diff --git a/providers/nvidia/models/deepseek-ai/deepseek-coder-6.7b-instruct.toml b/providers/nvidia/models/deepseek-ai/deepseek-coder-6.7b-instruct.toml
new file mode 100644
index 00000000..4d653e52
--- /dev/null
+++ b/providers/nvidia/models/deepseek-ai/deepseek-coder-6.7b-instruct.toml
@@ -0,0 +1,21 @@
+name = "Deepseek Coder 6.7b Instruct"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2023-10-29"
+last_updated = "2023-10-29"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/deepseek-ai/deepseek-r1-0528.toml b/providers/nvidia/models/deepseek-ai/deepseek-r1-0528.toml
new file mode 100644
index 00000000..912ad231
--- /dev/null
+++ b/providers/nvidia/models/deepseek-ai/deepseek-r1-0528.toml
@@ -0,0 +1,21 @@
+name = "Deepseek R1 0528"
+attachment = false
+reasoning = true
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2025-05-28"
+last_updated = "2025-05-28"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/deepseek-ai/deepseek-r1.toml b/providers/nvidia/models/deepseek-ai/deepseek-r1.toml
new file mode 100644
index 00000000..f1f14ece
--- /dev/null
+++ b/providers/nvidia/models/deepseek-ai/deepseek-r1.toml
@@ -0,0 +1,21 @@
+name = "Deepseek R1"
+attachment = false
+reasoning = true
+temperature = true
+tool_call = false
+structured_output = false
+release_date = "2025-01-20"
+last_updated = "2025-01-20"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/google/codegemma-1.1-7b.toml b/providers/nvidia/models/google/codegemma-1.1-7b.toml
new file mode 100644
index 00000000..ca07d5ec
--- /dev/null
+++ b/providers/nvidia/models/google/codegemma-1.1-7b.toml
@@ -0,0 +1,21 @@
+name = "Codegemma 1.1 7b"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = false
+structured_output = false
+release_date = "2024-04-30"
+last_updated = "2024-04-30"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/google/codegemma-7b.toml b/providers/nvidia/models/google/codegemma-7b.toml
new file mode 100644
index 00000000..ac3519b0
--- /dev/null
+++ b/providers/nvidia/models/google/codegemma-7b.toml
@@ -0,0 +1,21 @@
+name = "Codegemma 7b"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = false
+structured_output = false
+release_date = "2024-03-21"
+last_updated = "2024-03-21"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/google/gemma-2-27b-it.toml b/providers/nvidia/models/google/gemma-2-27b-it.toml
new file mode 100644
index 00000000..6bcc69a8
--- /dev/null
+++ b/providers/nvidia/models/google/gemma-2-27b-it.toml
@@ -0,0 +1,21 @@
+name = "Gemma 2 27b It"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-06-24"
+last_updated = "2024-06-24"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/google/gemma-2-2b-it.toml b/providers/nvidia/models/google/gemma-2-2b-it.toml
new file mode 100644
index 00000000..e750c621
--- /dev/null
+++ b/providers/nvidia/models/google/gemma-2-2b-it.toml
@@ -0,0 +1,21 @@
+name = "Gemma 2 2b It"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-07-16"
+last_updated = "2024-07-16"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/google/gemma-3-12b-it.toml b/providers/nvidia/models/google/gemma-3-12b-it.toml
new file mode 100644
index 00000000..4313e2ed
--- /dev/null
+++ b/providers/nvidia/models/google/gemma-3-12b-it.toml
@@ -0,0 +1,21 @@
+name = "Gemma 3 12b It"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2025-03-01"
+last_updated = "2025-03-01"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/google/gemma-3-1b-it.toml b/providers/nvidia/models/google/gemma-3-1b-it.toml
new file mode 100644
index 00000000..d10b23aa
--- /dev/null
+++ b/providers/nvidia/models/google/gemma-3-1b-it.toml
@@ -0,0 +1,21 @@
+name = "Gemma 3 1b It"
+attachment = true
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2025-03-10"
+last_updated = "2025-03-10"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text","image"]
+output = ["text"]
diff --git a/providers/nvidia/models/google/gemma-3n-e2b-it.toml b/providers/nvidia/models/google/gemma-3n-e2b-it.toml
