id: gmicloud
npm: @ai-sdk/openai-compatible
env: GMICLOUD_API_KEY
api: https://api.gmi-serving.com/v1
Models
Claude Opus 4.6
anthropic/claude-opus-4.6in $5.00/M
out $25.00/M
cache read $0.50/M
ctx: 409,600
max out: 128,000
in: text
out: text
reasoning
tools
vision
structured
temp
open weights
Claude Opus 4.7
anthropic/claude-opus-4.7in $4.50/M
out $22.50/M
cache read $0.45/M
ctx: 409,600
max out: 128,000
in: text
out: text
reasoning
tools
vision
structured
temp
open weights
Claude Sonnet 4.6
anthropic/claude-sonnet-4.6in $3.00/M
out $15.00/M
cache read $0.30/M
ctx: 409,600
max out: 64,000
in: text
out: text
reasoning
tools
vision
structured
temp
open weights
DeepSeek V4 Flash
deepseek-ai/DeepSeek-V4-Flashin $0.11/M
out $0.22/M
cache read $0.02/M
ctx: 1,048,575
max out: 384,000
in: text
out: text
reasoning
tools
vision
structured
temp
open weights
DeepSeek V4 Pro
deepseek-ai/DeepSeek-V4-Proin $1.39/M
out $2.78/M
cache read $0.12/M
ctx: 1,048,576
max out: 384,000
in: text
out: text
reasoning
tools
vision
structured
temp
open weights
GLM-5
zai-org/GLM-5-FP8in $0.60/M
out $1.92/M
cache read $0.12/M
ctx: 202,752
max out: 131,072
in: text
out: text
reasoning
tools
vision
structured
temp
open weights
GLM-5.1
zai-org/GLM-5.1-FP8in $0.98/M
out $3.08/M
cache read $0.18/M
ctx: 202,752
max out: 131,072
in: text
out: text
reasoning
tools
vision
structured
temp
open weights
Kimi K2.6
moonshotai/Kimi-K2.6in $0.85/M
out $3.60/M
cache read $0.14/M
ctx: 65,536
max out: 65,536
in: text
out: text
reasoning
tools
vision
structured
temp
open weights