GPT-5 vs GPT-6.1 Sol (Batch)
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-5openai/gpt-5 | GPT-6.1 Sol (Batch)openai/gpt-6.1-sol-batch |
|---|---|---|
| Maker | openai | openai |
| Kind | Chat | Chat |
| Input per 1M tokens | $1.3125 | $1.05 Lower |
| Cached input per 1M tokens | $0.13125 | $0.0525 |
| Cache write per 1M tokens | Same as input | $1.3125 |
| Output per 1M tokens | $10.50 | $5.25 Lower |
| Context window | 400,000 tokens | 1,050,000 tokens Larger |
| Max output | 128,000 tokens | 128,000 tokens |
| Capabilities | Reasoning, tool use, vision, file input, web search, fast | Reasoning, tool use, vision, file input |
| Takes | Text, image, pdf | 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 | 2025-08-07 | 2026-09-29 |
Example costs
Example requests, priced at today’s rates with no cached input.
| Example request | GPT-5 | GPT-6.1 Sol (Batch) |
|---|---|---|
| 1,000 tokens in, 200 out | $0.003413 | $0.0021 |
| 10,000 tokens in, 1,000 out | $0.023625 | $0.01575 |
| 100,000 tokens in, 4,000 out | $0.17325 | $0.126 |