# Inferenceapis

serves 14 tracked open-weights models.

models
14
verified
—
of overall top 10
4
cheapest on
—
vs best $
2.45×
ctx (median)
1048k

# models

model rank $/M in $/M out src ✓
glm-5.3 #1 $1.82 $5.72 litellm —
glm-5.3-flash #3 $0.20 $0.66 litellm —
deepseek-v4-flash-0731 #6 $0.19 $0.38 litellm —
deepseek-v4-pro #7 $1.72 $5.15 litellm —
minimax-m3 #12 $0.39 $1.56 litellm —
kimi-k2.7-code #19 $0.89 $4.42 litellm —
deepseek-v4-flash #22 $0.19 $0.38 litellm —
gpt-oss-120b #63 $0.20 $0.80 litellm —
qwen3-vl-235b-a22b-instruct #73 $0.26 $1.15 litellm —
gpt-oss-20b #75 $0.04 $0.19 litellm —
deepseek-v3 #77 $0.19 $0.38 litellm —
llama-3.3-70b-instruct #94 $0.20 $0.50 litellm —
deepseek-v4-pro-0813 — $1.72 $5.15 litellm —
deepseek-v4.1-flash — $0.40 $1.60 litellm —

all providers · machine-readable: providers.json