Website
Updated 12/8/2025
Fireworks AI interface preview
Performance Stats
Avg Speed
147.26t/s
Latency
4.15s
Total Tests
80
Models
11
Fireworks AI logo

Fireworks AI

About Fireworks AI

Fireworks AI provides a cloud platform for running and fine-tuning open-source AI models with optimized inference for production applications.

OpenAIgpt-ossDeepSeekDeepSeek-V3ChatGLMGLM-4QwenQwen3QwenQwen3-VL

Health Check

0%Recent availability
History (72 pts)
PastNow

Supported Models

ModelSpeedLatencyTests
accounts/fireworks/models/gpt-oss-20b
359.18 t/s
1.14s
10
accounts/fireworks/models/minimax-m2p1
185.81 t/s
1.91s
10
accounts/fireworks/models/gpt-oss-120b
144.71 t/s
0.79s
10
accounts/fireworks/models/kimi-k2-thinking
127.75 t/s
3.47s
5
accounts/fireworks/models/deepseek-v3p2
114.61 t/s
0.49s
5
accounts/fireworks/models/deepseek-v3p1-terminus
112.67 t/s
0.89s
5
accounts/fireworks/models/glm-4p7
105.59 t/s
10.50s
20
accounts/fireworks/models/qwen3-235b-a22b-instruct-2507
78.64 t/s
0.62s
5
accounts/fireworks/models/glm-4p6
69.26 t/s
10.03s
5
accounts/fireworks/models/qwen3-vl-235b-a22b-thinking
51.54 t/s
1.25s
5
accounts/fireworks/models/qwen3-vl-235b-a22b-thinking
51.54 t/s
1.25s
5

Recent Test Records

TimeModelSpeedLatency
Jan 13, 04:45 PMaccounts/fireworks/models/glm-4p7
121.26 t/s
10.59s
Jan 13, 04:39 PMaccounts/fireworks/models/glm-4p7
120.41 t/s
8.25s
Jan 13, 04:22 PMaccounts/fireworks/models/glm-4p7
82.21 t/s
11.73s
Jan 13, 02:55 AMaccounts/fireworks/models/gpt-oss-120b
136.18 t/s
0.85s
Jan 13, 01:51 AMaccounts/fireworks/models/gpt-oss-120b
153.24 t/s
0.74s
Jan 13, 01:23 AMaccounts/fireworks/models/minimax-m2p1
192.15 t/s
2.12s
Jan 13, 01:22 AMaccounts/fireworks/models/kimi-k2-thinking
127.75 t/s
3.47s
Jan 13, 01:21 AMaccounts/fireworks/models/glm-4p6
69.26 t/s
10.03s
Jan 13, 01:17 AMaccounts/fireworks/models/deepseek-v3p2
114.61 t/s
0.49s
Jan 13, 01:15 AMaccounts/fireworks/models/qwen3-vl-235b-a22b-thinking
51.54 t/s
1.25s