From e52ae039f2e3ffc3874c1fa2052fa4de501c3b85 Mon Sep 17 00:00:00 2001
From: "devin-ai-integration[bot]"
 <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Date: Wed, 12 Aug 2026 21:48:02 +0000
Subject: [PATCH] feat(model_prices): add NVIDIA Nemotron 3.5 Lightning on
 OpenRouter and DeepInfra (#36696)

* feat(model_prices): add NVIDIA Nemotron 3.5 Lightning on OpenRouter and DeepInfra

Nemotron 3.5 Lightning shipped 2026-08-11 with public per-token pricing on
OpenRouter and DeepInfra at $0.05/M in and $0.20/M out. Without cost map
entries both ids raise "This model isn't mapped yet" and log at zero spend.

* fix(model_prices): stop asserting an output cap for Nemotron 3.5 Lightning

262144 is the native context window, not the output budget, and neither
OpenRouter nor DeepInfra publishes an output cap. Keeps max_input_tokens at the
native 256K window: 1M needs VLLM_ALLOW_LONG_MAX_MODEL_LEN=1 on a self-hosted
deployment, so it is not what these hosted endpoints serve.

* chore(tests): drop the Nemotron 3.5 Lightning metadata test

Requested on the review thread: the cost map entries stand on their own.

---------

Co-authored-by: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
---
 ...odel_prices_and_context_window_backup.json | 22 +++++++++++++++++++
 model_prices_and_context_window.json          | 22 +++++++++++++++++++
 2 files changed, 44 insertions(+)

diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
index b12e4a9fea3..00ba060e1e5 100644
--- a/litellm/model_prices_and_context_window_backup.json
+++ b/litellm/model_prices_and_context_window_backup.json
@@ -15552,6 +15552,17 @@
         "supports_tool_choice": true,
         "supports_function_calling": true
     },
+    "deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning": {
+        "max_input_tokens": 262144,
+        "input_cost_per_token": 5e-08,
+        "output_cost_per_token": 2e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
+        "source": "https://deepinfra.com/nvidia/NVIDIA-Nemotron-3.5-Lightning",
+        "supports_tool_choice": true,
+        "supports_function_calling": true,
+        "supports_reasoning": true
+    },
     "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2": {
         "max_tokens": 131072,
         "max_input_tokens": 131072,
@@ -31754,6 +31765,17 @@
         "supports_video_input": true,
         "supports_vision": true
     },
+    "openrouter/nvidia/nemotron-3.5-lightning": {
+        "input_cost_per_token": 5e-08,
+        "litellm_provider": "openrouter",
+        "max_input_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 2e-07,
+        "source": "https://openrouter.ai/nvidia/nemotron-3.5-lightning",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
     "openrouter/openai/gpt-3.5-turbo": {
         "input_cost_per_token": 1.5e-06,
         "litellm_provider": "openrouter",
diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index b12e4a9fea3..00ba060e1e5 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -15552,6 +15552,17 @@
         "supports_tool_choice": true,
         "supports_function_calling": true
     },
+    "deepinfra/nvidia/NVIDIA-Nemotron-3.5-Lightning": {
+        "max_input_tokens": 262144,
+        "input_cost_per_token": 5e-08,
+        "output_cost_per_token": 2e-07,
+        "litellm_provider": "deepinfra",
+        "mode": "chat",
+        "source": "https://deepinfra.com/nvidia/NVIDIA-Nemotron-3.5-Lightning",
+        "supports_tool_choice": true,
+        "supports_function_calling": true,
+        "supports_reasoning": true
+    },
     "deepinfra/nvidia/NVIDIA-Nemotron-Nano-9B-v2": {
         "max_tokens": 131072,
         "max_input_tokens": 131072,
@@ -31754,6 +31765,17 @@
         "supports_video_input": true,
         "supports_vision": true
     },
+    "openrouter/nvidia/nemotron-3.5-lightning": {
+        "input_cost_per_token": 5e-08,
+        "litellm_provider": "openrouter",
+        "max_input_tokens": 262144,
+        "mode": "chat",
+        "output_cost_per_token": 2e-07,
+        "source": "https://openrouter.ai/nvidia/nemotron-3.5-lightning",
+        "supports_function_calling": true,
+        "supports_reasoning": true,
+        "supports_tool_choice": true
+    },
     "openrouter/openai/gpt-3.5-turbo": {
         "input_cost_per_token": 1.5e-06,
         "litellm_provider": "openrouter",