Prompts for people who ship the work.
A working library of prompt templates, organised by what you are making — text, images, video, audio, avatars, software, marketing — with separate packs for the tools you actually open.
- 07Categories
- 08Tool packs
- 73Templates
- 00Signup walls
Top 24 AI models right now
Current language models released in the last 240 days, ranked by published Epoch Capabilities Index (ECI) scores. Equal scores share a rank; there are no estimated scores or lab quotas. Higher ECI means stronger measured capability, not necessarily better value for your task. Image and video rankings use blind votes from Arena’s text-to-image and text-to-video leaderboards. Models released in the last 60 days are tagged New. Open any model for prices, specs and head-to-head comparisons.
Recently released AI models
Released in the last 30 days, newest first. Benchmark scores may not yet be available.
- New
GPT-6.2 AstraOpenAIReleased
- New
GPT-6.2 SolOpenAIReleased
- New
MAI-Image-2.7MicrosoftReleased
- New
MAI-Image-2.7 FlashMicrosoftReleased
- New
Hy4 flashTencentReleased
- New
Qwen4 MaxAlibaba (Qwen)Released
- New
Gemini 4 HydrogenGoogleReleased
- New
Gemini 4 CarbonGoogleReleased
- New
Claude Fable 5.2AnthropicReleased
- New
Muse EmberMetaReleased
- New
Gemini Omni 1.2 FlashGoogleReleased
- New
GPT-6 CyberOpenAIReleased
- New
Inkling 2 SmallThinking MachinesReleased
- New
Ling 3.2 FlashinclusionAIReleased
- New
GPT Image 2.6 FlareOpenAIReleased
- New
GPT Image 2.6 SunburstOpenAIReleased
- New
Hy4TencentReleased
- New
LongCat-2.5Meituan (LongCat)Released
- New
Particle-1Particle AiReleased
- New
GPT-6.1 TerraOpenAIReleased
- New
Kimi K3.1 ProMoonshot AIReleased
- New
FlintRecursiveReleased
- New
Ornith 1.5 122BDeepReinforceReleased
- New
MiniMax-M3.1-FlashMiniMaxReleased
Top language models
- Rank 01New
GPT-6.2 AstraOpenAIECI 174.2
- Rank 02New
Claude Fable 5.2AnthropicECI 173.5
- Rank 03New
Gemini 4 CarbonGoogleECI 169.8
- Rank 04
GPT-6 AstraOpenAIECI 169.2
- Rank 05New
Claude Opus 5.5AnthropicECI 168.7
- Rank 06New
GPT-6.1 SolOpenAIECI 168.6
- Rank 07New
GPT-6.1 TerraOpenAIECI 167.7
- Rank 08
Claude Fable 5.1AnthropicECI 167.1
- Rank 09New
Claude Sonnet 5.5AnthropicECI 166.6
- Rank 10New
Gemini 4 ArgonGoogleECI 166.6
- Rank 11
Claude Opus 5AnthropicECI 164.7
- Rank 12
Claude Fable 5AnthropicECI 164.2
- Rank 13New
GPT-6 SolOpenAIECI 163.8
- Rank 14
GPT-5.6 SolOpenAIECI 163.1
- Rank 15
GPT-5.5 ProOpenAIECI 162.8
- Rank 16New
Muse WonderMetaECI 161.7
- Rank 17New
Kimi K3.1 ProMoonshot AIECI 161.4
- Rank 18
GPT-5.6 TerraOpenAIECI 160.8
- Rank 19New
Claude Haiku 5.5AnthropicECI 160.3
- Rank 20
GPT-5.5OpenAIECI 160.2
- Rank 21
Claude Opus 4.8AnthropicECI 159.9
- Rank 22New
DeepSeek V4.1 Flash 1017DeepSeekECI 159.4
- Rank 23
Gemini 3.8 FlashGoogleECI 158.8
- Rank 24
Kimi K3Moonshot AIECI 158.6
Top text-to-image models
GPT Image 2.5 SunburstOpenAIArena 1,427
GPT Image 2.5 FlareOpenAIArena 1,401
GPT Image 2OpenAIArena 1,381
- New
MAI-Image-2.6MicrosoftArena 1,329
- New
Nano Banana 2.1GoogleArena 1,325
Grok Imagine Image 2.0xAIArena 1,317
Reve 2.1reveArena 1,300
Muse ImageMetaArena 1,269
Top text-to-video models
- New
Gemini Omni 1.2 FlashGoogleArena 1,540
Gemini Omni 1.1 FlashGoogleArena 1,513
Gemini Omni Flash PreviewGoogleArena 1,509
FLUX 3 VideoBlack Forest LabsArena 1,491
Grok Imagine Video 1.5xAIArena 1,488
Seedance 2.0ByteDance SeedArena 1,483
Seedance 2.5ByteDance SeedArena 1,479
Wan v3.0 VideoAlibaba (Qwen)Arena 1,476
Start from the output you need
Prompting is medium-specific. A prompt that produces a clean product photograph looks nothing like one that produces a passing test suite.
