diff --git a/litellm-rust/loadtest/README.md b/litellm-rust/loadtest/README.md
index d9b0255a778..5b6b09d9d21 100644
--- a/litellm-rust/loadtest/README.md
+++ b/litellm-rust/loadtest/README.md
@@ -16,7 +16,7 @@ machines.
 | `s3stub` | In-memory path-style S3 (PUT, GET, ListObjectsV2) for the `s3_v2` logs of a full-feature run. Objects are stored compressed and listed from a sorted index, so millions of logs fit. |
 
 Workloads live in `workloads/`: `smoke`, `realistic-ramp`, `long-streams`, `large-context`,
-`key-churn` and `soak`. `sustained-100`, `sustained-250`, `sustained-500` and `sustained-1000` hold one rate for
+`key-churn` and `soak`. `sustained-10`, `-25`, `-50`, `-75`, `-100`, `-250`, `-500` and `-1000` hold one rate for
 15 minutes with evenly spaced arrivals and smoke's request mix over every model group;
 `sustained-check` runs the same mix at 100, 500 and 1,000 rps for 2 minutes each, to check that the
 client, mock and stack hold 1,000 rps before the long runs.
diff --git a/litellm-rust/loadtest/workloads/sustained-10.json b/litellm-rust/loadtest/workloads/sustained-10.json
new file mode 100644
index 00000000000..b8612a9d554
--- /dev/null
+++ b/litellm-rust/loadtest/workloads/sustained-10.json
@@ -0,0 +1,71 @@
+{
+  "name": "sustained 10 rps for 15 minutes, evenly spaced arrivals, smoke's request mix over every model group",
+  "stages": [
+    {
+      "duration_s": 900,
+      "rps": 10
+    }
+  ],
+  "arrivals": "constant",
+  "nonstream_max_s": 360,
+  "warmup_s": 60,
+  "max_in_flight": 30000,
+  "keys": {
+    "file": "out/keys.txt",
+    "zipf_s": 0
+  },
+  "models": {
+    "chat": {
+      "prefix": "gpt-6-astra-",
+      "count": 10
+    },
+    "messages": {
+      "prefix": "claude-opus-5-5-",
+      "count": 10
+    }
+  },
+  "classes": [
+    {
+      "name": "chat",
+      "weight": 1,
+      "endpoint": "chat",
+      "stream_fraction": 0.5,
+      "context_tokens": {
+        "dist": "loguniform",
+        "min": 10000,
+        "max": 50000
+      },
+      "ttft_ms": {
+        "dist": "uniform",
+        "min": 200,
+        "max": 800
+      },
+      "duration_s": {
+        "dist": "uniform",
+        "min": 1,
+        "max": 5
+      }
+    },
+    {
+      "name": "messages",
+      "weight": 1,
+      "endpoint": "messages",
+      "stream_fraction": 0.5,
+      "context_tokens": {
+        "dist": "loguniform",
+        "min": 10000,
+        "max": 50000
+      },
+      "ttft_ms": {
+        "dist": "uniform",
+        "min": 200,
+        "max": 800
+      },
+      "duration_s": {
+        "dist": "uniform",
+        "min": 1,
+        "max": 5
+      }
+    }
+  ]
+}
diff --git a/litellm-rust/loadtest/workloads/sustained-25.json b/litellm-rust/loadtest/workloads/sustained-25.json
new file mode 100644
index 00000000000..9f29f543bd5
--- /dev/null
+++ b/litellm-rust/loadtest/workloads/sustained-25.json
@@ -0,0 +1,71 @@
+{
+  "name": "sustained 25 rps for 15 minutes, evenly spaced arrivals, smoke's request mix over every model group",
+  "stages": [
+    {
+      "duration_s": 900,
+      "rps": 25
+    }
+  ],
+  "arrivals": "constant",
+  "nonstream_max_s": 360,
+  "warmup_s": 60,
+  "max_in_flight": 30000,
+  "keys": {
+    "file": "out/keys.txt",
+    "zipf_s": 0
+  },
+  "models": {
+    "chat": {
+      "prefix": "gpt-6-astra-",
+      "count": 10
+    },
+    "messages": {
+      "prefix": "claude-opus-5-5-",
+      "count": 10
+    }
+  },
+  "classes": [
+    {
+      "name": "chat",
+      "weight": 1,
+      "endpoint": "chat",
+      "stream_fraction": 0.5,
+      "context_tokens": {
+        "dist": "loguniform",
+        "min": 10000,
+        "max": 50000
+      },
+      "ttft_ms": {
+        "dist": "uniform",
+        "min": 200,
+        "max": 800
+      },
+      "duration_s": {
+        "dist": "uniform",
