fix(cloudflare-ai-gateway): correct model metadata

chore: remove Cloudflare gateway sync
fix(sync): preserve canonical Cloudflare gateway catalog
2026-08-03 23:16:01 -05:00 · 2026-08-03 22:02:22 -05:00 · 2026-08-03 21:58:40 -05:00 · 2026-08-03 21:56:49 -05:00 · 2026-08-03 21:56:48 -05:00
25 changed files with 266 additions and 0 deletions
@@ -0,0 +1,6 @@
+base_model = "openai/gpt-4.1-mini"
+
+[cost]
+input = 0.4
+output = 1.6
+cache_read = 0.1
@@ -0,0 +1,6 @@
+base_model = "openai/gpt-4.1-nano"
+
+[cost]
+input = 0.1
+output = 0.4
+cache_read = 0.025
@@ -0,0 +1,6 @@
+base_model = "openai/gpt-4.1"
+
+[cost]
+input = 2
+output = 8
+cache_read = 0.5
@@ -0,0 +1,7 @@
+base_model = "openai/gpt-5-chat-latest"
+reasoning_options = []
+
+[cost]
+input = 1.25
+output = 10
+cache_read = 0.125
@@ -0,0 +1,10 @@
+base_model = "openai/gpt-5-codex"
+
+[[reasoning_options]]
+type = "effort"
+values = ["low", "medium", "high"]
+
+[cost]
+input = 1.25
+output = 10
+cache_read = 0.125
@@ -0,0 +1,10 @@
+base_model = "openai/gpt-5-mini"
+
+[[reasoning_options]]
+type = "effort"
+values = ["minimal", "low", "medium", "high"]
+
+[cost]
+input = 0.25
+output = 2
+cache_read = 0.025
@@ -0,0 +1,10 @@
+base_model = "openai/gpt-5-nano"
+
+[[reasoning_options]]
+type = "effort"
+values = ["minimal", "low", "medium", "high"]
+
+[cost]
+input = 0.05
+output = 0.4
+cache_read = 0.005
@@ -0,0 +1,9 @@
+base_model = "openai/gpt-5-pro"
+
+[[reasoning_options]]
+type = "effort"
+values = ["high"]
+
+[cost]
+input = 15
+output = 120
@@ -0,0 +1,10 @@
+base_model = "openai/gpt-5.1-chat-latest"
+
+[[reasoning_options]]
+type = "effort"
+values = ["medium"]
+
+[cost]
+input = 1.25
+output = 10
+cache_read = 0.125
@@ -0,0 +1,10 @@
+base_model = "openai/gpt-5.1-codex-max"
+
+[[reasoning_options]]
+type = "effort"
+values = ["low", "medium", "high", "xhigh"]
+
+[cost]
+input = 1.25
+output = 10
+cache_read = 0.125
@@ -0,0 +1,10 @@
+base_model = "openai/gpt-5.1-codex-mini"
+
+[[reasoning_options]]
+type = "effort"
+values = ["low", "medium", "high"]
+
+[cost]
+input = 0.25
+output = 2
+cache_read = 0.025
@@ -0,0 +1,10 @@
+base_model = "openai/gpt-5.2-chat-latest"
+
+[[reasoning_options]]
+type = "effort"
+values = ["medium"]
+
+[cost]
+input = 1.75
+output = 14
+cache_read = 0.175
@@ -0,0 +1,9 @@
+base_model = "openai/gpt-5.2-pro"
+
+[[reasoning_options]]
+type = "effort"
+values = ["medium", "high", "xhigh"]
+
+[cost]
+input = 21
+output = 168
@@ -0,0 +1,6 @@
+base_model = "openai/gpt-5.3-chat-latest"
+
+[cost]
+input = 1.75
+output = 14
+cache_read = 0.175
@@ -0,0 +1,10 @@
+base_model = "openai/gpt-5.4-mini"
+
+[[reasoning_options]]
+type = "effort"
+values = ["none", "low", "medium", "high", "xhigh"]
+
+[cost]
+input = 0.75
+output = 4.5
+cache_read = 0.075
@@ -0,0 +1,10 @@
+base_model = "openai/gpt-5.4-nano"
+
+[[reasoning_options]]
+type = "effort"
+values = ["none", "low", "medium", "high", "xhigh"]
+
+[cost]
+input = 0.2
+output = 1.25
+cache_read = 0.02
@@ -0,0 +1,14 @@
+base_model = "openai/gpt-5.4-pro"
+
+[[reasoning_options]]
+type = "effort"
+values = ["medium", "high", "xhigh"]
+
+[cost]
+input = 30
+output = 180
+
+[[cost.tiers]]
+tier = { type = "context", size = 272_000 }
+input = 60
+output = 270