-
01
Text prompts
Prompts for the writing you actually ship: articles, landing pages, emails, summaries and rewrites.
-
02
Image prompts
Describe the shot like a photographer or art director, and the model stops guessing.
-
03
Video prompts
One shot, one movement, one action. Video prompts fail when they try to be a whole scene.
-
04
Audio prompts
Music and voice models respond to arrangement notes, tempo and mix language — not to genre names alone.
-
05
Avatar prompts
The hard part of avatars is not the first image, it is the second one looking like the same person.
-
06
Software prompts
Coding agents fail on missing context, not missing intelligence. Give them the constraints a new teammate would need.
-
07
Marketing prompts
Marketing prompts get good when you feed them your data instead of asking for best practices.
Same intent, different phrasing
Midjourney wants a subject-first shot list. Claude wants tagged sections. Kiro and Antigravity want acceptance criteria and verification commands.
-
01
Prompt for Midjourney
Midjourney rewards concrete nouns, camera language and a short parameter tail. Adjective stacking does very little.
-
02
Prompt for Gemini
Gemini is at its best when you hand it a lot of material and a precise job to do with it.
-
03
Prompt for Kiro
Kiro works from your project context. The prompt that pays off most is the one you write once as a steering file.
-
04
Prompt for Antigravity
Antigravity agents work across editor, terminal and browser. Prompt them like you would brief a contractor who has to show evidence.
-
05
Prompt for ChatGPT
Most ChatGPT problems are input problems. Set up your instructions once, then keep each request to a single job.
-
06
Prompt for Claude
Claude follows structure well. Tag your inputs, separate instructions from material, and it stays on the rails.
-
07
Prompt for Sora
Write Sora prompts like shot cards. One subject, one action, one camera move, one light setup.
-
08
Prompt for Veo
Veo is strongest when you approve the frame first and ask only for motion and sound.
Seven parts, every time
Medium and model change the details, not the skeleton. When output disappoints, one of these is missing.
Role and audience
Who produces this, and who reads it. Sets vocabulary and depth.
One task
A single deliverable. Anything with an "and then" belongs in a second prompt.
Context you supply
Source text, product facts, code, screenshots. Never rely on recall for something you can paste.
Constraints
Length, format, tone, banned words, technical limits. Most of the quality lives here.
Output shape
Headings, a table, JSON, a shot list. Name it rather than hoping for it.
Uncertainty rule
How to flag doubt, and what to do when the answer is not in the material.
Scope fence
What to leave alone. Essential once a model can edit files or run commands.
Fast diagnostic: read your prompt as a competent stranger would. Every question you would need to ask is a gap the model fills by guessing.
Learn it from the source
Two references worth reading in full before anything else. Both are vendor documentation, maintained by the people who build the models.
- What is prompt engineering? — Google Cloud cloud.google.com ↗ Plain-language overview of prompt engineering, prompt types and where it fits in a production workflow.
- Prompt engineering guide — OpenAI API docs developers.openai.com ↗ The API-side reference: message roles, instruction placement, reasoning controls and structured output.
Pick a medium and get going
No account, no paywall, no newsletter gate. Every template is copy-and-go, and every page explains why it is shaped the way it is.