AI models for ads, copy, and creatives
Performance creative needs fast variation: hooks, CTAs, UGC scripts, subject lines. Pair a strong creative model for concepts with a cheap one for mass variants — same Geek Hub API.
Models in this collection
| Model | Type | Context | Price |
|---|---|---|---|
 GPT-5.5OpenAI | Chat | 272k tokens | $5.4503/M in · $32.7018/M out |
 Gemini 2.5 ProGoogle | Chat | 2M tokens | $1.3626/M in · $10.9006/M out |
 Claude Sonnet 5Anthropic | Chat | 1M tokens | $3.2702/M in · $16.3509/M out |
 Grok 4.3xAI | Chat | 1M tokens | $1.3626/M in · $2.7251/M out |
| GPT-4.1 mini (legacy)OpenAI | Chat | 1M tokens | $0.436/M in · $1.7441/M out |
| Gemini 2.5 FlashGoogle | Chat | 1M tokens | $0.327/M in · $2.7251/M out |
| Claude Haiku 4.5Anthropic | Chat | 200k tokens | $1.0901/M in · $5.4503/M out |
Why these models
GPT-5.5, Gemini Pro, and Sonnet for briefs and angles; Grok for a more spontaneous tone; Flash/mini/Haiku to generate dozens of variants without inflating creative CPA.
Use them with Geek Hub
One OpenAI-compatible base URL and API key. Swap any model id from this list without rewriting your client.
Get an API keyFAQ
- Can I generate image/video creatives here?
- This collection is chat/copy. For image and video use the Image Models and Video Models collections; the same API key works.
- How do I cut cost on copy A/B?
- Concepts with a strong model; 20–50 variants with Flash/mini. Store the model id per stage in your pipeline.
- Does this work for LATAM Spanish?
- Yes. Listed models handle Spanish well; set market and tone in the system prompt.