Documentation Index
Fetch the complete documentation index at: https://docs.fireworks.ai/llms.txt
Use this file to discover all available pages before exploring further.
Overview
Serverless inference is priced per token. 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, 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.
Text and vision models
Per-model pricing for headline models. Fast variants appear as adjacent rows.
| Model | Input | Cached input | Output |
|---|
| Kimi K2.6 | $0.95 | $0.16 | $4.00 |
| Kimi K2.6 Turbo (Fast, Preview) | $2.00 | $0.30 | $8.00 |
| Kimi K2.5 | $0.60 | $0.10 | $3.00 |
| DeepSeek V4 Pro | $1.74 | $0.145 | $3.48 |
| DeepSeek V3 family | $0.56 | $0.28 | $1.68 |
| GLM 5.1 | $1.40 | $0.26 | $4.40 |
| GLM 5.1 Fast (Preview) | $2.80 | $0.52 | $8.80 |
| GLM 5 | $1.00 | $0.20 | $3.20 |
| GLM 4.7 | $0.60 | $0.30 | $2.20 |
| MiniMax 2.7 | $0.30 | $0.06 | $1.20 |
| MiniMax 2.5 | $0.30 | $0.03 | $1.20 |
| Qwen3 VL 30B A3B | $0.15 | $0.075 | $0.60 |
| OpenAI GPT OSS 120B | $0.15 | $0.015 | $0.60 |
| OpenAI GPT OSS 20B | $0.07 | $0.035 | $0.30 |
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 tier 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 |
Priority serverless
Priority routes traffic above the Standard tier for higher reliability during peak periods, at a premium per-token price. Opt in by setting service_tier: "priority" on OpenAI-compatible chat completions or the Anthropic-compatible messages API. See Serverless Priority and Fast for usage.
| Model | Input | Cached input | Output |
|---|
| Kimi K2.6 | $1.50 | $0.22 | $6.00 |
| GLM 5.1 | $2.10 | $0.39 | $6.60 |
| MiniMax 2.7 | $0.45 | $0.09 | $1.80 |
| OpenAI GPT OSS 120B | $0.18 | $0.018 | $0.72 |
Priority tier is in Preview. Available models and pricing may change as the program expands.
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 budget, on-demand GPU quotas), see Account quotas.
