GPT OSS 20B vs DeepSeek V4 Flash
Side-by-side API pricing comparison · Fireworks vs Fireworks
🏆
GPT OSS 20B is 13.5% cheaper on blended cost ($0.185 vs $0.210/Mtok)
GPT OSS 20B
by Fireworks
Current budget Open weightsInput
$0.070/Mtok
Output
$0.300/Mtok
✓ Cheaper
| Blended avg | $0.185/Mtok |
|---|---|
| Cached input | $0.035/Mtok |
| Context | 128K tokens |
| Modality | text |
| Parameters | 20B |
| Released | Jan 1, 2026 |
DeepSeek V4 Flash
by Fireworks
Current budgetInput
$0.140/Mtok
Output
$0.280/Mtok
| Blended avg | $0.210/Mtok |
|---|---|
| Cached input | $0.028/Mtok |
| Context | 1M tokens |
| Modality | text |
| Parameters | Proprietary |
| Released | Dec 1, 2025 |
Cost at scale — 1M tokens (50/50 input/output)
| Volume | GPT OSS 20B | DeepSeek V4 Flash | Savings |
|---|---|---|---|
| 1M tokens | $0.19 | $0.21 | $0.03 (14.3%) |
| 10M tokens | $1.85 | $2.1 | $0.25 (11.9%) |
| 100M tokens | $18.5 | $21 | $2.5 (11.9%) |
| 1000M tokens | $185 | $210 | $25 (11.9%) |
Summary
GPT OSS 20B by Fireworks costs $0.070/Mtok input and $0.300/Mtok output, with a 128K-token context window. It supports text input.
DeepSeek V4 Flash by Fireworks costs $0.140/Mtok input and $0.280/Mtok output, with a 1M-token context window. It supports text input.
On a blended cost basis, GPT OSS 20B is 13.5% cheaper than DeepSeek V4 Flash.
Note: Pricing is per million tokens. Actual costs vary with usage patterns, prompt caching, and batch discounts. Always verify against official provider pricing pages.