Fireworks AI

Model Aggregator

Fireworks AI is a high-performance serverless inference platform for open and open-weight frontier models (DeepSeek, GLM, Qwen, Kimi, MiniMax, GPT-OSS), offering Standard and Priority throughput tiers with cached-input discounts.

Models

Prompt Caching

✓

Batch Discount

—

Tool Calling

—

Visit Website →View Official Pricing →

Model16

Model	Input Price	Output Price	Cached Input	Context	Modality
DeepSeek V4 FlashDeepSeek	$0.14	$0.28	$0.028	—	text
DeepSeek V4 ProDeepSeek	$1.74	$3.48	$0.145	—	text
GLM 5.1GLM	$1.4	$4.4	$0.26	—	text
GLM 5.1 FastGLM	$2.8	$8.8	$0.52	—	text
GLM 5.2GLM	$1.4	$4.4	$0.14	—	text
GLM 5.2 FastGLM	$2.1	$6.6	$0.21	—	text
Kimi K2.6Kimi	$0.95	$4	$0.16	—	text
Kimi K2.6 FastKimi	$2	$8	$0.3	—	text
Kimi K2.7 CodeKimi	$0.95	$4	$0.19	—	text
Kimi K2.7 Code FastKimi	$1.9	$8	$0.38	—	text
MiniMax M2.7MiniMax	$0.3	$1.2	$0.06	—	text
MiniMax M3MiniMax	$0.3	$1.2	$0.06	—	text
NVIDIA Nemotron 3 Ultra (Preview)Nemotron	$0.6	$2.4	$0.12	—	text
OpenAI GPT OSS 120BGPT-OSS	$0.15	$0.6	$0.015	—	text
OpenAI GPT OSS 20BGPT-OSS	$0.07	$0.3	$0.035	—	text
Qwen 3.7 PlusQwen	$0.4	$1.6	$0.08	—	text