> ## Documentation Index > Fetch the complete documentation index at: https://fireworks.ai/docs/llms.txt > Use this file to discover all available pages before exploring further. # Serverless Pricing > Per-token serverless pricing for text, vision, and embedding models on Fireworks, including Standard, Priority, Fast, and Ultra-fast (Preview) serverless mode rates. ## Overview 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://fireworks.ai/docs/serverless/serverless-modes.md). Every text or vision request is billed across three dimensions: * **Input tokens** — what you send to the model. * **Cached input tokens** — input tokens served from [prompt cache](https://fireworks.ai/docs/guides/prompt-caching.md), priced lower. * **Output tokens** — what the model generates. Embeddings are billed only on input tokens. ## How pricing works * Prices below are **per 1 million tokens** in US dollars. * **Batch inference** is billed at **50% of serverless pricing** on both input and output. See [Batch inference](https://fireworks.ai/docs/guides/batch-inference.md). ## Text and vision models 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. | Model | Standard | Priority | | - | - | - | | [Ember-1](https://app.fireworks.ai/models/fireworks/ember-1) | \$3.00 / \$0.30 / \$15.00 | \$3.75 / \$0.375 / \$18.75 | | [Muse Spark Open](https://app.fireworks.ai/models/fireworks/muse-spark-open) | \$1.25 / \$0.15 / \$4.25 | \$1.875 / \$0.225 / \$6.375 | | [Kimi K3.1 Pro](https://app.fireworks.ai/models/fireworks/kimi-k3p1-pro) | \$2.00 / \$0.20 / \$10.00 | \$3.00 / \$0.30 / \$15.00 | | [Kimi K3](https://app.fireworks.ai/models/fireworks/kimi-k3) | \$3.00 / \$0.30 / \$15.00 | \$3.75 / \$0.375 / \$18.75 | | [Kimi K3 Fast](https://app.fireworks.ai/models/fireworks/kimi-k3) | \$4.50 / \$0.45 / \$22.50 | — | | [Kimi K3 (US)](https://app.fireworks.ai/models/fireworks/kimi-k3) | \$4.50 / \$0.45 / \$22.50 | \$5.625 / \$0.5625 / \$28.125 | | [DeepSeek V4.1 Flash](https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash) | \$0.30 / \$0.006 / \$1.20 | \$0.375 / \$0.0075 / \$1.50 | | [DeepSeek V4.1 Flash (US)](https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash) | \$0.45 / \$0.009 / \$1.80 | \$0.5625 / \$0.01125 / \$2.25 | | [DeepSeek V4.1 Flash 1017](https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash-1017) | \$0.30 / \$0.006 / \$1.20 | \$0.375 / \$0.0075 / \$1.50 | | [DeepSeek V4.1 Flash 1017 Ultra-fast (Preview)](https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash-1017) | \$2.40 / \$0.048 / \$9.60 | — | | [DeepSeek V4.1 Flash 1017 (US)](https://app.fireworks.ai/models/fireworks/deepseek-v4p1-flash-1017) | \$0.45 / \$0.009 / \$1.80 | \$0.5625 / \$0.01125 / \$2.25 | | [GLM 5.3 Flash](https://app.fireworks.ai/models/fireworks/glm-5p3-flash) | \$0.15 / \$0.03 / \$0.50 | \$0.1875 / \$0.0375 / \$0.625 | | [GLM 5.3 Flash (US)](https://app.fireworks.ai/models/fireworks/glm-5p3-flash) | \$0.225 / \$0.045 / \$0.75 | \$0.28125 / \$0.05625 / \$0.9375 | | [Ultramarine 1 Flash (US)](https://app.fireworks.ai/models/fireworks/ultramarine-1-flash-us) | \$0.15 / \$0.03 / \$0.50 | \$0.1875 / \$0.0375 / \$0.625 | | [GLM 5.3](https://app.fireworks.ai/models/fireworks/glm-5p3) | \$1.40 / \$0.26 / \$4.40 | \$1.75 / \$0.325 / \$5.50 | | [GLM 5.3 (US)](https://app.fireworks.ai/models/fireworks/glm-5p3) | \$2.10 / \$0.39 / \$6.60 | \$2.625 / \$0.4875 / \$8.25 | | [GLM 5.3 Fast](https://app.fireworks.ai/models/fireworks/glm-5p3) | \$2.10 / \$0.39 / \$6.60 | — | | [Qwen 3.8 Max](https://app.fireworks.ai/models/fireworks/qwen3p8-max) | \$2.00 / \$0.25 / \$6.00 | \$3.00 / \$0.375 / \$9.00 | | [MiniMax M3](https://app.fireworks.ai/models/fireworks/minimax-m3) | \$0.30 / \$0.06 / \$1.20 | \$0.45 / \$0.09 / \$1.80 | | [OpenAI GPT OSS 120B](https://app.fireworks.ai/models/fireworks/gpt-oss-120b) | \$0.15 / \$0.015 / \$0.60 | \$0.18 / \$0.018 / \$0.72 | | [NVIDIA Nemotron 3.5 Lightning 30B A3B](https://app.fireworks.ai/models/fireworks/nemotron-lightning-3p5-30b-a3b) | \$0.05 / \$0.01 / \$0.20 | \$0.0625 / \$0.0125 / \$0.25 | | [NVIDIA Nemotron 3 Ultra (Preview)](https://app.fireworks.ai/models/fireworks/nemotron-3-ultra-nvfp4) | \$0.60 / \$0.12 / \$2.40 | \$0.75 / \$0.15 / \$3.00 | **—** in the Priority column means Priority is not available for that model. This pricing table is the source of truth for Priority availability. Muse Spark Open runs on US-only capacity. The 50% US-only premium is waived, so the rates in that row are what you pay. ## Decision models [Rune 26B-A4B](https://app.fireworks.ai/models/fireworks/rune) is a System One decision model. It reads the input once and returns calibrated probabilities for a set of typed questions, and it never generates output tokens. You pay for input only, so the rates below cover the full cost of a request. | Model | Standard | Priority | | - | - | - | | [Rune 26B-A4B](https://app.fireworks.ai/models/fireworks/rune) | \$0.042 / \$0.0084 / \$0.00 | — | Cached input is 20% of the input rate. Call it with `model: "accounts/fireworks/models/rune"`; see the [System One decisions API](https://fireworks.ai/docs/api-reference/post-systemone.md) for the request shape. Rune runs on US capacity. There is no US-capacity premium, so the rates above are what you pay. ## Other base models — by size and architecture For any text or vision model not listed individually, pricing is set by parameter count and architecture. These size-based prices apply uniformly to input and output (no separate cached-input rate): | Model | \$ / 1M tokens | | - | - | | Less than 4B parameters | \$0.10 | | 4B – 16B parameters | \$0.20 | | More than 16B parameters | \$0.90 | | MoE up to 56B parameters (e.g. Mixtral 8x7B) | \$0.50 | | MoE 56.1B – 176B parameters (e.g. DBRX, Mixtral 8x22B) | \$1.20 | ## Embeddings Embeddings are billed per 1M input tokens. | Base model parameter count | \$ / 1M input tokens | | - | - | | up to 150M | \$0.008 | | 150M – 350M | \$0.016 | | Qwen3 8B | \$0.10 | ## Notes * For account-level controls (spend tiers, monthly spend limits, on-demand GPU quotas), see [Account quotas](https://fireworks.ai/docs/guides/quotas_usage/account-quotas.md). This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.