diff --git a/tests/integration/common/recordings/02c93bb3c314427bae2b7a7a6f054792b9f22d2cb4522eab802810be8672d3dc.json b/tests/integration/common/recordings/02c93bb3c314427bae2b7a7a6f054792b9f22d2cb4522eab802810be8672d3dc.json
index b57937c0a..0d77df1f0 100644
--- a/tests/integration/common/recordings/02c93bb3c314427bae2b7a7a6f054792b9f22d2cb4522eab802810be8672d3dc.json
+++ b/tests/integration/common/recordings/02c93bb3c314427bae2b7a7a6f054792b9f22d2cb4522eab802810be8672d3dc.json
@@ -12,7 +12,27 @@
     "body": {
       "__type__": "ollama._types.ProcessResponse",
       "__data__": {
-        "models": []
+        "models": [
+          {
+            "model": "llama3.2:3b",
+            "name": "llama3.2:3b",
+            "digest": "a80c4f17acd55265feec403c7aef86be0c25983ab279d83f3bcd3abbcb5b8b72",
+            "expires_at": "2025-10-04T12:20:09.202126-07:00",
+            "size": 3367856128,
+            "size_vram": 3367856128,
+            "details": {
+              "parent_model": "",
+              "format": "gguf",
+              "family": "llama",
+              "families": [
+                "llama"
+              ],
+              "parameter_size": "3.2B",
+              "quantization_level": "Q4_K_M"
+            },
+            "context_length": 4096
+          }
+        ]
       }
     },
     "is_streaming": false
diff --git a/tests/integration/inference/recordings/28b529023374d3345f46c0b183ee352ff5014ff344238bd40b820c61510097eb.json b/tests/integration/inference/recordings/28b529023374d3345f46c0b183ee352ff5014ff344238bd40b820c61510097eb.json
index 9f75a03de..e1d9a8658 100644
--- a/tests/integration/inference/recordings/28b529023374d3345f46c0b183ee352ff5014ff344238bd40b820c61510097eb.json
+++ b/tests/integration/inference/recordings/28b529023374d3345f46c0b183ee352ff5014ff344238bd40b820c61510097eb.json
@@ -14,12 +14,12 @@
       "__data__": {
         "models": [
           {
-            "model": "llama3.2:3b-instruct-fp16",
-            "name": "llama3.2:3b-instruct-fp16",
-            "digest": "195a8c01d91ec3cb1e0aad4624a51f2602c51fa7d96110f8ab5a20c84081804d",
-            "expires_at": "2025-10-03T20:06:59.383555-07:00",
-            "size": 7919570944,
-            "size_vram": 7919570944,
+            "model": "llama3.2:3b",
+            "name": "llama3.2:3b",
+            "digest": "a80c4f17acd55265feec403c7aef86be0c25983ab279d83f3bcd3abbcb5b8b72",
+            "expires_at": "2025-10-04T12:20:09.202126-07:00",
+            "size": 3367856128,
+            "size_vram": 3367856128,
             "details": {
               "parent_model": "",
               "format": "gguf",
@@ -28,45 +28,7 @@
                 "llama"
               ],
               "parameter_size": "3.2B",
-              "quantization_level": "F16"
-            },
-            "context_length": 4096
-          },
-          {
-            "model": "all-minilm:l6-v2",
-            "name": "all-minilm:l6-v2",
-            "digest": "1b226e2802dbb772b5fc32a58f103ca1804ef7501331012de126ab22f67475ef",
-            "expires_at": "2025-10-03T20:06:55.533878-07:00",
-            "size": 585846784,
-            "size_vram": 585846784,
-            "details": {
-              "parent_model": "",
-              "format": "gguf",
-              "family": "bert",
-              "families": [
-                "bert"
-              ],
-              "parameter_size": "23M",
-              "quantization_level": "F16"
-            },
-            "context_length": 256
-          },
-          {
-            "model": "llama-guard3:1b",
-            "name": "llama-guard3:1b",
-            "digest": "494147e06bf99e10dbe67b63a07ac81c162f18ef3341aa3390007ac828571b3b",
-            "expires_at": "2025-10-03T20:06:23.356289-07:00",
-            "size": 2350966784,
-            "size_vram": 2350966784,
-            "details": {
-              "parent_model": "",
-              "format": "gguf",
-              "family": "llama",
-              "families": [
-                "llama"
-              ],
-              "parameter_size": "1.5B",
-              "quantization_level": "Q8_0"
+              "quantization_level": "Q4_K_M"