@@ -0,0 +1,14 @@
+base_model = "openai/gpt-5.5-pro"
+
+[[reasoning_options]]
+type = "effort"
+values = ["medium", "high", "xhigh"]
+
+[cost]
+input = 30
+output = 180
+
+[[cost.tiers]]
+tier = { type = "context", size = 272_000 }
+input = 60
+output = 270
@@ -0,0 +1,19 @@
+base_model = "openai/gpt-5.6-sol"
+name = "GPT-5.6"
+
+[[reasoning_options]]
+type = "effort"
+values = ["none", "low", "medium", "high", "xhigh", "max"]
+
+[cost]
+input = 5
+output = 30
+cache_read = 0.5
+cache_write = 6.25
+
+[[cost.tiers]]
+tier = { type = "context", size = 272_000 }
+input = 10
+output = 45
+cache_read = 1
+cache_write = 12.5
@@ -0,0 +1,10 @@
+base_model = "openai/gpt-5"
+
+[[reasoning_options]]
+type = "effort"
+values = ["minimal", "low", "medium", "high"]
+
+[cost]
+input = 1.25
+output = 10
+cache_read = 0.125
@@ -0,0 +1,9 @@
+base_model = "openai/o1-pro"
+
+[[reasoning_options]]
+type = "effort"
+values = ["low", "medium", "high"]
+
+[cost]
+input = 150
+output = 600
@@ -0,0 +1,10 @@
+base_model = "openai/o3-deep-research"
+
+[[reasoning_options]]
+type = "effort"
+values = ["medium"]
+
+[cost]
+input = 10
+output = 40
+cache_read = 2.5
@@ -0,0 +1,10 @@
+base_model = "openai/o4-mini-deep-research"
+
+[[reasoning_options]]
+type = "effort"
+values = ["medium"]
+
+[cost]
+input = 2
+output = 8
+cache_read = 0.5
@@ -0,0 +1,21 @@
+# Toggle: chat_template_kwargs.enable_thinking = true|false
+# Effort: reasoning_effort = low|medium|high
+# https://developers.cloudflare.com/workers-ai/models/gemma-4-26b-a4b-it/ (accessed 2026-08-03)
+base_model = "google/gemma-4-26b-a4b-it"
+
+interleaved = true
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "effort"
+values = ["low", "medium", "high"]
+
+[cost]
+input = 0.1
+output = 0.3
+
+[limit]
+context = 256_000
+output = 16_384
@@ -0,0 +1,20 @@
+# Toggle: chat_template_kwargs.enable_thinking = true|false
+# Effort: reasoning_effort = low|medium|high
+# https://developers.cloudflare.com/workers-ai/models/kimi-k2.7-code/ (accessed 2026-08-03)
+base_model = "moonshotai/kimi-k2.7-code"
+temperature = true
+
+[[reasoning_options]]
+type = "toggle"
+
+[[reasoning_options]]
+type = "effort"
+values = ["low", "medium", "high"]
+
+[cost]
+input = 0.95
+output = 4
+cache_read = 0.19
+
+[modalities]
+input = ["text", "image"]
Author	SHA1	Message	Date
Aiden Cline	da7f7853a6	fix(cloudflare-ai-gateway): correct model metadata	2026-08-03 23:16:01 -05:00
Aiden Cline	36235594af	chore: remove Cloudflare gateway sync	2026-08-03 22:02:22 -05:00
Aiden Cline	dfe2237a73	fix(sync): preserve canonical Cloudflare gateway catalog	2026-08-03 21:58:40 -05:00
Aiden Cline	b2aa5f29f5	fix(sync): stop auto-omitting limit.input on AI Gateway models factorBaseModel was called with context:0 when the gateway has no limit override, which tripped baseModelOmit and stripped inherited limit.input. Inherit the base metadata context instead.	2026-08-03 21:56:49 -05:00
Aiden Cline	463a69b73c	feat(sync): add Cloudflare AI Gateway model catalog sync Reuse Workers AI sync secrets against /compat/models (gateway default). Hybrid sync: API membership + list prices; capabilities via base_model. Refresh catalog: add missing OpenAI/Workers AI models, drop nemotron.	2026-08-03 21:56:48 -05:00