# OpenInference
HQ US · serves 3 tracked open-weights models. · privacy policy
- models
- 3
- verified
- —
- of overall top 10
- 1
- cheapest on
- —
- vs best $
- 2.34×
- ctx (median)
- 1024k
- uptime
- 100.0%
# models
| model | rank | $/M in | $/M out | ✓ |
|---|---|---|---|---|
| glm-5.3-flash | #3 | $0.08 | $0.01 | — |
| deepseek-v4.1-flash | — | $0.02 | $1.00 | — |
| deepseek-v4.1-flash-1017 | — | $0.02 | $1.00 | — |
# recent changes
| when (UTC) | model | change |
|---|---|---|
| Oct 26 05:00 | glm-5.3-flash | $/M input $0.07 → $0.08 ↑ 15.3% |
| Oct 26 05:00 | glm-5.3-flash | $/M output $0.07 → $0.01 ↓ 85.7% |
| Oct 25 04:57 | glm-5.3-flash | $/M input $0.09 → $0.07 ↓ 28.7% |
| Oct 25 04:57 | glm-5.3-flash | $/M output $0.02 → $0.07 ↑ 232.7% |
| Oct 24 20:59 | glm-5.3-flash | $/M input $0.77 → $0.09 ↓ 88.0% |
| Oct 24 20:59 | glm-5.3-flash | $/M output $0.00 → $0.02 ↑ 813.7% |
| Oct 24 16:05 | glm-5.3-flash | $/M input $0.04 → $0.77 ↑ 1769.6% |
| Oct 24 16:05 | glm-5.3-flash | $/M output $0.05 → $0.00 ↓ 95.1% |
| Oct 24 11:18 | glm-5.3-flash | $/M input $0.02 → $0.04 ↑ 125.0% |
| Oct 24 11:18 | glm-5.3-flash | $/M output $0.11 → $0.05 ↓ 55.6% |
| Oct 24 09:36 | glm-5.3-flash | $/M input $0.03 → $0.02 ↓ 33.3% |
| Oct 24 09:36 | glm-5.3-flash | $/M output $0.36 → $0.11 ↓ 70.4% |
| Oct 24 04:48 | deepseek-v4.1-flash | $/M input $0.07 → $0.02 ↓ 71.4% |
| Oct 24 04:48 | deepseek-v4.1-flash | $/M output $0.50 → $1.00 ↑ 100.0% |
| Oct 24 04:48 | deepseek-v4.1-flash-1017 | $/M input $0.07 → $0.02 ↓ 71.4% |
| Oct 24 04:48 | deepseek-v4.1-flash-1017 | $/M output $0.50 → $1.00 ↑ 100.0% |
| Oct 24 04:48 | glm-5.3-flash | $/M input $0.03 → $0.03 ↓ 8.0% |
| Oct 24 04:48 | glm-5.3-flash | $/M output $0.09 → $0.36 ↑ 288.3% |
| Oct 23 21:31 | glm-5.3-flash | $/M input $0.01 → $0.03 ↑ 476.9% |
| Oct 23 21:31 | glm-5.3-flash | $/M output $0.20 → $0.09 ↓ 53.5% |
all providers · machine-readable: providers.json