Add Azure models

fwang · fwang · commit 24a6c0b527d3 · 2025-06-11T16:51:05.000-04:00
diff --git a/providers/azure/models/gpt-3.5-turbo-0125.toml b/providers/azure/models/gpt-3.5-turbo-0125.toml
@@ -0,0 +1,14 @@
+name = "GPT-3.5 Turbo 0125"
+attachment = false
+reasoning = false
+temperature = true
+
+[cost]
+input = 0.50
+output = 1.50
+inputCached = 0.00
+outputCached = 0.00
+
+[limit]
+context = 16384
+output = 16384
diff --git a/providers/azure/models/gpt-3.5-turbo-0301.toml b/providers/azure/models/gpt-3.5-turbo-0301.toml
@@ -0,0 +1,14 @@
+name = "GPT-3.5 Turbo 0301"
+attachment = false
+reasoning = false
+temperature = true
+
+[cost]
+input = 1.50
+output = 2.00
+inputCached = 0.00
+outputCached = 0.00
+
+[limit]
+context = 4096
+output = 4096
diff --git a/providers/azure/models/gpt-3.5-turbo-0613.toml b/providers/azure/models/gpt-3.5-turbo-0613.toml
@@ -0,0 +1,14 @@
+name = "GPT-3.5 Turbo 0613"
+attachment = false
+reasoning = false
+temperature = true
+
+[cost]
+input = 3.00
+output = 4.00
+inputCached = 0.00
+outputCached = 0.00
+
+[limit]
+context = 16384
+output = 16384
diff --git a/providers/azure/models/gpt-3.5-turbo-1106.toml b/providers/azure/models/gpt-3.5-turbo-1106.toml
@@ -0,0 +1,14 @@
+name = "GPT-3.5 Turbo 1106"
+attachment = false
+reasoning = false
+temperature = true
+
+[cost]
+input = 1.00
+output = 2.00
+inputCached = 0.00
+outputCached = 0.00
+
+[limit]
+context = 16384
+output = 16384
diff --git a/providers/azure/models/gpt-3.5-turbo-instruct.toml b/providers/azure/models/gpt-3.5-turbo-instruct.toml
@@ -0,0 +1,14 @@
+name = "GPT-3.5 Turbo Instruct"
+attachment = false
+reasoning = false
+temperature = true
+
+[cost]
+input = 1.50
+output = 2.00
+inputCached = 0.00
+outputCached = 0.00
+
+[limit]
+context = 4096
+output = 4096
diff --git a/providers/azure/models/gpt-4-32k.toml b/providers/azure/models/gpt-4-32k.toml
@@ -0,0 +1,14 @@
+name = "GPT-4 32K"
+attachment = false
+reasoning = false
+temperature = true
+
+[cost]
+input = 60.00
+output = 120.00
+inputCached = 0.00
+outputCached = 0.00
+
+[limit]
+context = 32768
+output = 32768
diff --git a/providers/azure/models/gpt-4-turbo-vision.toml b/providers/azure/models/gpt-4-turbo-vision.toml
@@ -0,0 +1,14 @@
+name = "GPT-4 Turbo Vision"
+attachment = true
+reasoning = false
+temperature = true
+
+[cost]
+input = 10.00
+output = 30.00
+inputCached = 0.00
+outputCached = 0.00
+
+[limit]
+context = 128000
+output = 4096
diff --git a/providers/azure/models/gpt-4-turbo.toml b/providers/azure/models/gpt-4-turbo.toml
@@ -0,0 +1,14 @@
+name = "GPT-4 Turbo"
+attachment = true
+reasoning = false
+temperature = true
+
+[cost]
+input = 10.00
+output = 30.00
+inputCached = 0.00
+outputCached = 0.00
+
+[limit]
+context = 128_000
+output = 4_096
diff --git a/providers/azure/models/gpt-4.1-mini.toml b/providers/azure/models/gpt-4.1-mini.toml
@@ -0,0 +1,14 @@
+name = "GPT-4.1 Mini"
+attachment = true
+reasoning = false
