moderate
Gemini Pro
Analyzing massive datasets, full codebases, or hour-long video files.
- Context
- 2M tokens
- Price
- $1.25 / $10
- Speed
- Moderate
GPT-6
Tiers: Sol · Luna
Execution work at scale: Sol when the task is hard or mistakes are expensive, Luna for high-volume work where speed and price matter most.
- Context
- 1.05M tokens
- Price
- Sol $2 / $10 · Luna $0.10 / $0.50
- Speed
- Fast
| Model | Best for | Context | Pricein / out per M tokens | Speed | Where | Rating |
|---|---|---|---|---|---|---|
| Claude Opus Fabian's pick Anthropic | Almost everything: planning, deep reasoning, writing, research, and complex agentic coding. Fable only adds an edge on very big, long-running tasks. | 1M tokens | $4 / $20 | Moderate | Claude, Claude Code, Claude Cowork, Perplexity Computer, Poe | |
| Gemini Pro Google | Analyzing massive datasets, full codebases, or hour-long video files. | 2M tokens | $1.25 / $10 | Moderate | Gemini, Poe, Google AI Studio | |
| GPT-6 OpenAI · Sol · Luna | Execution work at scale: Sol when the task is hard or mistakes are expensive, Luna for high-volume work where speed and price matter most. | 1.05M tokens | Sol $2 / $10 · Luna $0.10 / $0.50 | Fast | ChatGPT, OpenAI Codex, Poe, OpenRouter |
Execute
The workhorses. Drafting, coding, formatting, summarising, agents that run all day. I rarely pick these by hand anymore: they do their best work as subagents, when a stronger model hands them a focused job. GPT-6 comes in two tiers here, Sol for the harder work and Luna for volume.
8 models
Claude Sonnet
Focused coding, drafting, and research jobs handed to it as a subagent by Opus or Fable, and high-volume API work.
- Context
- 1M tokens
- Price
- $2 / $10
- Speed
- Fast
GPT-6
Tiers: Sol · Luna
Execution work at scale: Sol when the task is hard or mistakes are expensive, Luna for high-volume work where speed and price matter most.
- Context
- 1.05M tokens
- Price
- Sol $2 / $10 · Luna $0.10 / $0.50
- Speed
- Fast
GLM-5.3-Flash
Running an assistant or agent that works all day on tool calls, where cost per task matters more than personality.
- Context
- 1M tokens
- Price
- $0.15 / $0.50
- Speed
- Fast
Qwen3.7-Max
Complex, multi-step agentic coding tasks.
- Context
- 1M tokens
- Price
- ~$0.65 / $3.25
- Speed
- Moderate
DeepSeek V4 Flash
High-volume reasoning tasks where cost efficiency is critical.
- Context
- 1M tokens
- Price
- $0.14 / $0.28
- Speed
- Fast
Gemini Flash
High-volume execution work: coding, agents, copy, and anything where speed and price beat peak intelligence.
- Context
- 1M tokens
- Price
- $0.75 / $3.75
- Speed
- Instant
Grok 4.7
Running inside Grok Bot, and reading what people on X are saying about a topic right now.
- Context
- 500K tokens
- Price
- $2 / $6
- Speed
- Moderate
Claude Haiku
A subagent that searches large document collections for a stronger model.
