From 2968087d3787281cf500a059d69aa8d9ebb950ca Mon Sep 17 00:00:00 2001
From: Paul Gauthier <paul@aider.chat>
Date: Mon, 20 Jan 2025 10:09:48 -0800
Subject: [PATCH] more deepseek config

---
 HISTORY.md                          |  5 ++++-
 aider/models.py                     | 16 ++++++++++++++++
 aider/resources/model-metadata.json | 18 +++++++++++++++++-
 3 files changed, 37 insertions(+), 2 deletions(-)

diff --git a/HISTORY.md b/HISTORY.md
index 045001b29..248825ccb 100644
--- a/HISTORY.md
+++ b/HISTORY.md
@@ -2,6 +2,9 @@
 
 ### main branch
 
+- Support for DeepSeek R1.
+  - Use shortcut: `--model r1`
+  - Also via OpenRouter: `--model openrouter/deepseek/deepseek-r1`
 - Added `--line-endings` for file writing, by Titusz Pan.
 - Added examples_as_sys_msg=True for GPT-4o models, improves benchmark scores.
 - Bumped all dependencies, to pick up litellm support for o1 system messages.
@@ -10,7 +13,7 @@
 ### Aider v0.71.1
 
 - Fix permissions issue in Docker images.
-- Added read-only file announcements to chat.
+- Added read-only file announcements.
 - Bugfix: ASCII fallback for unicode errors.
 - Bugfix: integer indices for list slicing in repomap calculations.
 
diff --git a/aider/models.py b/aider/models.py
index e9354213e..a75d604ce 100644
--- a/aider/models.py
+++ b/aider/models.py
@@ -76,6 +76,7 @@ MODEL_ALIASES = {
     "3": "gpt-3.5-turbo",
     # Other models
     "deepseek": "deepseek/deepseek-chat",
+    "r1": "deepseek/deepseek-reasoner",
     "flash": "gemini/gemini-2.0-flash-exp",
 }
 
@@ -622,6 +623,21 @@ MODEL_SETTINGS = [
         use_repo_map=True,
         send_undo_reply=False,
     ),
+    ModelSettings(
+        "openrouter/deepseek/deepseek-r1",
+        "diff",
+        weak_model_name="openrouter/deepseek/deepseek-chat",
+        editor_model_name="openrouter/deepseek/deepseek-chat",
+        editor_edit_format="editor-diff",
+        use_repo_map=True,
+        examples_as_sys_msg=True,
+        use_temperature=False,
+        reminder="user",
+        caches_by_default=True,
+        extra_params={
+            "max_tokens": 8192,
+        },
+    ),
     ModelSettings(
         "deepseek/deepseek-reasoner",
         "diff",
diff --git a/aider/resources/model-metadata.json b/aider/resources/model-metadata.json
index d8ab09461..7c46f948a 100644
--- a/aider/resources/model-metadata.json
+++ b/aider/resources/model-metadata.json
@@ -1,7 +1,23 @@
 {
     "deepseek-reasoner": {
         "max_tokens": 8192,
-        "max_input_tokens": 128000,
+        "max_input_tokens": 64000,
+        "max_output_tokens": 8192,
+        "input_cost_per_token": 0.00000055,
+        "input_cost_per_token_cache_hit": 0.00000014,
+        "cache_read_input_token_cost": 0.00000014,
+        "cache_creation_input_token_cost": 0.0,
+        "output_cost_per_token": 0.00000219,
+        "litellm_provider": "deepseek",
+        "mode": "chat",
+        //"supports_function_calling": true, 
+        "supports_assistant_prefill": true,
+        //"supports_tool_choice": true,
+        "supports_prompt_caching": true
+    },
+    "openrouter/deepseek/deepseek-r1": {
+        "max_tokens": 8192,
+        "max_input_tokens": 64000,
         "max_output_tokens": 8192,
         "input_cost_per_token": 0.00000055,
         "input_cost_per_token_cache_hit": 0.00000014,