AI models for data analysis
LLM data analysis: clean tables, propose queries, explain charts. Semrush ~720/mo for “best ai for data analysis”. Pair reasoning for logic with vision when the input is a chart.
Models in this collection
| Model | Type | Context | Price |
|---|---|---|---|
| Chat | 272k tokens | $5.4503/M in · $32.7018/M out | |
| Chat | 1M tokens | $3.2702/M in · $16.3509/M out | |
| Chat | 2M tokens | $1.3626/M in · $10.9006/M out | |
| Chat | 200k tokens | $1.1991/M in · $4.7963/M out | |
| Chat | 1M tokens | $0.4742/M in · $0.9484/M out | |
| Chat | 1M tokens | $1.3626/M in · $2.7251/M out | |
| Chat | 272k tokens | $0.8175/M in · $4.9053/M out | |
| Chat | 1M tokens | $0.327/M in · $2.7251/M out |
Why these models
GPT/Claude for insight narrative; o3-mini/DeepSeek/Grok Reasoning for logic; Flash/mini for cheap iterative EDA.
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 it run code?
- The model proposes; your sandbox (Python/SQL) executes. Do not assume native execution.
- Large CSVs?
- Summarize or sample first. Or embeddings + RAG over rows. Long context helps but is not magic.
- Charts as images?
- Yes with vision (Gemini/Claude). See Vision Models.