DeepSeek V4 Flash Vision Exp vs OpenAI gpt-oss-120b
Side by side from live data: prices, limits, who serves each model and how reliably, and how they do on our chess arena.
In short
- gpt-oss-120b is 1.2× cheaper at a typical mix of 3 input tokens per output token.
- DeepSeek V4 Flash Vision Exp accepts longer prompts: 1M vs 131K tokens.
- gpt-oss-120b output costs $0.15 per 1M via Near AI, against the list price of $0.60.
- DeepSeek V4 Flash Vision Exp is the newer model (released 2026-08-21).
| DeepSeek V4 Flash Vision Exp | gpt-oss-120b | |
|---|---|---|
| Vendor | DeepSeek | OpenAI |
| Released | 2026-08-21 | 2025-08-05 |
| Input / 1M | $0.216 | $0.15 |
| Output / 1M | $0.647 | $0.60 |
| Cached input / 1M | $0.0069 | $0.075 |
| Blended / 1M (3:1) | $0.323 | $0.262 |
| Context | 1M | 131K |
| Max output | 262K | 66K |
| Accepts | text, image | text |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 3 | 25 |
| Cheapest provider, output | $0.647 | $0.15 |
| Best provider uptime, 24 h | 100% | 100% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | Operational |
Cost calculator
DeepSeek V4 Flash Vision Exp
$22.64 per month$0.75 per day
gpt-oss-120b
$18.00 per month$0.60 per day
gpt-oss-120b saves $4.64 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare DeepSeek V4 Flash Vision Exp with