| Model | Endpoint | Context | Input /M | Output /M | Cached input /M | Cache write /M | Uptime 1d |
|---|---|---|---|---|---|---|---|
 DeepSeek V4.1 Flash 1017 | near-ai | 1M | $0.30 | $1.20 | $0.006 | — | 100.00% |
 GLM 5.3 Flash | near-ai/fp8 | 1M | $0.08 | $0.50 | $0.012 | — | 100.00% |
 Qwen3.8 27B | near-ai/fp8 | 262K | $0.04 | $1.35 | $0.018 | — | 99.93% |
 gpt-oss-120b | near-ai/fp4 | 131K | $0.03 | $0.15 | $0.015 | — | 100.00% |