| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
 Beam 1.0 501B A23B | coreweave/nvfp4 | 1M | $0.30 | $1.00 | $0.04 | — | 99.90% |
 DeepSeek V3.1 | coreweave/fp8 | 161K | $0.50 | $1.50 | $0.20 | — | 99.72% |
| DeepSeek V4 Flash 0731 | coreweave/fp8 | 262K | $0.13 | $0.27 | $0.05 | — | 99.72% |
| DeepSeek V4 Pro 0813 | coreweave/fp8 | 1M | $1.31 | $3.96 | $0.044 | — | 99.72% |
| DeepSeek V4.1 Flash | coreweave/fp8 | 1M | $0.13 | $0.65 | $0.002 | — | 99.72% |
| DeepSeek V4.1 Flash 1017 | coreweave/fp8 | 1M | $0.30 | $1.20 | $0.006 | — | 97.15% |
 GLM 5.2 | coreweave/fp4 | 1M | $0.62 | $2.42 | $0.14 | — | 98.96% |
| GLM 5.3 | coreweave/nvfp4 | 1M | $0.75 | $3.00 | $0.19 | — | 99.63% |
| GLM 5.3 Flash | coreweave/nvfp4 | 1M | $0.12 | $0.38 | $0.02 | — | 67.50% |
 Gemma 4 26B A4B | coreweave/bf16 | 262K | $0.10 | $0.30 | $0.05 | — | 99.72% |
| Gemma 4 31B | coreweave/fp4 | 262K | $0.10 | $0.34 | $0.10 | — | 99.72% |
 Granite 4.2 8B | coreweave/bf16 | 131K | $0.06 | $0.15 | $0.015 | — | 99.61% |
 Kimi K2.6 | coreweave/fp4 | 262K | $0.65 | $3.41 | $0.15 | — | 99.72% |
| Kimi K2.7 Code | coreweave/int4 | 262K | $0.60 | $3.00 | $0.12 | — | 99.59% |
 Llama 3.1 8B Instruct | coreweave/bf16 | 131K | $0.22 | $0.22 | $0.22 | — | 99.79% |
| Llama 3.3 70B Instruct | coreweave/fp16 | 128K | $0.71 | $0.71 | $0.71 | — | 99.72% |
 MiniMax M3 | coreweave/fp4 | 262K | $0.23 | $0.96 | $0.05 | — | 99.72% |
 Nemotron 3.5 Lightning | coreweave/bf16 | 262K | $0.07 | $0.20 | $0.04 | — | 99.78% |
| Nemotron 3.5 Super VL | coreweave/nvfp4 | 1M | $0.15 | $0.47 | $0.02 | — | 99.70% |
 Qwen3.6 35B A3B | coreweave/fp8 | 262K | $0.10 | $0.89 | $0.035 | — | 98.76% |
| Qwen3.8 27B | coreweave/fp8 | 262K | $0.40 | $3.00 | $0.15 | — | 99.53% |
 gpt-oss-120b | coreweave/fp4 | 131K | $0.03 | $0.17 | $0.03 | — | 98.81% |
| gpt-oss-20b | coreweave/fp4 | 131K | $0.03 | $0.13 | $0.03 | — | 99.72% |