+        "min": 1,
+        "max": 5
+      }
+    },
+    {
+      "name": "messages",
+      "weight": 1,
+      "endpoint": "messages",
+      "stream_fraction": 0.5,
+      "context_tokens": {
+        "dist": "loguniform",
+        "min": 10000,
+        "max": 50000
+      },
+      "ttft_ms": {
+        "dist": "uniform",
+        "min": 200,
+        "max": 800
+      },
+      "duration_s": {
+        "dist": "uniform",
+        "min": 1,
+        "max": 5
+      }
+    }
+  ]
+}
diff --git a/litellm-rust/loadtest/workloads/sustained-50.json b/litellm-rust/loadtest/workloads/sustained-50.json
new file mode 100644
index 00000000000..de1bd9e1091
--- /dev/null
+++ b/litellm-rust/loadtest/workloads/sustained-50.json
@@ -0,0 +1,71 @@
+{
+  "name": "sustained 50 rps for 15 minutes, evenly spaced arrivals, smoke's request mix over every model group",
+  "stages": [
+    {
+      "duration_s": 900,
+      "rps": 50
+    }
+  ],
+  "arrivals": "constant",
+  "nonstream_max_s": 360,
+  "warmup_s": 60,
+  "max_in_flight": 30000,
+  "keys": {
+    "file": "out/keys.txt",
+    "zipf_s": 0
+  },
+  "models": {
+    "chat": {
+      "prefix": "gpt-6-astra-",
+      "count": 10
+    },
+    "messages": {
+      "prefix": "claude-opus-5-5-",
+      "count": 10
+    }
+  },
+  "classes": [
+    {
+      "name": "chat",
+      "weight": 1,
+      "endpoint": "chat",
+      "stream_fraction": 0.5,
+      "context_tokens": {
+        "dist": "loguniform",
+        "min": 10000,
+        "max": 50000
+      },
+      "ttft_ms": {
+        "dist": "uniform",
+        "min": 200,
+        "max": 800
+      },
+      "duration_s": {
+        "dist": "uniform",
+        "min": 1,
+        "max": 5
+      }
+    },
+    {
+      "name": "messages",
+      "weight": 1,
+      "endpoint": "messages",
+      "stream_fraction": 0.5,
+      "context_tokens": {
+        "dist": "loguniform",
+        "min": 10000,
+        "max": 50000
+      },
+      "ttft_ms": {
+        "dist": "uniform",
+        "min": 200,
+        "max": 800
+      },
+      "duration_s": {
+        "dist": "uniform",
+        "min": 1,
+        "max": 5
+      }
+    }
+  ]
+}
diff --git a/litellm-rust/loadtest/workloads/sustained-75.json b/litellm-rust/loadtest/workloads/sustained-75.json
new file mode 100644
index 00000000000..907ba5e2477
--- /dev/null
+++ b/litellm-rust/loadtest/workloads/sustained-75.json
@@ -0,0 +1,71 @@
+{
+  "name": "sustained 75 rps for 15 minutes, evenly spaced arrivals, smoke's request mix over every model group",
+  "stages": [
+    {
+      "duration_s": 900,
+      "rps": 75
+    }
+  ],
+  "arrivals": "constant",
+  "nonstream_max_s": 360,
+  "warmup_s": 60,
+  "max_in_flight": 30000,
+  "keys": {
+    "file": "out/keys.txt",
+    "zipf_s": 0
+  },
+  "models": {
+    "chat": {
+      "prefix": "gpt-6-astra-",
+      "count": 10
+    },
+    "messages": {
+      "prefix": "claude-opus-5-5-",
+      "count": 10
+    }
+  },
+  "classes": [
+    {
+      "name": "chat",
+      "weight": 1,
+      "endpoint": "chat",
+      "stream_fraction": 0.5,
+      "context_tokens": {
+        "dist": "loguniform",
+        "min": 10000,
+        "max": 50000
+      },
+      "ttft_ms": {
+        "dist": "uniform",
+        "min": 200,
+        "max": 800
+      },
+      "duration_s": {
+        "dist": "uniform",
+        "min": 1,
+        "max": 5
+      }
+    },
+    {
+      "name": "messages",
+      "weight": 1,
+      "endpoint": "messages",
+      "stream_fraction": 0.5,
+      "context_tokens": {
+        "dist": "loguniform",
+        "min": 10000,
+        "max": 50000
+      },
+      "ttft_ms": {
+        "dist": "uniform",
+        "min": 200,
+        "max": 800
+      },
+      "duration_s": {
+        "dist": "uniform",
+        "min": 1,
+        "max": 5
+      }
+    }
+  ]
+}