             },
             "context_length": 4096
           }
diff --git a/tests/integration/inference/recordings/28b74a89cdc85de62395836bb21baa777d3197245698f4a7531afa0a15c11d1c.json b/tests/integration/inference/recordings/28b74a89cdc85de62395836bb21baa777d3197245698f4a7531afa0a15c11d1c.json
index 2b6ca43e2..548ce9cfb 100644
--- a/tests/integration/inference/recordings/28b74a89cdc85de62395836bb21baa777d3197245698f4a7531afa0a15c11d1c.json
+++ b/tests/integration/inference/recordings/28b74a89cdc85de62395836bb21baa777d3197245698f4a7531afa0a15c11d1c.json
@@ -13,11 +13,30 @@
       "__type__": "ollama._types.ProcessResponse",
       "__data__": {
         "models": [
+          {
+            "model": "llama3.2:3b",
+            "name": "llama3.2:3b",
+            "digest": "a80c4f17acd55265feec403c7aef86be0c25983ab279d83f3bcd3abbcb5b8b72",
+            "expires_at": "2025-10-04T12:20:09.202126-07:00",
+            "size": 3367856128,
+            "size_vram": 3367856128,
+            "details": {
+              "parent_model": "",
+              "format": "gguf",
+              "family": "llama",
+              "families": [
+                "llama"
+              ],
+              "parameter_size": "3.2B",
+              "quantization_level": "Q4_K_M"
+            },
+            "context_length": 4096
+          },
           {
             "model": "llama3.2:3b-instruct-fp16",
             "name": "llama3.2:3b-instruct-fp16",
             "digest": "195a8c01d91ec3cb1e0aad4624a51f2602c51fa7d96110f8ab5a20c84081804d",
-            "expires_at": "2025-10-03T20:07:04.627464-07:00",
+            "expires_at": "2025-10-04T11:27:25.408562-07:00",
             "size": 7919570944,
             "size_vram": 7919570944,
             "details": {
@@ -31,44 +50,6 @@
               "quantization_level": "F16"
             },
             "context_length": 4096
-          },
-          {
-            "model": "all-minilm:l6-v2",
-            "name": "all-minilm:l6-v2",
-            "digest": "1b226e2802dbb772b5fc32a58f103ca1804ef7501331012de126ab22f67475ef",
-            "expires_at": "2025-10-03T20:06:55.533878-07:00",
-            "size": 585846784,
-            "size_vram": 585846784,
-            "details": {
-              "parent_model": "",
-              "format": "gguf",
-              "family": "bert",
-              "families": [
-                "bert"
-              ],
-              "parameter_size": "23M",
-              "quantization_level": "F16"
-            },
-            "context_length": 256
-          },
-          {
-            "model": "llama-guard3:1b",
-            "name": "llama-guard3:1b",
-            "digest": "494147e06bf99e10dbe67b63a07ac81c162f18ef3341aa3390007ac828571b3b",
-            "expires_at": "2025-10-03T20:06:23.356289-07:00",
-            "size": 2350966784,
-            "size_vram": 2350966784,
-            "details": {
-              "parent_model": "",
-              "format": "gguf",
-              "family": "llama",
-              "families": [
-                "llama"
-              ],
-              "parameter_size": "1.5B",
-              "quantization_level": "Q8_0"
-            },
-            "context_length": 4096
           }
         ]
       }
diff --git a/tests/integration/inference/recordings/acdd905b048175b96ff61d93fd81d650b26bda3cf12e1f0cbd2820ae73f4f2f9.json b/tests/integration/inference/recordings/acdd905b048175b96ff61d93fd81d650b26bda3cf12e1f0cbd2820ae73f4f2f9.json
index c0a337fba..70651cad0 100644
--- a/tests/integration/inference/recordings/acdd905b048175b96ff61d93fd81d650b26bda3cf12e1f0cbd2820ae73f4f2f9.json
+++ b/tests/integration/inference/recordings/acdd905b048175b96ff61d93fd81d650b26bda3cf12e1f0cbd2820ae73f4f2f9.json
@@ -1,4 +1,5 @@
 {
+  "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-inference:chat_completion:non_streaming_01]",
   "request": {
     "method": "POST",
     "url": "http://0.0.0.0:11434/v1/v1/chat/completions",
@@ -8,7 +9,7 @@
       "messages": [
         {
           "role": "user",
-          "content": "Test trace openai 0"
+          "content": "Which planet do humans live on?"
