| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
 Clef | primeintellect | 66K | $0.24 | $0.00 | — | — | 100.00% |
| Clef Flash | primeintellect | 25K | $0.038 | $0.00 | — | — | 100.00% |
 DeepSeek V4 Flash 0731 | primeintellect/fp4 | 1M | $0.44 | $1.32 | $0.014 | — | 99.16% |
| DeepSeek V4.1 Flash | primeintellect | 1M | $0.039 | $1.20 | $0.0012 | — | 98.37% |
| DeepSeek V4.1 Flash 1017 | primeintellect | 1M | $0.0437 | $0.70 | $0.0024 | — | 100.00% |
 GLM 5.3 | primeintellect | 1M | $0.40 | $2.464 | $0.0744 | — | 100.00% |
| GLM 5.3 Flash | primeintellect | 1M | $0.0525 | $0.25 | $0.0105 | — | 100.00% |
 Gemma 4 26B A4B | primeintellect/bf16 | 262K | $0.013 | $0.038 | $0.006 | — | 99.79% |
| Gemma 4 31B | primeintellect/fp4 | 262K | $0.20 | $0.335 | $0.10 | — | 99.30% |
 Moondream 3 Preview | primeintellect/fp8 | 32K | $0.30 | $2.50 | — | — | 100.00% |
| Moondream 3.1 | primeintellect/fp8 | 32K | $0.30 | $2.50 | — | — | 100.00% |
 Nemotron 3.5 Super VL | primeintellect/nvfp4 | 1M | $0.15 | $0.50 | $0.02 | — | 99.38% |
| Nemotron 3.5 Transcribe | primeintellect/bf16 | — | $16.6667 | $0.00 | — | — | 100.00% |
| Parakeet TDT 0.6B v3 | primeintellect/bf16 | — | $16.6667 | $0.00 | — | — | 100.00% |
| Parakeet Ultra | primeintellect/bf16 | — | $16.6667 | $0.00 | — | — | 100.00% |
 Qwen3 ASR 0.6B | primeintellect/bf16 | — | $3.33 | $0.00 | — | — | 99.62% |
| Qwen3 ASR 1.7B | primeintellect/bf16 | — | $7.50 | $0.00 | — | — | 100.00% |
| Qwen3 Reranker 0.6B | primeintellect/bf16 | 33K | $0.00 | $0.00 | — | — | 100.00% |
| Qwen3 Reranker 8B | primeintellect/bf16 | 33K | $0.00 | $0.00 | — | — | 100.00% |
| Qwen3.5-9B | primeintellect/bf16 | 262K | $0.046 | $0.067 | $0.041 | — | 100.00% |
| Qwen3.6 35B A3B | primeintellect/fp8 | 262K | $0.017 | $0.155 | $0.015 | — | 100.00% |
| Qwen3.8 27B | primeintellect/fp8 | 262K | $0.187 | $1.327 | $0.021 | — | 100.00% |
 Ripple-65B Preview | primeintellect/bf16 | 1M | $0.10 | $0.30 | $0.025 | — | 99.82% |
 Whisper Large V3 Turbo | primeintellect/bf16 | — | $11.1111 | $0.00 | — | — | 100.00% |
| gpt-oss-120b | primeintellect/fp4 | 131K | $0.046 | $0.099 | $0.042 | — | 100.00% |
| gpt-oss-20b | primeintellect/fp4 | 131K | $0.02 | $0.03 | $0.018 | — | 98.82% |