+temperature = true
+
+[cost]
+input = 0.40
+output = 1.60
+inputCached = 0.10
+outputCached = 0.00
+
+[limit]
+context = 1047576
+output = 32768
diff --git a/providers/azure/models/gpt-4.1-nano.toml b/providers/azure/models/gpt-4.1-nano.toml
@@ -0,0 +1,14 @@
+name = "GPT-4.1 Nano"
+attachment = true
+reasoning = false
+temperature = true
+
+[cost]
+input = 0.10
+output = 0.40
+inputCached = 0.03
+outputCached = 0.00
+
+[limit]
+context = 1047576
+output = 32768
diff --git a/providers/azure/models/gpt-4.1.toml b/providers/azure/models/gpt-4.1.toml
@@ -0,0 +1,14 @@
+name = "GPT-4.1"
+attachment = true
+reasoning = false
+temperature = true
+
+[cost]
+input = 2.00
+output = 8.00
+inputCached = 0.50
+outputCached = 0.00
+
+[limit]
+context = 1_047_576
+output = 32_768
diff --git a/providers/azure/models/gpt-4.toml b/providers/azure/models/gpt-4.toml
@@ -0,0 +1,14 @@
+name = "GPT-4"
+attachment = false
+reasoning = false
+temperature = true
+
+[cost]
+input = 60.00
+output = 120.00
+inputCached = 0.00
+outputCached = 0.00
+
+[limit]
+context = 8192
+output = 8192
diff --git a/providers/azure/models/gpt-4o-mini.toml b/providers/azure/models/gpt-4o-mini.toml
@@ -0,0 +1,14 @@
+name = "GPT-4o Mini"
+attachment = true
+reasoning = false
+temperature = true
+
+[cost]
+input = 0.15
+output = 0.60
+inputCached = 0.08
+outputCached = 0.00
+
+[limit]
+context = 128_000
+output = 16_384
diff --git a/providers/azure/models/gpt-4o.toml b/providers/azure/models/gpt-4o.toml
@@ -0,0 +1,14 @@
+name = "GPT-4o"
+attachment = true
+reasoning = false
+temperature = true
+
+[cost]
+input = 2.50
+output = 10.00
+inputCached = 1.25
+outputCached = 0.00
+
+[limit]
+context = 128_000
+output = 16_384
diff --git a/providers/azure/models/o1-mini.toml b/providers/azure/models/o1-mini.toml
@@ -0,0 +1,14 @@
+name = "o1-mini"
+attachment = false
+reasoning = true
+temperature = false
+
+[cost]
+input = 1.10
+output = 4.40
+inputCached = 0.55
+outputCached = 0.00
+
+[limit]
+context = 128_000
+output = 65_536
diff --git a/providers/azure/models/o1-preview.toml b/providers/azure/models/o1-preview.toml
@@ -0,0 +1,14 @@
+name = "o1-preview"
+attachment = false
+reasoning = true
+temperature = false
+
+[cost]
+input = 16.50
+output = 66.00
+inputCached = 8.25
+outputCached = 0.00
+
+[limit]
+context = 128_000
+output = 32_768
diff --git a/providers/azure/models/o1.toml b/providers/azure/models/o1.toml
@@ -0,0 +1,14 @@
+name = "o1"
+attachment = false
+reasoning = true
+temperature = false
+
+[cost]
+input = 15.00
+output = 60.00
+inputCached = 7.50
+outputCached = 0.00
+
+[limit]
+context = 200_000
+output = 100_000
diff --git a/providers/azure/models/o3-mini.toml b/providers/azure/models/o3-mini.toml
@@ -0,0 +1,14 @@
+name = "o3-mini"
+attachment = false
+reasoning = true
+temperature = false
+
+[cost]
+input = 1.10
+output = 4.40
+inputCached = 0.55
+outputCached = 0.00
+
+[limit]
+context = 200_000
+output = 100_000
