diff --git a/openapi.yaml b/openapi.yaml
index dea4b15..13d9f86 100644
--- a/openapi.yaml
+++ b/openapi.yaml
@@ -1192,11 +1192,12 @@ paths:
             )
 
             response = client.chat.completions.create(
-                model="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+                model="Qwen/Qwen3.5-9B",
                 messages=[
                     {"role": "system", "content": "You are a helpful assistant."},
                     {"role": "user", "content": "What are some fun things to do in New York?"},
-                ]
+                ],
+                reasoning={"enabled": False}
             )
         - lang: Python
           label: Together AI SDK (v1)
@@ -1209,11 +1210,12 @@ paths:
             )
 
             response = client.chat.completions.create(
-                model="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+                model="Qwen/Qwen3.5-9B",
                 messages=[
                     {"role": "system", "content": "You are a helpful assistant."},
                     {"role": "user", "content": "What are some fun things to do in New York?"},
-                ]
+                ],
+                reasoning={"enabled": False}
             )
 
             print(response.choices[0].message.content)
@@ -1227,11 +1229,12 @@ paths:
             });
 
             const response = await client.chat.completions.create({
-              model: "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+              model: "Qwen/Qwen3.5-9B",
               messages: [
                 { role: "system", content: "You are a helpful assistant." },
                 { role: "user", "content": "What are some fun things to do in New York?" },
               ],
+              reasoning: { enabled: false },
             });
 
             console.log(response.choices[0].message?.content);
@@ -1245,11 +1248,12 @@ paths:
             });
 
             const response = await client.chat.completions.create({
-              model: "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+              model: "Qwen/Qwen3.5-9B",
               messages: [
                 { role: "system", content: "You are a helpful assistant." },
                 { role: "user", "content": "What are some fun things to do in New York?" },
               ],
+              reasoning: { enabled: false },
             });
 
             console.log(response.choices[0].message?.content);
@@ -1260,11 +1264,12 @@ paths:
                  -H "Authorization: Bearer $TOGETHER_API_KEY" \
                  -H "Content-Type: application/json" \
                  -d '{
-                   "model": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+                   "model": "Qwen/Qwen3.5-9B",
                    "messages": [
                      {"role": "system", "content": "You are a helpful assistant."},
                      {"role": "user", "content": "What are some fun things to do in New York?"}
-                   ]
+                   ],
+                   "reasoning": {"enabled": false}
                  }'
       operationId: chat-completions
       requestBody:
@@ -1337,7 +1342,7 @@ paths:
             )
 
             response = client.completions.create(
-                model="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+                model="Qwen/Qwen3.5-9B",
                 prompt="The largest city in France is",
                 max_tokens=1
             )
@@ -1354,7 +1359,7 @@ paths:
             )
 
             response = client.completions.create(
-                model="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+                model="Qwen/Qwen3.5-9B",
                 prompt="The largest city in France is",
                 max_tokens=1
             )
@@ -1370,7 +1375,7 @@ paths:
             });
 
             const response = await client.completions.create({
-              model: "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+              model: "Qwen/Qwen3.5-9B",
               prompt: "The largest city in France is",
               max_tokens: 1,
             });
@@ -1386,7 +1391,7 @@ paths:
             });
 
             const response = await client.completions.create({
-              model: "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+              model: "Qwen/Qwen3.5-9B",
               prompt: "The largest city in France is",
               max_tokens: 1
             });
@@ -1399,7 +1404,7 @@ paths:
                  -H "Authorization: Bearer $TOGETHER_API_KEY" \
                  -H "Content-Type: application/json" \
                  -d '{
-                   "model": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+                   "model": "Qwen/Qwen3.5-9B",
                    "prompt": "The largest city in France is",
                    "max_tokens": 1
                  }'
@@ -5126,7 +5131,7 @@ paths:
             )
 
             endpoint = client.endpoints.create(
-                model="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+                model="Qwen/Qwen3.5-9B-FP8",
                 hardware="1x_nvidia_a100_80gb_sxm",
                 autoscaling={
                   "min_replicas": 2,
@@ -5146,7 +5151,7 @@ paths:
             )
 
             endpoint = client.endpoints.create(
-                model="meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+                model="Qwen/Qwen3.5-9B-FP8",
                 hardware="1x_nvidia_a100_80gb_sxm",
                 min_replicas=2,
                 max_replicas=5,
@@ -5163,7 +5168,7 @@ paths:
             });
 
             const endpoint = await client.endpoints.create({
-              model: "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+              model: "Qwen/Qwen3.5-9B-FP8",
               hardware: "1x_nvidia_a100_80gb_sxm",
               autoscaling: {
                 max_replicas: 5,
@@ -5182,7 +5187,7 @@ paths:
             });
 
