Fireworks AI logo

Fireworks AI

模型集成商

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.

模型
16
提示缓存
批量折扣
Tool Calling
模型16
模型输入价格输出价格
DeepSeek V4 FlashDeepSeek¥0.9478¥1.9
DeepSeek V4 ProDeepSeek¥11.78¥23.56
GLM 5.1GLM¥9.48¥29.79
GLM 5.1 FastGLM¥18.96¥59.58
GLM 5.2GLM¥9.48¥29.79
GLM 5.2 FastGLM¥14.22¥44.68
Kimi K2.6Kimi¥6.43¥27.08
Kimi K2.6 FastKimi¥13.54¥54.16
Kimi K2.7 CodeKimi¥6.43¥27.08
Kimi K2.7 Code FastKimi¥12.86¥54.16
MiniMax M2.7MiniMax¥2.03¥8.12
MiniMax M3MiniMax¥2.03¥8.12
NVIDIA Nemotron 3 Ultra (Preview)Nemotron¥4.06¥16.25
OpenAI GPT OSS 120BGPT-OSS¥1.02¥4.06
OpenAI GPT OSS 20BGPT-OSS¥0.4739¥2.03
Qwen 3.7 PlusQwen¥2.71¥10.83