         }
       ],
       "stream": false
@@ -20,14 +21,14 @@
     "body": {
       "__type__": "openai.types.chat.chat_completion.ChatCompletion",
       "__data__": {
-        "id": "rec-140187e305dc",
+        "id": "rec-acdd905b0481",
         "choices": [
           {
             "finish_reason": "stop",
             "index": 0,
             "logprobs": null,
             "message": {
-              "content": "I'm happy to help you test the OpenAI API, however I can not access the API.\n\nInstead why don't we follow these steps:\n\n*   Check documentation\n*   Contact support\n*   Reach out to their community forum. \n\nLet me know if I can be of any additional assistance",
+              "content": "Humans live on Earth. It is the third planet from the Sun and the only known planet in the universe that supports life.",
               "refusal": null,
               "role": "assistant",
               "annotations": null,
@@ -43,9 +44,9 @@
         "service_tier": null,
         "system_fingerprint": "fp_ollama",
         "usage": {
-          "completion_tokens": 61,
-          "prompt_tokens": 31,
-          "total_tokens": 92,
+          "completion_tokens": 26,
+          "prompt_tokens": 32,
+          "total_tokens": 58,
           "completion_tokens_details": null,
           "prompt_tokens_details": null
         }
diff --git a/tests/integration/inference/recordings/d94bbf50e75423e35f37c42dff284c2589ce81445e3245e5810e5adad8194684.json b/tests/integration/inference/recordings/d94bbf50e75423e35f37c42dff284c2589ce81445e3245e5810e5adad8194684.json
index 3dc394a50..2e81e04ad 100644
--- a/tests/integration/inference/recordings/d94bbf50e75423e35f37c42dff284c2589ce81445e3245e5810e5adad8194684.json
+++ b/tests/integration/inference/recordings/d94bbf50e75423e35f37c42dff284c2589ce81445e3245e5810e5adad8194684.json
@@ -1,4 +1,5 @@
 {
+  "test_id": "tests/integration/inference/test_openai_completion.py::test_openai_chat_completion_non_streaming[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-inference:chat_completion:non_streaming_02]",
   "request": {
     "method": "POST",
     "url": "http://0.0.0.0:11434/v1/v1/chat/completions",
@@ -20,14 +21,14 @@
     "body": {
       "__type__": "openai.types.chat.chat_completion.ChatCompletion",
       "__data__": {
-        "id": "rec-0e8f2b001dd9",
+        "id": "rec-d94bbf50e754",
         "choices": [
           {
             "finish_reason": "stop",
             "index": 0,
             "logprobs": null,
             "message": {
-              "content": "The planet Saturn has rings.",
+              "content": "You are probably thinking of Saturn. Saturn is the only planet in our solar system with noticeable ring systems, and its main ring system is called the Solar System's S Ring.",
               "refusal": null,
               "role": "assistant",
               "annotations": null,
@@ -43,9 +44,9 @@
         "service_tier": null,
         "system_fingerprint": "fp_ollama",
         "usage": {
-          "completion_tokens": 7,
+          "completion_tokens": 36,
           "prompt_tokens": 39,
-          "total_tokens": 46,
+          "total_tokens": 75,
           "completion_tokens_details": null,
           "prompt_tokens_details": null
         }