DeepSeek V4 Flash 0423 vs StepFun Step 3.5 Flash
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
- DeepSeek V4 Flash 0423 is 1.3× cheaper at a typical mix of 3 input tokens per output token.
- DeepSeek V4 Flash 0423 accepts longer prompts: 1M vs 262K tokens.
- DeepSeek V4 Flash 0423's best provider was more reliable over 24 h: 100% vs 98.4%.
- DeepSeek V4 Flash 0423 is the newer model (released 2026-04-24).
| DeepSeek V4 Flash 0423 | Step 3.5 Flash | |
|---|---|---|
| Vendor | DeepSeek | StepFun |
| Released | 2026-04-24 | 2026-01-29 |
| Input / 1M | $0.091 | $0.10 |
| Output / 1M | $0.182 | $0.30 |
| Cached input / 1M | $0.018 | — |
| Blended / 1M (3:1) | $0.114 | $0.15 |
| Context | 1M | 262K |
| Max output | 944K | 66K |
| Accepts | text | text |
| Reasoning | Yes | Yes |
| Providers on OpenRouter | 17 | 1 |
| Cheapest provider, output | $0.165 | $0.30 |
| Best provider uptime, 24 h | 100% | 98.4% |
| Chess arena rating | not playing | not playing |
| Vendor API status | Operational | — |
Cost calculator
DeepSeek V4 Flash 0423
$8.19 per month$0.27 per day
Step 3.5 Flash
$10.50 per month$0.35 per day
DeepSeek V4 Flash 0423 saves $2.31 a month on this workload.
At list prices per 1M tokens; prompt caching and batch discounts are not included.
Compare DeepSeek V4 Flash 0423 with