Skip to content
Open
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
16 changes: 16 additions & 0 deletions providers/gmicloud/models/anthropic/claude-opus-4.6.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
[extends]
from = "anthropic/claude-opus-4-6"
omit = ["experimental.modes.fast", "cost.cache_write"]

[cost]
input = 5.00
output = 25.00
cache_read = 0.50

[limit]
context = 409_600
output = 128_000

[modalities]
input = ["text"]
output = ["text"]
16 changes: 16 additions & 0 deletions providers/gmicloud/models/anthropic/claude-opus-4.7.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
[extends]
from = "anthropic/claude-opus-4-7"
omit = ["cost.cache_write"]

[cost]
input = 4.50
output = 22.50
cache_read = 0.45

[limit]
context = 409_600
output = 128_000

[modalities]
input = ["text"]
output = ["text"]
16 changes: 16 additions & 0 deletions providers/gmicloud/models/anthropic/claude-sonnet-4.6.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
[extends]
from = "anthropic/claude-sonnet-4-6"
omit = ["cost.cache_write"]

[cost]
input = 3.00
output = 15.00
cache_read = 0.30

[limit]
context = 409_600
output = 64_000

[modalities]
input = ["text"]
output = ["text"]
11 changes: 11 additions & 0 deletions providers/gmicloud/models/deepseek-ai/DeepSeek-V4-Flash.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
[extends]
from = "deepseek/deepseek-v4-flash"

[cost]
input = 0.112
output = 0.224
cache_read = 0.022

[limit]
context = 1_048_575
output = 384_000
11 changes: 11 additions & 0 deletions providers/gmicloud/models/deepseek-ai/DeepSeek-V4-Pro.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,11 @@
[extends]
from = "deepseek/deepseek-v4-pro"

[cost]
input = 1.392
output = 2.784
cache_read = 0.116

[limit]
context = 1_048_576
output = 384_000
15 changes: 15 additions & 0 deletions providers/gmicloud/models/moonshotai/Kimi-K2.6.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,15 @@
[extends]
from = "moonshotai/kimi-k2.6"

[cost]
input = 0.855
output = 3.60
cache_read = 0.144

[limit]
context = 65_536
output = 65_536

[modalities]
input = ["text"]
output = ["text"]
5 changes: 5 additions & 0 deletions providers/gmicloud/provider.toml
Original file line number Diff line number Diff line change
@@ -0,0 +1,5 @@
name = "GMI Cloud"
env = ["GMICLOUD_API_KEY"]
npm = "@ai-sdk/openai-compatible"
api = "https://api.gmi-serving.com/v1"
doc = "https://docs.gmicloud.ai/inference-engine/api-reference/llm-api-reference"