             const endpoint = await client.endpoints.create({
-              model: "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+              model: "Qwen/Qwen3.5-9B-FP8",
               hardware: "1x_nvidia_a100_80gb_sxm",
               autoscaling: {
                 max_replicas: 5,
@@ -5198,7 +5203,7 @@ paths:
                  -H "Authorization: Bearer $TOGETHER_API_KEY" \
                  -H "Content-Type: application/json" \
                  -d '{
-                   "model": "meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo",
+                   "model": "Qwen/Qwen3.5-9B-FP8",
                    "hardware": "1x_nvidia_a100_80gb_sxm",
                    "autoscaling": {
                      "max_replicas": 5,
@@ -6277,14 +6282,14 @@ paths:
                 type="classify",
                 parameters=ParametersEvaluationClassifyParameters(
                     judge=ParametersEvaluationClassifyParametersJudge(
-                        model="meta-llama/Llama-3.1-70B-Instruct-Turbo",
+                        model="openai/gpt-oss-120b",
                         model_source="serverless",
                         system_template="You are an expert evaluator...",
                     ),
                     input_data_file_path="file-abc123",
                     labels=["good", "bad"],
                     pass_labels=["good"],
-                    model_to_evaluate="meta-llama/Llama-3.1-8B-Instruct-Turbo"
+                    model_to_evaluate="Qwen/Qwen3.5-9B"
                 )
             )
 
@@ -6301,12 +6306,12 @@ paths:
 
             response = client.evaluation.create(
                 type="classify",
-                judge_model_name="meta-llama/Llama-3.1-70B-Instruct-Turbo",
+                judge_model_name="openai/gpt-oss-120b",
                 judge_system_template="You are an expert evaluator...",
                 input_data_file_path="file-abc123",
                 labels=["good", "bad"],
                 pass_labels=["good"],
-                model_to_evaluate="meta-llama/Llama-3.1-8B-Instruct-Turbo"
+                model_to_evaluate="Qwen/Qwen3.5-9B"
             )
 
             print(response.workflow_id)
@@ -6323,14 +6328,14 @@ paths:
               type: 'classify',
               parameters: {
                 judge: {
-                  model: 'meta-llama/Llama-3.1-70B-Instruct-Turbo',
+                  model: 'openai/gpt-oss-120b',
                   model_source: 'serverless',
                   system_template: 'You are an expert evaluator...',
                 },
                 input_data_file_path: 'file-abc123',
                 labels: ['good', 'bad'],
                 pass_labels: ['good'],
-                model_to_evaluate: 'meta-llama/Llama-3.1-8B-Instruct-Turbo',
+                model_to_evaluate: 'Qwen/Qwen3.5-9B',
               },
             });
 
@@ -6348,14 +6353,14 @@ paths:
               type: 'classify',
               parameters: {
                 judge: {
-                  model: 'meta-llama/Llama-3.1-70B-Instruct-Turbo',
+                  model: 'openai/gpt-oss-120b',
                   model_source: 'serverless',
                   system_template: 'You are an expert evaluator...',
                 },
                 input_data_file_path: 'file-abc123',
                 labels: ['good', 'bad'],
                 pass_labels: ['good'],
-                model_to_evaluate: 'meta-llama/Llama-3.1-8B-Instruct-Turbo',
+                model_to_evaluate: 'Qwen/Qwen3.5-9B',
               },
             });
 
@@ -9096,15 +9101,15 @@ components:
             The name of the model to query.<br>
             <br>
             [See all of Together AI's chat models](https://docs.together.ai/docs/serverless-models#chat-models)
-          example: meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
+          example: Qwen/Qwen3.5-9B
           anyOf:
             - type: string
               enum:
                 - Qwen/Qwen2.5-72B-Instruct-Turbo
                 - Qwen/Qwen2.5-7B-Instruct-Turbo
+                - Qwen/Qwen3.5-9B
                 - meta-llama/Meta-Llama-3.1-405B-Instruct-Turbo
                 - meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo
-                - meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo
             - type: string
         max_tokens:
           type: integer
@@ -11879,7 +11884,7 @@ components:
         model_id:
           type: string
           description: 'Model to use for processing batch requests'
-          example: 'meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo'
+          example: 'Qwen/Qwen3.5-9B'
     BatchErrorResponse:
       type: object
       properties:
@@ -11930,7 +11935,7 @@ components:
           description: 'Completion progress (0.0 to 100)'
         model_id:
           type: string
-          example: 'meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo'
+          example: 'Qwen/Qwen3.5-9B'
           description: 'Model used for processing requests'
         output_file_id:
           type: string