new file mode 100644
index 00000000..9bb985e8
--- /dev/null
+++ b/providers/nvidia/models/google/gemma-3n-e2b-it.toml
@@ -0,0 +1,22 @@
+name = "Gemma 3n E2b It"
+attachment = true
+reasoning = false
+temperature = true
+knowledge = "2024-06"
+tool_call = true
+structured_output = true
+release_date = "2025-06-12"
+last_updated = "2025-06-12"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text","image"]
+output = ["text"]
diff --git a/providers/nvidia/models/google/gemma-3n-e4b-it.toml b/providers/nvidia/models/google/gemma-3n-e4b-it.toml
new file mode 100644
index 00000000..f7319994
--- /dev/null
+++ b/providers/nvidia/models/google/gemma-3n-e4b-it.toml
@@ -0,0 +1,22 @@
+name = "Gemma 3n E4b It"
+attachment = true
+reasoning = false
+temperature = true
+knowledge = "2024-06"
+tool_call = true
+structured_output = true
+release_date = "2025-06-03"
+last_updated = "2025-06-03"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text","image"]
+output = ["text"]
diff --git a/providers/nvidia/models/meta/codellama-70b.toml b/providers/nvidia/models/meta/codellama-70b.toml
new file mode 100644
index 00000000..6380e16c
--- /dev/null
+++ b/providers/nvidia/models/meta/codellama-70b.toml
@@ -0,0 +1,21 @@
+name = "Codellama 70b"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = false
+structured_output = false
+release_date = "2024-01-29"
+last_updated = "2024-01-29"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/meta/llama-3.1-405b-instruct.toml b/providers/nvidia/models/meta/llama-3.1-405b-instruct.toml
new file mode 100644
index 00000000..6ae93e51
--- /dev/null
+++ b/providers/nvidia/models/meta/llama-3.1-405b-instruct.toml
@@ -0,0 +1,21 @@
+name = "Llama 3.1 405b Instruct"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-07-16"
+last_updated = "2024-07-16"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/meta/llama-3.1-70b-instruct.toml b/providers/nvidia/models/meta/llama-3.1-70b-instruct.toml
new file mode 100644
index 00000000..75877316
--- /dev/null
+++ b/providers/nvidia/models/meta/llama-3.1-70b-instruct.toml
@@ -0,0 +1,21 @@
+name = "Llama 3.1 70b Instruct"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-07-16"
+last_updated = "2024-07-16"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/meta/llama-3.2-11b-vision-instruct.toml b/providers/nvidia/models/meta/llama-3.2-11b-vision-instruct.toml
new file mode 100644
index 00000000..dbabb665
--- /dev/null
+++ b/providers/nvidia/models/meta/llama-3.2-11b-vision-instruct.toml
@@ -0,0 +1,22 @@
+name = "Llama 3.2 11b Vision Instruct"
+attachment = true
+reasoning = false
+temperature = true
+knowledge = "2023-12"
+tool_call = true
+structured_output = true
+release_date = "2024-09-18"
+last_updated = "2024-09-18"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text","image"]
+output = ["text"]
diff --git a/providers/nvidia/models/meta/llama-3.2-1b-instruct.toml b/providers/nvidia/models/meta/llama-3.2-1b-instruct.toml
new file mode 100644
index 00000000..646f2c4a
--- /dev/null
+++ b/providers/nvidia/models/meta/llama-3.2-1b-instruct.toml
@@ -0,0 +1,22 @@
+name = "Llama 3.2 1b Instruct"
+attachment = false
+reasoning = false
+temperature = true
+knowledge = "2023-12"
+tool_call = true
+structured_output = true
+release_date = "2024-09-18"
+last_updated = "2024-09-18"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/meta/llama-3.3-70b-instruct.toml b/providers/nvidia/models/meta/llama-3.3-70b-instruct.toml
new file mode 100644
index 00000000..e7477811
--- /dev/null
+++ b/providers/nvidia/models/meta/llama-3.3-70b-instruct.toml
@@ -0,0 +1,21 @@
+name = "Llama 3.3 70b Instruct"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-11-26"
+last_updated = "2024-11-26"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/meta/llama-4-maverick-17b-128e-instruct.toml b/providers/nvidia/models/meta/llama-4-maverick-17b-128e-instruct.toml
new file mode 100644
index 00000000..d1032a07
--- /dev/null
