id: modal
npm: @ai-sdk/openai-compatible
env: MODAL_PROXY_TOKEN
api: https://inference.us-west.modal.direct/v1
Models
GLM 5.3 Flash
zai-org/GLM-5.3-Flashin $0.45/M
out $1.50/M
cache read $0.09/M
ctx: 1,000,000
max out: 131,072
in: text, image, video
out: text
reasoning
tools
vision
structured
temp
open weights
Inkling
thinkingmachines/Inkling-NVFP4in $1.20/M
out $5.00/M
cache read $0.27/M
ctx: 1,048,576
max out: 262,144
in: text, image, audio
out: text
reasoning
tools
vision
structured
temp
open weights
Kimi K3
moonshotai/Kimi-K3in $3.00/M
out $15.00/M
reason $15.00/M
cache read $0.30/M
ctx: 1,048,576
max out: 131,072
in: text, image
out: text
reasoning
tools
vision
structured
temp
open weights
Qwen3.8-Max
Qwen/Qwen3.8-2.4T-A95Bin $2.00/M
out $6.00/M
cache read $0.25/M
ctx: 1,010,000
max out: 131,072
in: text
out: text
reasoning
tools
vision
structured
temp
open weights