Fireworks AI

Agregador de Modelos

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.

Modelos

Caché de Prompts

✓

Descuento por Lotes

—

Tool Calling

—

Visitar Sitio Web →Ver Precios Oficiales →

Modelo16

Modelo	Precio de Entrada	Precio de Salida	Entrada en Caché	Contexto	Modalidad
DeepSeek V4 FlashDeepSeek	€0.1229	€0.2458	€0.0246	—	text
DeepSeek V4 ProDeepSeek	€1.53	€3.05	€0.1273	—	text
GLM 5.1GLM	€1.23	€3.86	€0.2282	—	text
GLM 5.1 FastGLM	€2.46	€7.72	€0.4565	—	text
GLM 5.2GLM	€1.23	€3.86	€0.1229	—	text
GLM 5.2 FastGLM	€1.84	€5.79	€0.1843	—	text
Kimi K2.6Kimi	€0.8339	€3.51	€0.1404	—	text
Kimi K2.6 FastKimi	€1.76	€7.02	€0.2633	—	text
Kimi K2.7 CodeKimi	€0.8339	€3.51	€0.1668	—	text
Kimi K2.7 Code FastKimi	€1.67	€7.02	€0.3336	—	text
MiniMax M2.7MiniMax	€0.2633	€1.05	€0.0527	—	text
MiniMax M3MiniMax	€0.2633	€1.05	€0.0527	—	text
NVIDIA Nemotron 3 Ultra (Preview)Nemotron	€0.5267	€2.11	€0.1053	—	text
OpenAI GPT OSS 120BGPT-OSS	€0.1317	€0.5267	€0.0132	—	text
OpenAI GPT OSS 20BGPT-OSS	€0.0614	€0.2633	€0.0307	—	text
Qwen 3.7 PlusQwen	€0.3511	€1.4	€0.0702	—	text