- Context
- 200K tokens
- Price
- $1 / $5
- Speed
- Instant
| Model | Best for | Context | Pricein / out per M tokens | Speed | Where | Rating |
|---|---|---|---|---|---|---|
| Claude Sonnet Fabian's pick Anthropic | Focused coding, drafting, and research jobs handed to it as a subagent by Opus or Fable, and high-volume API work. | 1M tokens | $2 / $10 | Fast | Claude, Poe, Perplexity, Claude Code | |
| GPT-6 OpenAI · Sol · Luna | Execution work at scale: Sol when the task is hard or mistakes are expensive, Luna for high-volume work where speed and price matter most. | 1.05M tokens | Sol $2 / $10 · Luna $0.10 / $0.50 | Fast | ChatGPT, OpenAI Codex, Poe, OpenRouter | |
| GLM-5.3-Flash Zhipu AI (Z.ai) | Running an assistant or agent that works all day on tool calls, where cost per task matters more than personality. | 1M tokens | $0.15 / $0.50 | Fast | OpenClaw, OpenRouter | |
| Qwen3.7-Max Alibaba Cloud | Complex, multi-step agentic coding tasks. | 1M tokens | ~$0.65 / $3.25 | Moderate | Poe, OpenRouter | |
| DeepSeek V4 Flash DeepSeek | High-volume reasoning tasks where cost efficiency is critical. | 1M tokens | $0.14 / $0.28 | Fast | OpenRouter | |
| Gemini Flash Google | High-volume execution work: coding, agents, copy, and anything where speed and price beat peak intelligence. | 1M tokens | $0.75 / $3.75 | Instant | Gemini, Poe, Google AI Studio, Antigravity | |
| Grok 4.7 xAI | Running inside Grok Bot, and reading what people on X are saying about a topic right now. | 500K tokens | $2 / $6 | Moderate | Grok Bot, Poe, OpenRouter | |
| Claude Haiku Anthropic | A subagent that searches large document collections for a stronger model. | 200K tokens | $1 / $5 | Instant | Claude, Poe |
Search the live web
Models with a search index wired in. For anything where "as of today" matters and you want the sources, not a confident guess.
2 models
Sonar Pro
Real-time web research, fact-checking, and synthesizing multiple online sources with inline citations.
- Context
- 127K tokens
- Price
- $1 flat + search fees
- Speed
- Fast
Grok 4.7
Running inside Grok Bot, and reading what people on X are saying about a topic right now.
- Context
- 500K tokens
- Price
- $2 / $6
- Speed
- Moderate
| Model | Best for | Context | Pricein / out per M tokens | Speed | Where | Rating |
|---|---|---|---|---|---|---|
| Sonar Pro Fabian's pick Perplexity | Real-time web research, fact-checking, and synthesizing multiple online sources with inline citations. | 127K tokens | $1 flat + search fees | Fast | Perplexity | |
| Grok 4.7 xAI | Running inside Grok Bot, and reading what people on X are saying about a topic right now. | 500K tokens | $2 / $6 | Moderate | Grok Bot, Poe, OpenRouter |
Run privately on your own machine
Open-weights models small enough for a laptop or a workstation. Nothing leaves the building. Weaker than the cloud tier, and that is the trade.
4 models
Gemma 4 27B
Local coding and more complex automation tasks on workstations.
- Runs on
- A workstation
- Price
- Free, runs locally
- Speed
- Moderate
Gemma 4 12B
Local automation, admin tasks, and privacy-first workflows on a laptop.
- Runs on
- A laptop
- Price
- Free, runs locally
- Speed
- Fast
GLM-5.3-Flash
Running an assistant or agent that works all day on tool calls, where cost per task matters more than personality.
- Runs on
- 1M tokens
- Price
- $0.15 / $0.50
- Speed
- Fast
DeepSeek V4 Flash
High-volume reasoning tasks where cost efficiency is critical.
- Runs on
- 1M tokens
- Price
- $0.14 / $0.28
- Speed
- Fast
| Model | Best for | Runs on | Price | Speed | Where | Rating |
|---|---|---|---|---|---|---|
| Gemma 4 27B Fabian's pick Google | Local coding and more complex automation tasks on workstations. | A workstation | Free, runs locally | Moderate | Hugging Face | |
| Gemma 4 12B Google | Local automation, admin tasks, and privacy-first workflows on a laptop. | A laptop | Free, runs locally | Fast | Hugging Face | |
| GLM-5.3-Flash Zhipu AI (Z.ai) | Running an assistant or agent that works all day on tool calls, where cost per task matters more than personality. | 1M tokens | $0.15 / $0.50 | Fast | OpenClaw, OpenRouter | |
| DeepSeek V4 Flash DeepSeek | High-volume reasoning tasks where cost efficiency is critical. | 1M tokens | $0.14 / $0.28 | Fast | OpenRouter |
Make images
No context window here, and prices per image or per month. What matters is what each one is good at.
