GPT-4 Turbo vs GPT-6.1 Sol
Lower and Larger mark one number at a time; they don’t rank the models. How well a model does depends on your task; see Benchmarks for measured results.
| Detail | GPT-4 Turboopenai/gpt-4-turbo | GPT-6.1 Solopenai/gpt-6.1-sol |
|---|---|---|
| Maker | openai | openai |
| Kind | Chat | Chat |
| Input per 1M tokens | $10.50 | $2.10 Lower |
| Cached input per 1M tokens | Not applicable | $0.105 |
| Cache write per 1M tokens | Not applicable | $2.625 |
| Output per 1M tokens | $31.50 | $10.50 Lower |
| Context window | 128,000 tokens | 1,050,000 tokens Larger |
| Max output | 4,096 tokens | 128,000 tokens Larger |
| Capabilities | Tool use, vision | Reasoning, tool use, vision, file input, web search, fast |
| Takes | Text, image | Text, image, pdf |
| Returns | Text | Text |
| Zero data retention | Yes, on every provider | Not on every provider |
| No training on requests | Yes, on every provider | Yes, on every provider |
| Released | 2024-04-09 | 2026-09-29 |
Example costs
Example requests, priced at today’s rates with no cached input.
| Example request | GPT-4 Turbo | GPT-6.1 Sol |
|---|---|---|
| 1,000 tokens in, 200 out | $0.0168 | $0.0042 |
| 10,000 tokens in, 1,000 out | $0.1365 | $0.0315 |
| 100,000 tokens in, 4,000 out | $1.176 | $0.252 |