+++ b/providers/nvidia/models/meta/llama-4-maverick-17b-128e-instruct.toml
@@ -0,0 +1,22 @@
+name = "Llama 4 Maverick 17b 128e Instruct"
+attachment = true
+reasoning = false
+temperature = true
+knowledge = "2024-02"
+tool_call = true
+structured_output = true
+release_date = "2025-04-01"
+last_updated = "2025-04-01"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text","image"]
+output = ["text"]
diff --git a/providers/nvidia/models/meta/llama-4-scout-17b-16e-instruct.toml b/providers/nvidia/models/meta/llama-4-scout-17b-16e-instruct.toml
new file mode 100644
index 00000000..32c09ba2
--- /dev/null
+++ b/providers/nvidia/models/meta/llama-4-scout-17b-16e-instruct.toml
@@ -0,0 +1,22 @@
+name = "Llama 4 Scout 17b 16e Instruct"
+attachment = true
+reasoning = false
+temperature = true
+knowledge = "2024-02"
+tool_call = true
+structured_output = true
+release_date = "2025-04-02"
+last_updated = "2025-04-02"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text","image"]
+output = ["text"]
diff --git a/providers/nvidia/models/meta/llama3-70b-instruct.toml b/providers/nvidia/models/meta/llama3-70b-instruct.toml
new file mode 100644
index 00000000..c3650086
--- /dev/null
+++ b/providers/nvidia/models/meta/llama3-70b-instruct.toml
@@ -0,0 +1,21 @@
+name = "Llama3 70b Instruct"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-04-17"
+last_updated = "2024-04-17"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/meta/llama3-8b-instruct.toml b/providers/nvidia/models/meta/llama3-8b-instruct.toml
new file mode 100644
index 00000000..9c3c20ca
--- /dev/null
+++ b/providers/nvidia/models/meta/llama3-8b-instruct.toml
@@ -0,0 +1,21 @@
+name = "Llama3 8b Instruct"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-04-17"
+last_updated = "2024-04-17"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/microsoft/phi-3-medium-128k-instruct.toml b/providers/nvidia/models/microsoft/phi-3-medium-128k-instruct.toml
new file mode 100644
index 00000000..3dd52a2c
--- /dev/null
+++ b/providers/nvidia/models/microsoft/phi-3-medium-128k-instruct.toml
@@ -0,0 +1,22 @@
+name = "Phi 3 Medium 128k Instruct"
+attachment = true
+reasoning = false
+temperature = true
+knowledge = "2023-10"
+tool_call = true
+structured_output = true
+release_date = "2024-05-07"
+last_updated = "2024-05-07"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text","image"]
+output = ["text"]
diff --git a/providers/nvidia/models/microsoft/phi-3-medium-4k-instruct.toml b/providers/nvidia/models/microsoft/phi-3-medium-4k-instruct.toml
new file mode 100644
index 00000000..ef9a99bd
--- /dev/null
+++ b/providers/nvidia/models/microsoft/phi-3-medium-4k-instruct.toml
@@ -0,0 +1,22 @@
+name = "Phi 3 Medium 4k Instruct"
+attachment = true
+reasoning = false
+temperature = true
+knowledge = "2023-10"
+tool_call = true
+structured_output = true
+release_date = "2024-05-07"
+last_updated = "2024-05-07"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 4000
+output = 4096
+
+[modalities]
+input = ["text","image"]
+output = ["text"]
diff --git a/providers/nvidia/models/microsoft/phi-3-small-128k-instruct.toml b/providers/nvidia/models/microsoft/phi-3-small-128k-instruct.toml
new file mode 100644
index 00000000..85f8b1c6
--- /dev/null
+++ b/providers/nvidia/models/microsoft/phi-3-small-128k-instruct.toml
@@ -0,0 +1,22 @@
+name = "Phi 3 Small 128k Instruct"
+attachment = true
+reasoning = false
+temperature = true
+knowledge = "2023-10"
+tool_call = true
+structured_output = true
+release_date = "2024-05-07"
+last_updated = "2024-05-07"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text","image"]
+output = ["text"]
diff --git a/providers/nvidia/models/microsoft/phi-3-small-8k-instruct.toml b/providers/nvidia/models/microsoft/phi-3-small-8k-instruct.toml
new file mode 100644
index 00000000..c05bda32
--- /dev/null
+++ b/providers/nvidia/models/microsoft/phi-3-small-8k-instruct.toml
@@ -0,0 +1,22 @@
+name = "Phi 3 Small 8k Instruct"
+attachment = true
+reasoning = false
