Fireworks AI

モデルアグリゲーター

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.

モデル

プロンプトキャッシュ

✓

バッチ割引

—

Tool Calling

—

ウェブサイトを見る →公式料金を見る →

モデル29

					モダリティ
DeepSeek V4 FlashDeepSeek	¥22	¥44	¥4	—	text
DeepSeek V4 Flash (0731)DeepSeek	¥34	¥103	¥1	—	text
DeepSeek V4 Flash Vision ExpDeepSeek	¥34	¥103	¥1	—	text
DeepSeek V4 ProDeepSeek	¥272	¥544	¥23	—	text
DeepSeek V4 Pro (0813)DeepSeek	¥206	¥619	¥7	—	text
GLM 5.1GLM	¥219	¥688	¥41	—	text
GLM 5.1 FastGLM	¥438	¥1375	¥81	—	text
GLM 5.2GLM	¥219	¥688	¥22	—	text
GLM 5.2 FastGLM	¥328	¥1031	¥33	—	text
GLM 5.2 Fast USGLM	¥328	¥1031	¥33	—	text
GLM 5.3GLM	¥219	¥688	¥41	—	text
GLM 5.3 FastGLM	¥328	¥1031	¥61	—	text
GLM 5.3 FlashGLM	¥23	¥78	¥5	—	text
Kimi K2.6Kimi	¥148	¥625	¥25	—	text
Kimi K2.6 FastKimi	¥313	¥1250	¥47	—	text
Kimi K2.7 CodeKimi	¥148	¥625	¥30	—	text
Kimi K2.7 Code FastKimi	¥297	¥1250	¥59	—	text
Kimi K3Kimi	¥469	¥2344	¥47	—	text
Kimi K3 FastKimi	¥703	¥3516	¥70	—	text
Kimi K3 USKimi	¥516	¥2578	¥52	—	text
MiniMax M2.7MiniMax	¥47	¥188	¥9	—	text
MiniMax M3MiniMax	¥47	¥188	¥9	—	text
Muse Glimmer 30B	¥55	¥234	¥6	—	text
NVIDIA Nemotron 3 Ultra (Preview)Nemotron	¥94	¥375	¥19	—	text
NVIDIA Nemotron 3.5 Lightning 30B A3BNemotron	¥8	¥31	¥2	—	text
OpenAI GPT OSS 120BGPT-OSS	¥23	¥94	¥2	—	text
OpenAI GPT OSS 20BGPT-OSS	¥11	¥47	¥5	—	text
Qwen 3.7 PlusQwen	¥63	¥250	¥13	—	text
Qwen 3.8 MaxQwen	¥313	¥938	¥39	—	text