F
Fireworks
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
93.3%2026-07-212026-08-19
Inference Latency
OpenAI: gpt-oss-20b412ms TTFT · 151 TPS
DeepSeek: DeepSeek V4 Flash 0731793ms TTFT · 85 TPS
MiniMax: MiniMax M2.72844ms TTFT · 188 TPS
Meta: Muse Glimmer 30B888ms TTFT · 57 TPS
MoonshotAI: Kimi K2.6601ms TTFT · 64 TPS
DeepSeek: DeepSeek V4 Pro 08131077ms TTFT · 57 TPS
Z.ai: GLM 5.21644ms TTFT · 41 TPS
DeepSeek: DeepSeek V4 Pro 04232595ms TTFT · 40 TPS
Z.ai: GLM 5.2873ms TTFT · 143 TPS
MoonshotAI: Kimi K34056ms TTFT · 33 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| OpenAI: gpt-oss-20b | $0.07 | $0.30 | 412ms | 151 |
| DeepSeek: DeepSeek V4 Flash 0731 | $0.14 | $0.28 | 793ms | 85 |
| MiniMax: MiniMax M2.7 | $0.30 | $1.20 | 2844ms | 188 |
| Meta: Muse Glimmer 30B | $0.35 | $1.50 | 888ms | 57 |
| MoonshotAI: Kimi K2.6 | $0.95 | $4.00 | 601ms | 64 |
| DeepSeek: DeepSeek V4 Pro 0813 | $1.32 | $3.96 | 1077ms | 57 |
| Z.ai: GLM 5.2 | $1.40 | $4.40 | 1644ms | 41 |
| DeepSeek: DeepSeek V4 Pro 0423 | $1.74 | $3.48 | 2595ms | 40 |
| Z.ai: GLM 5.2 | $2.10 | $6.60 | 873ms | 143 |
| MoonshotAI: Kimi K3 | $3.00 | $15.00 | 4056ms | 33 |
Community Reviews
4.5★★★★★(2 reviews)
clouduser42
★★★★★2025-06-15
Reliable service, great API documentation.
mlresearcher
★★★★☆2025-06-10
Good performance but support could be faster.