DInference
Updated Sep 11, 2026
| Model | 1M input | 1M output | 1M cache read | Context | Released |
|---|
| GLM-5.2 | $1.25 | $3.89 | — | 1.0M | Jun 13, 2026 |
| GLM-5.1 | $1.25 | $3.89 | — | 200k | Apr 7, 2026 |
| GLM-5 | $0.75 | $2.4 | — | 200k | Feb 12, 2026 |
| MiniMax-M2.5 | $0.22 | $0.88 | — | 200k | Feb 12, 2026 |
| GLM-4.7 | $0.45 | $1.65 | — | 200k | Dec 22, 2025 |
| GPT OSS 120B | $0.0675 | $0.27 | — | 131k | Aug 1, 2025 |