GPT OSS 120 B vs DeepSeek V4 Flash 0731: cost comparison
Prices updated 2026-11-07 · computed from live provider data
Short answer: DeepSeek V4 Flash 0731 is cheaper on a
3:1 input/output blend — $0.072 per million tokens versus
$0.093, a 23% difference.
DeepSeek V4 Flash 0731 offers the larger context window at 1,048,576 tokens, against 128,000 for GPT OSS 120 B.
Head to head
| GPT OSS 120 B | DeepSeek V4 Flash 0731 | |
|---|---|---|
| Input, per 1M tokens | $0.047 | $0.048 |
| Output, per 1M tokens | $0.230 | $0.144 |
| Blended 3:1, per 1M | $0.093 | $0.072 |
| Context window | 128,000 | 1,048,576 |
| Vendor | kyma | deepseek |
Monthly cost at real volumes
| Workload (input / output) | GPT OSS 120 B | DeepSeek V4 Flash 0731 |
|---|---|---|
| 1M in / 250K out | $0.105 | $0.084 |
| 10M in / 2.5M out | $1.05 | $0.840 |
| 100M in / 25M out | $10.49 | $8.40 |
Which should you pick?
Pick DeepSeek V4 Flash 0731 when you need the longer context window (1,048,576 vs 128,000 tokens). Pick DeepSeek V4 Flash 0731 when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.