feat: together now supports base64 embedding encoding (#3559)

# What does this PR do?

use together's new base64 support

## Test Plan

recordings for: ./scripts/integration-tests.sh --stack-config
server:ci-tests --suite base --setup together --subdirs inference
--pattern openai

tests/integration/recordings/responses/c8a59b661fd5.json

@@ -0,0 +1,46 @@
+{
+  "request": {
+    "method": "POST",
+    "url": "https://api.together.xyz/v1/v1/completions",
+    "headers": {},
+    "body": {
+      "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+      "prompt": "Say completions",
+      "max_tokens": 20,
+      "extra_body": {}
+    },
+    "endpoint": "/v1/completions",
+    "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free"
+  },
+  "response": {
+    "body": {
+      "__type__": "openai.types.completion.Completion",
+      "__data__": {
+        "id": "oCfwct8-4Yz4kd-984c2861287d4cc3",
+        "choices": [
+          {
+            "finish_reason": "length",
+            "index": 0,
+            "logprobs": null,
+            "text": " of the following sentences:\n* The _most_ important thing in life is...\n* The _least",
+            "seed": 12050749903881546000
+          }
+        ],
+        "created": 1758820465,
+        "model": "meta-llama/Llama-3.3-70B-Instruct-Turbo-Free",
+        "object": "text.completion",
+        "system_fingerprint": null,
+        "usage": {
+          "completion_tokens": 20,
+          "prompt_tokens": 3,
+          "total_tokens": 23,
+          "completion_tokens_details": null,
+          "prompt_tokens_details": null,
+          "cached_tokens": 0
+        },
+        "prompt": []
+      }
+    },
+    "is_streaming": false
+  }
+}