# Wafer

HQ US · serves 10 tracked open-weights models. · privacy policy

models
10
verified
—
of overall top 10
—
cheapest on
1 models
vs best $
1.83×
ctx (median)
1024k
uptime
100.0%

# models

model rank $/M in $/M out $/M cache src ✓
deepseek-v4-flash — $0.60 $0.17 $0.20 openrouter —
deepseek-v4-flash-0731 — $0.06 $0.30 $0.04 openrouter —
deepseek-v4-pro-0813 — $0.12 $4.00 $0.11 openrouter —
deepseek-v4.1-flash — $0.04 $0.50 $0.01 openrouter —
deepseek-v4.1-flash-1017 — $0.04 $0.50 $0.01 openrouter —
glm-5.2 — $0.01 $6.80 $0.01 openrouter —
glm-5.3 — $0.07 $1.40 $0.07 openrouter —
glm-5.3-flash — $0.04 $0.20 $0.04 openrouter —
kimi-k3 — $0.28 $9.60 $0.13 openrouter —
qwen3.8-27b — $0.06 $2.30 $0.06 openrouter —

# recent changes

when (UTC)modelchange
Nov 1 17:59 deepseek-v4-flash-0731 $/M input $0.04 → $0.06 ↑ 35.9%
Nov 1 06:26 deepseek-v4-flash-0731 $/M input $0.05 → $0.04 ↓ 8.4%
Oct 31 21:45 deepseek-v4-flash-0731 $/M input $0.06 → $0.05 ↓ 18.3%
Oct 31 21:45 deepseek-v4-pro-0813 $/M output $4.30 → $4.00 ↓ 7.0%
Oct 31 12:49 kimi-k3 $/M output $9.94 → $9.60 ↓ 3.4%
Oct 31 10:58 deepseek-v4-flash-0731 $/M input $0.04 → $0.06 ↑ 49.5%
Oct 31 10:58 glm-5.2 $/M output $7.00 → $6.80 ↓ 2.9%
Oct 31 10:58 kimi-k3 $/M input $0.16 → $0.28 ↑ 68.3%
Oct 31 05:58 deepseek-v4-flash-0731 $/M input $0.05 → $0.04 ↓ 14.2%
Oct 31 05:58 glm-5.3-flash $/M input $0.05 → $0.04 ↓ 8.3%
Oct 31 05:58 kimi-k3 $/M input $0.28 → $0.16 ↓ 40.6%
Oct 30 22:30 glm-5.3-flash $/M input $0.05 → $0.05 ↓ 11.1%
Oct 30 13:12 deepseek-v4-flash-0731 $/M input $0.04 → $0.05 ↑ 16.5%
Oct 30 11:26 deepseek-v4-flash-0731 $/M input $0.05 → $0.04 ↓ 20.2%

all providers · machine-readable: providers.json