# OpenInference

HQ US · serves 3 tracked open-weights models. · privacy policy

models
3
verified
—
of overall top 10
—
cheapest on
—
vs best $
1.77×
ctx (median)
1024k
uptime
99.7%

# models

model rank $/M in $/M out $/M cache src ✓
deepseek-v4.1-flash — $0.04 $0.50 $0.01 openrouter —
deepseek-v4.1-flash-1017 — $0.04 $0.50 $0.01 openrouter —
glm-5.3-flash — $0.03 $0.16 $0.02 openrouter —

# recent changes

when (UTC)modelchange
Nov 1 22:12 deepseek-v4.1-flash $/M input $0.00 → $0.04 ↑ 34900.0%
Nov 1 22:12 deepseek-v4.1-flash $/M output $0.76 → $0.50 ↓ 34.0%
Nov 1 17:59 deepseek-v4.1-flash $/M input $0.00 → $0.00 ↓ 95.5%
Nov 1 17:59 deepseek-v4.1-flash $/M output $0.67 → $0.76 ↑ 12.9%
Nov 1 11:53 deepseek-v4.1-flash $/M input $0.01 → $0.00 ↓ 69.9%
Nov 1 11:53 deepseek-v4.1-flash $/M output $0.55 → $0.67 ↑ 23.0%
Nov 1 11:53 glm-5.3-flash $/M input $0.01 → $0.03 ↑ 222.6%
Nov 1 11:53 glm-5.3-flash $/M output $0.17 → $0.16 ↓ 6.0%
Nov 1 06:26 deepseek-v4.1-flash $/M input $0.01 → $0.01 ↓ 48.2%
Nov 1 06:26 deepseek-v4.1-flash $/M output $0.11 → $0.55 ↑ 395.5%
Nov 1 06:26 deepseek-v4.1-flash-1017 $/M input $0.01 → $0.04 ↑ 148.2%
Nov 1 06:26 deepseek-v4.1-flash-1017 $/M output $0.11 → $0.50 ↑ 354.5%
Nov 1 06:26 glm-5.3-flash $/M input $0.02 → $0.01 ↓ 40.8%
Nov 1 06:26 glm-5.3-flash $/M output $0.03 → $0.17 ↑ 535.1%
Oct 31 21:45 deepseek-v4.1-flash $/M output $0.14 → $0.11 ↓ 23.6%
Oct 31 21:45 deepseek-v4.1-flash-1017 $/M output $0.14 → $0.11 ↓ 23.6%
Oct 31 21:45 glm-5.3-flash $/M input $0.02 → $0.02 ↓ 8.7%
Oct 31 21:45 glm-5.3-flash $/M output $0.04 → $0.03 ↓ 24.5%
Oct 31 10:58 deepseek-v4.1-flash $/M input $0.02 → $0.01 ↓ 9.0%
Oct 31 10:58 deepseek-v4.1-flash $/M output $0.19 → $0.14 ↓ 24.2%
Oct 31 10:58 deepseek-v4.1-flash-1017 $/M input $0.02 → $0.01 ↓ 9.0%
Oct 31 10:58 deepseek-v4.1-flash-1017 $/M output $0.19 → $0.14 ↓ 24.2%
Oct 31 10:58 glm-5.3-flash $/M input $0.02 → $0.02 ↓ 16.9%
Oct 31 10:58 glm-5.3-flash $/M output $0.06 → $0.04 ↓ 37.6%
Oct 31 05:58 deepseek-v4.1-flash $/M input $0.04 → $0.02 ↓ 56.8%
Oct 31 05:58 deepseek-v4.1-flash $/M output $0.40 → $0.19 ↓ 52.5%
Oct 31 05:58 deepseek-v4.1-flash-1017 $/M input $0.04 → $0.02 ↓ 56.8%
Oct 31 05:58 deepseek-v4.1-flash-1017 $/M output $0.40 → $0.19 ↓ 52.5%
Oct 30 22:30 deepseek-v4.1-flash $/M input $0.04 → $0.04 ↓ 17.1%
Oct 30 22:30 deepseek-v4.1-flash $/M output $1.04 → $0.40 ↓ 61.5%
Oct 30 22:30 deepseek-v4.1-flash-1017 $/M input $0.03 → $0.04 ↑ 5.9%
Oct 30 22:30 deepseek-v4.1-flash-1017 $/M output $1.14 → $0.40 ↓ 64.9%
Oct 30 22:30 glm-5.3-flash $/M output $0.06 → $0.06 ↓ 9.0%
Oct 30 13:12 glm-5.3-flash $/M input $0.02 → $0.02 ↓ 16.9%

all providers · machine-readable: providers.json