feat: add gpt-5.5 to model cost map (#26345)

* feat: add gpt-5.5 to model cost map

Add gpt-5.5 entry with pricing from OpenAI flagship page:
input $5/1M, cached input $0.50/1M, output $30/1M, 272K context.

* test: add gpt-5.5 coverage for model cost map and gpt-5 routing

- Add gpt-5.5 to GPT5_MODELS parametrized list so both OpenAIGPT5Config
  and AzureOpenAIGPT5Config routing tests cover the new model.
- Add test_generic_cost_per_token_gpt55 verifying the new entry's
  cost-map values ($5/$0.50/$30 per 1M) and that generic_cost_per_token
  returns the expected prompt/completion costs.

litellm/model_prices_and_context_window_backup.json

@@ -19273,6 +19273,42 @@
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": true
     },
+    "gpt-5.5": {
+        "cache_read_input_token_cost": 5e-07,
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "openai",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 3e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": true
+    },
     "gpt-5.4": {
         "cache_read_input_token_cost": 2.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 5e-07,

model_prices_and_context_window.json

@@ -19287,6 +19287,42 @@
         "supports_xhigh_reasoning_effort": true,
         "supports_minimal_reasoning_effort": true
     },
+    "gpt-5.5": {
+        "cache_read_input_token_cost": 5e-07,
+        "input_cost_per_token": 5e-06,
+        "litellm_provider": "openai",
+        "max_input_tokens": 272000,
+        "max_output_tokens": 128000,
+        "max_tokens": 128000,
+        "mode": "chat",
+        "output_cost_per_token": 3e-05,
+        "supported_endpoints": [
+            "/v1/chat/completions",
+            "/v1/batch",
+            "/v1/responses"
+        ],
+        "supported_modalities": [
+            "text",
+            "image"
+        ],
+        "supported_output_modalities": [
+            "text"
+        ],
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_pdf_input": true,
+        "supports_prompt_caching": true,
+        "supports_reasoning": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true,
+        "supports_service_tier": true,
+        "supports_vision": true,
+        "supports_none_reasoning_effort": true,
+        "supports_xhigh_reasoning_effort": true,
+        "supports_minimal_reasoning_effort": true
+    },
     "gpt-5.4": {
         "cache_read_input_token_cost": 2.5e-07,
         "cache_read_input_token_cost_above_272k_tokens": 5e-07,

tests/test_litellm/litellm_core_utils/llm_cost_calc/test_llm_cost_calc_utils.py

@@ -328,6 +328,43 @@ def test_generic_cost_per_token_gpt54_above_272k_tokens():
     assert round(completion_cost, 10) == round(expected_completion, 10)
 
 
+def test_generic_cost_per_token_gpt55():
+    """gpt-5.5: base pricing — $5/1M input, $30/1M output, $0.50/1M cached input."""
+    model = "gpt-5.5"
+    custom_llm_provider = "openai"
+    os.environ["LITELLM_LOCAL_MODEL_COST_MAP"] = "True"
+    litellm.model_cost = litellm.get_model_cost_map(url="")
+
+    model_cost_map = litellm.model_cost[model]
+
+    # Sanity-check the map values match OpenAI's published pricing.
+    assert model_cost_map["input_cost_per_token"] == 5e-6
+    assert model_cost_map["output_cost_per_token"] == 3e-5
+    assert model_cost_map["cache_read_input_token_cost"] == 5e-7
+    assert model_cost_map["litellm_provider"] == "openai"
+    assert model_cost_map["mode"] == "chat"
+    assert model_cost_map["max_input_tokens"] == 272000
+
+    prompt_tokens = 1000
+    completion_tokens = 500
+    usage = Usage(
+        prompt_tokens=prompt_tokens,
+        completion_tokens=completion_tokens,
+        total_tokens=prompt_tokens + completion_tokens,
+    )
+    prompt_cost, completion_cost = generic_cost_per_token(
+        model=model,
+        usage=usage,
+        custom_llm_provider=custom_llm_provider,
+    )
+    assert round(prompt_cost, 10) == round(
+        model_cost_map["input_cost_per_token"] * prompt_tokens, 10
+    )
+    assert round(completion_cost, 10) == round(
+        model_cost_map["output_cost_per_token"] * completion_tokens, 10
+    )
+
+
 def test_generic_cost_per_token_anthropic_prompt_caching():
     model = "claude-sonnet-4@20250514"
     usage = Usage(

tests/test_litellm/llms/openai/test_is_model_gpt_5_model.py

@@ -46,6 +46,7 @@ GPT5_MODELS = [
     "gpt-5.2",
     "gpt-5.3",
     "gpt-5.4",
+    "gpt-5.5",
     "gpt-5.1-chat",  # versioned chat — THE KEY REGRESSION CASE
     "gpt-5.2-chat",  # versioned chat — also a regression case
     "gpt-5.3-chat",  # versioned chat — THE KEY REGRESSION CASE