Fireworks AI · Pricing Plans
Fireworks Ai Plans Pricing
Fireworks Ai Plans Pricing is the pricing profile for Fireworks AI on the APIs.io network — every figure transcribed verbatim from the provider’s own pricing page on 2026-10-07.
It defines 22 plans, including Embeddings - base model up to 150M params — $0.008; Embeddings - base model 150M - 350M params — $0.016; Embeddings - Qwen3 8B — $0.1, and 19 more.
The page prices API or platform usage directly, priced per call; the service is delivered as managed.
Tagged areas include Artificial Intelligence, LLM, Inference, Multi-Modal, and Fine-Tuning.
22 Plans
Prices the API
Basis: per call
Delivered: managed
Transcribed from the provider's pricing page on 2026-10-07 — fireworks.ai/pricing.
View Source
Artificial IntelligenceLLMInferenceMulti-ModalFine-TuningGPU
Plans
Embeddings - base model up to 150M params
per-use
$0.008 per per 1M input tokens
Embeddings - base model 150M - 350M params
per-use
$0.016 per per 1M input tokens
Embeddings - Qwen3 8B
per-use
$0.1 per per 1M input tokens
Managed Training LoRA SFT - models up to 16B
per-use
$0.50 per per 1M training tokens
Managed Training LoRA DPO - models up to 16B
per-use
$1.00 per per 1M training tokens
Managed Training Full Param SFT - models up to 16B
per-use
$1.00 per per 1M training tokens
Managed Training Full Param DPO - models up to 16B
per-use
$2.00 per per 1M training tokens
Managed Training LoRA SFT - 16.1B-80B
per-use
$3.00 per per 1M training tokens
Managed Training LoRA DPO - 16.1B-80B
per-use
$6.00 per per 1M training tokens
Managed Training LoRA SFT - 80B-300B
per-use
$6.00 per per 1M training tokens
Managed Training LoRA DPO - 80B-300B
per-use
$12.00 per per 1M training tokens
Managed Training LoRA SFT - >300B
per-use
$10.00 per per 1M training tokens
Managed Training Full Param DPO - >300B
per-use
$40.00 per per 1M training tokens
Serverless Training API - GLM 5.3 Flash prefill
per-use
$2.96 per per 1M prefill tokens
Serverless Training API - GLM 5.3 train
per-use
$14.58 per per 1M train tokens
Serverless Training API - Kimi K3 sample
per-use
$27.11 per per 1M sample tokens
On Demand H100 80 GB GPU
per-use
$8.00 per per hour
On Demand H200 141 GB GPU
per-use
$8.00 per per hour
On Demand B200 180 GB GPU
per-use
$13.00 per per hour
On Demand B300 288 GB GPU
per-use
$15.00 per per hour
On Demand GB300 288 GB GPU
per-use
$20.00 per per hour
Enterprise
none
Contact Us
Sources
Work with this as data
Every plan here is available over the APIs.io API and to AI agents over MCP.