+temperature = true
+knowledge = "2023-10"
+tool_call = true
+structured_output = true
+release_date = "2024-05-07"
+last_updated = "2024-05-07"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 8000
+output = 4096
+
+[modalities]
+input = ["text","image"]
+output = ["text"]
diff --git a/providers/nvidia/models/microsoft/phi-3-vision-128k-instruct.toml b/providers/nvidia/models/microsoft/phi-3-vision-128k-instruct.toml
new file mode 100644
index 00000000..06a8d376
--- /dev/null
+++ b/providers/nvidia/models/microsoft/phi-3-vision-128k-instruct.toml
@@ -0,0 +1,21 @@
+name = "Phi 3 Vision 128k Instruct"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-05-19"
+last_updated = "2024-05-19"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text","image"]
+output = ["text"]
diff --git a/providers/nvidia/models/microsoft/phi-3.5-moe-instruct.toml b/providers/nvidia/models/microsoft/phi-3.5-moe-instruct.toml
new file mode 100644
index 00000000..00009696
--- /dev/null
+++ b/providers/nvidia/models/microsoft/phi-3.5-moe-instruct.toml
@@ -0,0 +1,21 @@
+name = "Phi 3.5 Moe Instruct"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-08-17"
+last_updated = "2024-08-17"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/microsoft/phi-3.5-vision-instruct.toml b/providers/nvidia/models/microsoft/phi-3.5-vision-instruct.toml
new file mode 100644
index 00000000..fe397e24
--- /dev/null
+++ b/providers/nvidia/models/microsoft/phi-3.5-vision-instruct.toml
@@ -0,0 +1,21 @@
+name = "Phi 3.5 Vision Instruct"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-08-16"
+last_updated = "2024-08-16"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text","image"]
+output = ["text"]
diff --git a/providers/nvidia/models/mistralai/codestral-22b-instruct-v0.1.toml b/providers/nvidia/models/mistralai/codestral-22b-instruct-v0.1.toml
new file mode 100644
index 00000000..cb47b5c5
--- /dev/null
+++ b/providers/nvidia/models/mistralai/codestral-22b-instruct-v0.1.toml
@@ -0,0 +1,21 @@
+name = "Codestral 22b Instruct V0.1"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-05-29"
+last_updated = "2024-05-29"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/mistralai/mamba-codestral-7b-v0.1.toml b/providers/nvidia/models/mistralai/mamba-codestral-7b-v0.1.toml
new file mode 100644
index 00000000..c7c426c2
--- /dev/null
+++ b/providers/nvidia/models/mistralai/mamba-codestral-7b-v0.1.toml
@@ -0,0 +1,21 @@
+name = "Mamba Codestral 7b V0.1"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = false
+structured_output = false
+release_date = "2024-07-16"
+last_updated = "2024-07-16"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/mistralai/mistral-large-2-instruct.toml b/providers/nvidia/models/mistralai/mistral-large-2-instruct.toml
new file mode 100644
index 00000000..3a754ff2
--- /dev/null
+++ b/providers/nvidia/models/mistralai/mistral-large-2-instruct.toml
@@ -0,0 +1,21 @@
+name = "Mistral Large 2 Instruct"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-07-24"
+last_updated = "2024-07-24"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/mistralai/mistral-small-3.1-24b-instruct-2503.toml b/providers/nvidia/models/mistralai/mistral-small-3.1-24b-instruct-2503.toml
new file mode 100644
index 00000000..8c2578dc
--- /dev/null
+++ b/providers/nvidia/models/mistralai/mistral-small-3.1-24b-instruct-2503.toml
@@ -0,0 +1,21 @@
+name = "Mistral Small 3.1 24b Instruct 2503"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2025-03-11"
+last_updated = "2025-03-11"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/nvidia/llama-3.1-nemotron-51b-instruct.toml b/providers/nvidia/models/nvidia/llama-3.1-nemotron-51b-instruct.toml
new file mode 100644
index 00000000..4a1cf4a7
--- /dev/null
+++ b/providers/nvidia/models/nvidia/llama-3.1-nemotron-51b-instruct.toml
@@ -0,0 +1,21 @@
+name = "Llama 3.1 Nemotron 51b Instruct"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-09-22"
+last_updated = "2024-09-22"
