refactor: address review feedback

- Use pydantic Field(ge=0, le=300) instead of custom validators
- Extract shared wait logic to execution_utils.py
- Use asyncio.wait_for for proper timeout handling
- Remove duplicated code in agent_output.py and run_agent.py

Note: Direct DB access will need adjustment for #12057 compatibility

autogpt_platform/backend/backend/api/features/chat/tools/agent_output.py

@@ -5,7 +5,7 @@ import re
 from datetime import datetime, timedelta, timezone
 from typing import Any
 
-from pydantic import BaseModel, field_validator
+from pydantic import BaseModel, Field, field_validator
 
 from backend.api.features.chat.model import ChatSession
 from backend.api.features.library import db as library_db
@@ -14,6 +14,7 @@ from backend.data import execution as execution_db
 from backend.data.execution import ExecutionStatus, GraphExecution, GraphExecutionMeta
 
 from .base import BaseTool
+from .execution_utils import TERMINAL_STATUSES, wait_for_execution
 from .models import (
     AgentOutputResponse,
     ErrorResponse,
@@ -34,6 +35,7 @@ class AgentOutputInput(BaseModel):
     store_slug: str = ""
     execution_id: str = ""
     run_time: str = "latest"
+    wait_if_running: int = Field(default=0, ge=0, le=300)
 
     @field_validator(
         "agent_name",
@@ -117,6 +119,11 @@ class AgentOutputTool(BaseTool):
         Select which run to retrieve using:
         - execution_id: Specific execution ID
         - run_time: 'latest' (default), 'yesterday', 'last week', or ISO date 'YYYY-MM-DD'
+
+        Wait for completion (optional):
+        - wait_if_running: Max seconds to wait if execution is still running (0-300).
+          If the execution is running/queued, waits up to this many seconds for it to complete.
+          Returns current status on timeout. If already finished, returns immediately.
         """
 
     @property
@@ -146,6 +153,13 @@ class AgentOutputTool(BaseTool):
                         "Time filter: 'latest', 'yesterday', 'last week', or 'YYYY-MM-DD'"
                     ),
                 },
+                "wait_if_running": {
+                    "type": "integer",
+                    "description": (
+                        "Max seconds to wait if execution is still running (0-300). "
+                        "If running, waits for completion. Returns current state on timeout."
+                    ),
+                },
             },
             "required": [],
         }
@@ -223,10 +237,14 @@ class AgentOutputTool(BaseTool):
         execution_id: str | None,
         time_start: datetime | None,
         time_end: datetime | None,
+        include_running: bool = False,
     ) -> tuple[GraphExecution | None, list[GraphExecutionMeta], str | None]:
         """
         Fetch execution(s) based on filters.
         Returns (single_execution, available_executions_meta, error_message).
+
+        Args:
+            include_running: If True, also look for running/queued executions (for waiting)
         """
         # If specific execution_id provided, fetch it directly
         if execution_id:
@@ -239,11 +257,22 @@ class AgentOutputTool(BaseTool):
                 return None, [], f"Execution '{execution_id}' not found"
             return execution, [], None
 
-        # Get completed executions with time filters
+        # Determine which statuses to query
+        statuses = [ExecutionStatus.COMPLETED]
+        if include_running:
+            statuses.extend(
+                [
+                    ExecutionStatus.RUNNING,
+                    ExecutionStatus.QUEUED,
+                    ExecutionStatus.INCOMPLETE,
+                ]
+            )
+
+        # Get executions with time filters
         executions = await execution_db.get_graph_executions(
             graph_id=graph_id,
             user_id=user_id,
-            statuses=[ExecutionStatus.COMPLETED],
+            statuses=statuses,
             created_time_gte=time_start,
             created_time_lte=time_end,
             limit=10,
@@ -310,10 +339,28 @@ class AgentOutputTool(BaseTool):
                 for e in available_executions[:5]
             ]
 
-        message = f"Found execution outputs for agent '{agent.name}'"
+        # Build appropriate message based on execution status
+        if execution.status == ExecutionStatus.COMPLETED:
+            message = f"Found execution outputs for agent '{agent.name}'"
+        elif execution.status == ExecutionStatus.FAILED:
+            message = f"Execution for agent '{agent.name}' failed"
+        elif execution.status == ExecutionStatus.TERMINATED:
+            message = f"Execution for agent '{agent.name}' was terminated"
+        elif execution.status in (
+            ExecutionStatus.RUNNING,
+            ExecutionStatus.QUEUED,
+            ExecutionStatus.INCOMPLETE,
+        ):
+            message = (
+                f"Execution for agent '{agent.name}' is still {execution.status.value}. "
+                "Results may be incomplete. Use wait_if_running to wait for completion."
+            )
+        else:
+            message = f"Found execution for agent '{agent.name}' (status: {execution.status.value})"
+
         if len(available_executions) > 1:
             message += (
-                f". Showing latest of {len(available_executions)} matching executions."
+                f" Showing latest of {len(available_executions)} matching executions."
             )
 
         return AgentOutputResponse(
@@ -428,13 +475,17 @@ class AgentOutputTool(BaseTool):
         # Parse time expression
         time_start, time_end = parse_time_expression(input_data.run_time)
 
