Index · comparison
GPT-4o mini vs DeepSeek Chat
GPT-4o mini is 45% cheaper than DeepSeek Chat ($0.75 vs $1.37 blended per 1M tokens).
GPT-4o mini on OpenAI vs DeepSeek Chat on DeepSeek — price performance. Every figure below is the value shown on each model's own endpoint page, with its source and verification date.
| Metric | GPT-4o mini | DeepSeek Chat |
|---|---|---|
| Input $/1M | $0.15 | $0.27 |
| Output $/1M | $0.6 | $1.1 |
| Blended $/1M | $0.75 | $1.37 |
| Context window | 128K | 64K |
| Max output | 16K | 8K |
Highlighted cell = better on that row (lower price/latency, higher context/intelligence/throughput). "—" = not measured for that model.
Which to pick
On blended token price, GPT-4o mini is the cheaper of the two ($0.75 vs $1.37 per 1M). Price alone rarely settles it: check the intelligence index and latency rows above against your workload, and open each endpoint page for the full price history and provider terms.
Sources: GPT-4o mini endpoint · DeepSeek Chat endpoint · GPT-4o mini price verified 2026-09-05 · DeepSeek Chat price verified 2026-09-03