+open_weights = false
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/nvidia/llama-3.1-nemotron-70b-instruct.toml b/providers/nvidia/models/nvidia/llama-3.1-nemotron-70b-instruct.toml
new file mode 100644
index 00000000..559a4275
--- /dev/null
+++ b/providers/nvidia/models/nvidia/llama-3.1-nemotron-70b-instruct.toml
@@ -0,0 +1,21 @@
+name = "Llama 3.1 Nemotron 70b Instruct"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-10-12"
+last_updated = "2024-10-12"
+open_weights = false
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/nvidia/llama-3.3-nemotron-super-49b-v1.5.toml b/providers/nvidia/models/nvidia/llama-3.3-nemotron-super-49b-v1.5.toml
new file mode 100644
index 00000000..46b9ac8c
--- /dev/null
+++ b/providers/nvidia/models/nvidia/llama-3.3-nemotron-super-49b-v1.5.toml
@@ -0,0 +1,21 @@
+name = "Llama 3.3 Nemotron Super 49b V1.5"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = false
+structured_output = false
+release_date = "2025-03-16"
+last_updated = "2025-03-16"
+open_weights = false
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/nvidia/llama-3.3-nemotron-super-49b-v1.toml b/providers/nvidia/models/nvidia/llama-3.3-nemotron-super-49b-v1.toml
new file mode 100644
index 00000000..63c9b271
--- /dev/null
+++ b/providers/nvidia/models/nvidia/llama-3.3-nemotron-super-49b-v1.toml
@@ -0,0 +1,21 @@
+name = "Llama 3.3 Nemotron Super 49b V1"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = false
+structured_output = false
+release_date = "2025-03-16"
+last_updated = "2025-03-16"
+open_weights = false
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/nvidia/llama3-chatqa-1.5-70b.toml b/providers/nvidia/models/nvidia/llama3-chatqa-1.5-70b.toml
new file mode 100644
index 00000000..5bef2305
--- /dev/null
+++ b/providers/nvidia/models/nvidia/llama3-chatqa-1.5-70b.toml
@@ -0,0 +1,21 @@
+name = "Llama3 Chatqa 1.5 70b"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-04-28"
+last_updated = "2024-04-28"
+open_weights = false
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/nvidia/nemotron-4-340b-instruct.toml b/providers/nvidia/models/nvidia/nemotron-4-340b-instruct.toml
new file mode 100644
index 00000000..db129f99
--- /dev/null
+++ b/providers/nvidia/models/nvidia/nemotron-4-340b-instruct.toml
@@ -0,0 +1,21 @@
+name = "Nemotron 4 340b Instruct"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-06-13"
+last_updated = "2024-06-13"
+open_weights = false
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/qwen/qwen2.5-coder-32b-instruct.toml b/providers/nvidia/models/qwen/qwen2.5-coder-32b-instruct.toml
new file mode 100644
index 00000000..484a4b6e
--- /dev/null
+++ b/providers/nvidia/models/qwen/qwen2.5-coder-32b-instruct.toml
@@ -0,0 +1,21 @@
+name = "Qwen2.5 Coder 32b Instruct"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-11-06"
+last_updated = "2024-11-06"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/qwen/qwen2.5-coder-7b-instruct.toml b/providers/nvidia/models/qwen/qwen2.5-coder-7b-instruct.toml
new file mode 100644
index 00000000..269dbbf8
--- /dev/null
+++ b/providers/nvidia/models/qwen/qwen2.5-coder-7b-instruct.toml
@@ -0,0 +1,21 @@
+name = "Qwen2.5 Coder 7b Instruct"
+attachment = false
+reasoning = false
+temperature = true
+tool_call = true
+structured_output = true
+release_date = "2024-09-17"
+last_updated = "2024-09-17"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]
diff --git a/providers/nvidia/models/qwen/qwq-32b.toml b/providers/nvidia/models/qwen/qwq-32b.toml
new file mode 100644
index 00000000..15ebe81d
--- /dev/null
+++ b/providers/nvidia/models/qwen/qwq-32b.toml
@@ -0,0 +1,21 @@
+name = "Qwq 32b"
+attachment = false
+reasoning = true
+temperature = true
+tool_call = false
+structured_output = false
+release_date = "2025-03-05"
+last_updated = "2025-03-05"
+open_weights = true
+
+[cost]
+input = 0.00
+output = 0.00
+
+[limit]
+context = 128000
+output = 4096
+
+[modalities]
+input = ["text"]
+output = ["text"]