Serverless inference is priced per token.
Fireworks AI Pricing → · 2026-11-03T17:00:48.261Z
| Model | Field | Old → New (/1M) | Change |
|---|---|---|---|
| DeepSeek V4.1 Flash 1017 Ultra-fast (Preview) | input | — → $2.4 | |
| DeepSeek V4.1 Flash 1017 Ultra-fast (Preview) | output | — → $9.6 | |
| DeepSeek V4.1 Flash 1017 Ultra-fast (Preview) | cached input | — → $0.048 |
- Serverless inference is priced per token. For how Standard, Priority, and Fast modes work and how to select one, see [Serverless Modes](https://docs.fireworks.ai/serverless/serverless-modes) + Serverless inference is priced per token. For how Standard, Priority, Fast, and Ultra-fast (Preview) modes work and how to select one, see [Serverless Modes](https://docs.fireworks.ai/serverless/serverless-modes) - Per-model pricing for headline models. Fast variants appear as adjacent rows. In each **Standard** or **Priority** cell, prices are **input / cached input / output** (USD per 1M tokens), in that order. + Per-model pricing for headline models. Fast and Ultra-fast (Preview) variants appear as adjacent rows. In each **Standard** or **Priority** cell, prices are **input / cached input / output** (USD per 1M tokens), in that order. + | [DeepSeek V4.1 Flash 1017 Ultra-fast (Preview)](https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash-1017) | $2.40 / $0.048 / $9.60 | — |