5 models
GPT-Image-2.5
Creative image work and UI design alike: conversational editing, precise inpainting, and text-heavy visuals that have to stay legible.
- Good at
- Editing, legible text
- Price
- $30 / M image tokens
- Speed
- Fast
Nano Banana 2
UI/UX screen mockups, infographics, and structured data visualization.
- Good at
- UI screens, infographics
- Price
- Free tier in Gemini
- Speed
- Fast
Midjourney
Concept art, stylized illustrations, and purely artistic aesthetics.
- Good at
- Art, mood, style
- Price
- $10–120 / month
- Speed
- Moderate
FLUX-2 Pro
Production-grade photorealism and precise prompt adherence.
- Good at
- Photorealism
- Price
- ~$0.03–0.06 / image
- Speed
- Moderate
Grok Imagine
Creative, stylized, or abstract motifs where you want to break away from sterile AI looks.
- Good at
- Stylised, abstract
- Price
- SuperGrok $30 / month
- Speed
- Fast
| Model | Best for | Good at | Price | Speed | Where | Rating |
|---|---|---|---|---|---|---|
| GPT-Image-2.5 Fabian's pick OpenAI | Creative image work and UI design alike: conversational editing, precise inpainting, and text-heavy visuals that have to stay legible. | Editing, legible text | $30 / M image tokens | Fast | ChatGPT, Poe | |
| Nano Banana 2 Google DeepMind | UI/UX screen mockups, infographics, and structured data visualization. | UI screens, infographics | Free tier in Gemini | Fast | Gemini, Poe | |
| Midjourney Midjourney | Concept art, stylized illustrations, and purely artistic aesthetics. | Art, mood, style | $10–120 / month | Moderate | Midjourney | |
| FLUX-2 Pro Black Forest Labs | Production-grade photorealism and precise prompt adherence. | Photorealism | ~$0.03–0.06 / image | Moderate | Poe | |
| Grok Imagine xAI | Creative, stylized, or abstract motifs where you want to break away from sterile AI looks. | Stylised, abstract | SuperGrok $30 / month | Fast | Grok Imagine |
Make video
Two entries so far, both priced per second of footage.
2 models
Veo 3.1
High-fidelity cinematic shots and realistic physics simulation.
- Good at
- Cinematic shots, physics
- Price
- ~$0.05–0.40 / sec
- Speed
- Moderate
Grok Imagine Video
Stylized animation and rapid video clip generation.
- Good at
- Stylised clips
- Price
- ~$0.05–0.14 / sec
- Speed
- Fast
| Model | Best for | Good at | Price | Speed | Where | Rating |
|---|---|---|---|---|---|---|
| Veo 3.1 Fabian's pick Google DeepMind | High-fidelity cinematic shots and realistic physics simulation. | Cinematic shots, physics | ~$0.05–0.40 / sec | Moderate | Veo 3.1, Google AI Studio | |
| Grok Imagine Video xAI | Stylized animation and rapid video clip generation. | Stylised clips | ~$0.05–0.14 / sec | Fast | Grok Imagine |
Voice & music
Speech that carries emotion, and full songs with a structure you control.
2 models
Eleven v3
Voiceovers, audiobooks, and emotional dialogue.
- Good at
- Expressive speech
- Price
- Credits, 1 per character
- Speed
- Fast
Lyria 3 Pro
Generating full-length, structured music tracks.
- Good at
- Full songs
- Price
- ~$0.08 / song
- Speed
- Moderate
| Model | Best for | Good at | Price | Speed | Where | Rating |
|---|---|---|---|---|---|---|
| Eleven v3 Fabian's pick ElevenLabs | Voiceovers, audiobooks, and emotional dialogue. | Expressive speech | Credits, 1 per character | Fast | ElevenLabs | |
| Lyria 3 Pro Google DeepMind | Generating full-length, structured music tracks. | Full songs | ~$0.08 / song | Moderate | Lyria |
No model matches that
Try the provider name (Anthropic, Google) or a tool you use (ChatGPT, Poe).
Missing a model you rely on? Tell me and I will put it through its paces.