diff --git a/providers/azure/models/o3.toml b/providers/azure/models/o3.toml
@@ -0,0 +1,14 @@
+name = "o3"
+attachment = true
+reasoning = true
+temperature = false
+
+[cost]
+input = 2.00
+output = 8.00
+inputCached = 0.50
+outputCached = 0.00
+
+[limit]
+context = 200_000
+output = 100_000
diff --git a/providers/azure/models/o4-mini.toml b/providers/azure/models/o4-mini.toml
@@ -0,0 +1,14 @@
+name = "o4-mini"
+attachment = true
+reasoning = true
+temperature = false
+
+[cost]
+input = 1.10
+output = 4.40
+inputCached = 0.28
+outputCached = 0.00
+
+[limit]
+context = 200_000
+output = 100_000
diff --git a/providers/azure/provider.toml b/providers/azure/provider.toml
@@ -0,0 +1,2 @@
+name = "Azure"
+env = ["AZURE_RESOURCE_NAME", "AZURE_API_KEY"]
diff --git a/providers/openai/models/gpt-4.1-mini.toml b/providers/openai/models/gpt-4.1-mini.toml
@@ -0,0 +1,14 @@
+name = "GPT-4.1 Mini"
+attachment = true
+reasoning = false
+temperature = true
+
+[cost]
+input = 0.40
+output = 1.60
+inputCached = 0.10
+outputCached = 0.00
+
+[limit]
+context = 1047576
+output = 32768
diff --git a/providers/openai/models/gpt-4.1-nano.toml b/providers/openai/models/gpt-4.1-nano.toml
@@ -0,0 +1,14 @@
+name = "GPT-4.1 Nano"
+attachment = true
+reasoning = false
+temperature = true
+
+[cost]
+input = 0.10
+output = 0.40
+inputCached = 0.03
+outputCached = 0.00
+
+[limit]
+context = 1047576
+output = 32768
diff --git a/providers/openai/models/gpt-4.1.toml b/providers/openai/models/gpt-4.1.toml
@@ -0,0 +1,14 @@
+name = "GPT-4.1"
+attachment = true
+reasoning = false
+temperature = true
+
+[cost]
+input = 2.00
+output = 8.00
+inputCached = 0.50
+outputCached = 0.00
+
+[limit]
+context = 1_047_576
+output = 32_768
diff --git a/providers/openai/models/gpt-4.5-preview.toml b/providers/openai/models/gpt-4.5-preview.toml
@@ -0,0 +1,14 @@
+name = "GPT-4.5 Preview"
+attachment = true
+reasoning = false
+temperature = true
+
+[cost]
+input = 75.00
+output = 150.00
+inputCached = 37.50
+outputCached = 0.00
+
+[limit]
+context = 128_000
+output = 16_384
diff --git a/providers/openai/models/gpt-4.toml b/providers/openai/models/gpt-4.toml
diff --git a/providers/openai/models/gpt-4o-mini.toml b/providers/openai/models/gpt-4o-mini.toml
diff --git a/providers/openai/models/o1-mini.toml b/providers/openai/models/o1-mini.toml
diff --git a/providers/openai/models/o1-preview.toml b/providers/openai/models/o1-preview.toml
diff --git a/providers/openai/models/o1-pro.toml b/providers/openai/models/o1-pro.toml
diff --git a/providers/openai/models/o1.toml b/providers/openai/models/o1.toml
diff --git a/providers/openai/models/o3-mini.toml b/providers/openai/models/o3-mini.toml
diff --git a/providers/openai/models/o3-pro.toml b/providers/openai/models/o3-pro.toml
diff --git a/providers/openai/models/o3.toml b/providers/openai/models/o3.toml
diff --git a/providers/openai/models/o4-mini.toml b/providers/openai/models/o4-mini.toml
