diff --git a/models/google/gemini-3.7-flash.toml b/models/google/gemini-3.7-flash.toml
new file mode 100644
index 0000000000..044c4a2efe
--- /dev/null
+++ b/models/google/gemini-3.7-flash.toml
@@ -0,0 +1,68 @@
+name = "Gemini 3.7 Flash"
+description = "High-efficiency Gemini model for agentic workflows, coding, and multimodal reasoning"
+family = "gemini-flash"
+release_date = "2026-08-13"
+last_updated = "2026-08-13"
+attachment = true
+reasoning = true
+temperature = true
+tool_call = true
+structured_output = true
+knowledge = "2026-03"
+open_weights = false
+
+[limit]
+context = 1_048_576
+output = 65_536
+
+[modalities]
+input = ["text", "image", "video", "audio", "pdf"]
+output = ["text"]
+
+[[benchmarks]]
+name = "FrontierCode"
+score = 43.6
+metric = "score"
+version = "1.1 Main"
+source = "https://deepmind.google/models/model-cards/gemini-3-7-flash/"
+date = "2026-08-13"
+
+[[benchmarks]]
+name = "DeepSWE"
+score = 65.3
+metric = "resolve rate"
+version = "1.1"
+source = "https://deepmind.google/models/model-cards/gemini-3-7-flash/"
+date = "2026-08-13"
+
+[[benchmarks]]
+name = "Terminal-Bench"
+score = 85.8
+metric = "accuracy"
+version = "2.1"
+source = "https://deepmind.google/models/model-cards/gemini-3-7-flash/"
+date = "2026-08-13"
+
+[[benchmarks]]
+name = "AutomationBench"
+score = 30.4
+metric = "accuracy"
+dataset = "private set"
+source = "https://deepmind.google/models/model-cards/gemini-3-7-flash/"
+date = "2026-08-13"
+
+[[benchmarks]]
+name = "GDP.pdf"
+score = 34.0
+metric = "accuracy"
+source = "https://deepmind.google/models/model-cards/gemini-3-7-flash/"
+date = "2026-08-13"
+
+[[benchmarks]]
+name = "GDM-MRCR"
+score = 97.0
+metric = "accuracy"
+variant = "128k average, 8-needle"
+version = "v2"
+source = "https://deepmind.google/models/model-cards/gemini-3-7-flash/"
+date = "2026-08-13"
diff --git a/providers/google-vertex/models/gemini-3.7-flash.toml b/providers/google-vertex/models/gemini-3.7-flash.toml
new file mode 100644
index 0000000000..3da8cc6ab6
--- /dev/null
+++ b/providers/google-vertex/models/gemini-3.7-flash.toml
@@ -0,0 +1,12 @@
+# Sources:
+# - https://cloud.google.com/gemini-enterprise-agent-platform/generative-ai/pricing
+# - https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/gemini/3-7-flash
+# - https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/thinking
+base_model = "google/gemini-3.7-flash"
+reasoning_options = [{ type = "effort", values = ["low", "medium", "high"] }]
+
+[cost]
+input = 0.75
+output = 3.75
+cache_read = 0.075
+input_audio = 0.75
diff --git a/providers/google/models/gemini-3.7-flash.toml b/providers/google/models/gemini-3.7-flash.toml
new file mode 100644
index 0000000000..eb3c50e2e2
--- /dev/null
+++ b/providers/google/models/gemini-3.7-flash.toml
@@ -0,0 +1,15 @@
+# Sources:
+# - https://blog.google/innovation-and-ai/models-and-research/gemini-models/introducing-gemini-3-7-flash/
+# - https://ai.google.dev/gemini-api/docs/pricing
+# - https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/thinking
+base_model = "google/gemini-3.7-flash"
+
+[[reasoning_options]]
+type = "effort"
+values = ["low", "medium", "high"]
+
+[cost]
+input = 0.75
+output = 3.75
+cache_read = 0.075
+input_audio = 0.75