C
CoreWeave
AGGREGATEDINFERENCE
N/A
Uptime
N/A
Rating
30-Day Uptime
100%2026-09-192026-10-18
Inference Latency
OpenAI: gpt-oss-120b260ms TTFT · 93 TPS
OpenAI: gpt-oss-20b109ms TTFT · 214 TPS
IBM: Granite 4.1 8B259ms TTFT · 101 TPS
NVIDIA: Nemotron 3.5 Lightning213ms TTFT · 344 TPS
Google: Gemma 4 31B768ms TTFT · 39 TPS
Google: Gemma 4 26B A4B 249ms TTFT · 67 TPS
IBM: Granite 4.2 8B223ms TTFT · 91 TPS
DeepSeek: DeepSeek V4 Flash 0731409ms TTFT · 116 TPS
DeepSeek: DeepSeek V4.1 Flash468ms TTFT · 224 TPS
NVIDIA: Nemotron 3.5 Super VL601ms TTFT · 221 TPS
Z.ai: GLM 5.3 Flash520ms TTFT · 199 TPS
Meta: Llama 3.1 8B Instruct212ms TTFT · 138 TPS
MiniMax: MiniMax M3473ms TTFT · 129 TPS
Qwen: Qwen3.6 35B A3B427ms TTFT · 141 TPS
Qwen: Qwen3.8 27B1514ms TTFT · 43 TPS
DeepSeek: DeepSeek V3.1188ms TTFT · 87 TPS
Z.ai: GLM 5.2383ms TTFT · 191 TPS
MoonshotAI: Kimi K2.6539ms TTFT · 47 TPS
MoonshotAI: Kimi K2.7 Code766ms TTFT · 44 TPS
Meta: Llama 3.3 70B Instruct118ms TTFT · 89 TPS
Inference Models
| Model | Input $/M | Output $/M | TTFT | TPS |
|---|---|---|---|---|
| OpenAI: gpt-oss-120b | $0.03 | $0.17 | 260ms | 93 |
| OpenAI: gpt-oss-20b | $0.03 | $0.13 | 109ms | 214 |
| IBM: Granite 4.1 8B | $0.05 | $0.10 | 259ms | 101 |
| NVIDIA: Nemotron 3.5 Lightning | $0.07 | $0.20 | 213ms | 344 |
| Google: Gemma 4 31B | $0.10 | $0.34 | 768ms | 39 |
| Google: Gemma 4 26B A4B | $0.10 | $0.30 | 249ms | 67 |
| IBM: Granite 4.2 8B | $0.10 | $0.15 | 223ms | 91 |
| DeepSeek: DeepSeek V4 Flash 0731 | $0.13 | $0.28 | 409ms | 116 |
| DeepSeek: DeepSeek V4.1 Flash | $0.15 | $0.65 | 468ms | 224 |
| NVIDIA: Nemotron 3.5 Super VL | $0.15 | $0.50 | 601ms | 221 |
| Z.ai: GLM 5.3 Flash | $0.15 | $0.50 | 520ms | 199 |
| Meta: Llama 3.1 8B Instruct | $0.22 | $0.22 | 212ms | 138 |
| MiniMax: MiniMax M3 | $0.23 | $0.96 | 473ms | 129 |
| Qwen: Qwen3.6 35B A3B | $0.25 | $1.25 | 427ms | 141 |
| Qwen: Qwen3.8 27B | $0.40 | $3.00 | 1514ms | 43 |
| DeepSeek: DeepSeek V3.1 | $0.55 | $1.65 | 188ms | 87 |
| Z.ai: GLM 5.2 | $0.62 | $2.42 | 383ms | 191 |
| MoonshotAI: Kimi K2.6 | $0.65 | $3.41 | 539ms | 47 |
| MoonshotAI: Kimi K2.7 Code | $0.71 | $3.50 | 766ms | 44 |
| Meta: Llama 3.3 70B Instruct | $0.71 | $0.71 | 118ms | 89 |
| Reflection: Beam 1.0 501B A23B | $1.00 | $3.00 | 372ms | 327 |
| Z.ai: GLM 5.3 | $1.20 | $4.00 | 400ms | 107 |
| DeepSeek: DeepSeek V4 Pro 0813 | $1.31 | $3.96 | 574ms | 126 |
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.