-        # Fetch execution(s)
+        # Check if we should wait for running executions
+        wait_timeout = input_data.wait_if_running
+
+        # Fetch execution(s) - include running if we're going to wait
         execution, available_executions, exec_error = await self._get_execution(
             user_id=user_id,
             graph_id=agent.graph_id,
             execution_id=input_data.execution_id or None,
             time_start=time_start,
             time_end=time_end,
+            include_running=wait_timeout > 0,
         )
 
         if exec_error:
@@ -443,4 +494,17 @@ class AgentOutputTool(BaseTool):
                 session_id=session_id,
             )
 
+        # If we have an execution that's still running and we should wait
+        if execution and wait_timeout > 0 and execution.status not in TERMINAL_STATUSES:
+            logger.info(
+                f"Execution {execution.id} is {execution.status}, "
+                f"waiting up to {wait_timeout}s for completion"
+            )
+            execution = await wait_for_execution(
+                user_id=user_id,
+                graph_id=agent.graph_id,
+                execution_id=execution.id,
+                timeout_seconds=wait_timeout,
+            )
+
         return self._build_response(agent, execution, available_executions, session_id)

autogpt_platform/backend/backend/api/features/chat/tools/execution_utils.py

@@ -0,0 +1,124 @@
+"""Shared utilities for execution waiting and status handling."""
+
+import asyncio
+import logging
+from typing import Any
+
+from backend.data import execution as execution_db
+from backend.data.execution import (
+    AsyncRedisExecutionEventBus,
+    ExecutionStatus,
+    GraphExecution,
+    GraphExecutionEvent,
+)
+
+logger = logging.getLogger(__name__)
+
+# Terminal statuses that indicate execution is complete
+TERMINAL_STATUSES = frozenset(
+    {
+        ExecutionStatus.COMPLETED,
+        ExecutionStatus.FAILED,
+        ExecutionStatus.TERMINATED,
+    }
+)
+
+
+async def wait_for_execution(
+    user_id: str,
+    graph_id: str,
+    execution_id: str,
+    timeout_seconds: int,
+) -> GraphExecution | None:
+    """
+    Wait for an execution to reach a terminal status using Redis pubsub.
+
+    Uses asyncio.wait_for to ensure timeout is respected even when no events
+    are received.
+
+    Args:
+        user_id: User ID
+        graph_id: Graph ID
+        execution_id: Execution ID to wait for
+        timeout_seconds: Max seconds to wait
+
+    Returns:
+        The execution with current status, or None if not found
+    """
+    # First check current status - maybe it's already done
+    execution = await execution_db.get_graph_execution(
+        user_id=user_id,
+        execution_id=execution_id,
+        include_node_executions=False,
+    )
+    if not execution:
+        return None
+
+    # If already in terminal state, return immediately
+    if execution.status in TERMINAL_STATUSES:
+        logger.debug(
+            f"Execution {execution_id} already in terminal state: {execution.status}"
+        )
+        return execution
+
+    logger.info(
+        f"Waiting up to {timeout_seconds}s for execution {execution_id} "
+        f"(current status: {execution.status})"
+    )
+
+    # Subscribe to execution updates via Redis pubsub
+    event_bus = AsyncRedisExecutionEventBus()
+    channel_key = f"{user_id}/{graph_id}/{execution_id}"
+
+    try:
+        # Use wait_for to enforce timeout on the entire listen operation
+        result = await asyncio.wait_for(
+            _listen_for_terminal_status(event_bus, channel_key, user_id, execution_id),
+            timeout=timeout_seconds,
+        )
+        return result
+    except asyncio.TimeoutError:
+        logger.info(f"Timeout waiting for execution {execution_id}")
+    except Exception as e:
+        logger.error(f"Error waiting for execution: {e}", exc_info=True)
+
+    # Return current state on timeout/error
+    return await execution_db.get_graph_execution(
+        user_id=user_id,
+        execution_id=execution_id,
+        include_node_executions=False,
+    )
+
+
+async def _listen_for_terminal_status(
+    event_bus: AsyncRedisExecutionEventBus,
+    channel_key: str,
+    user_id: str,
+    execution_id: str,
+) -> GraphExecution | None:
+    """
+    Listen for execution events until a terminal status is reached.
+
+    This is a helper that gets wrapped in asyncio.wait_for for timeout handling.
+    """
+    async for event in event_bus.listen_events(channel_key):
+        # Only process GraphExecutionEvents (not NodeExecutionEvents)
+        if isinstance(event, GraphExecutionEvent):
+            logger.debug(f"Received execution update: {event.status}")
+            if event.status in TERMINAL_STATUSES:
+                # Fetch full execution with outputs
+                return await execution_db.get_graph_execution(
+                    user_id=user_id,
+                    execution_id=execution_id,
+                    include_node_executions=False,
+                )
+
+    # Should not reach here normally (generator should yield indefinitely)
+    return None
+
+
+def get_execution_outputs(execution: GraphExecution | None) -> dict[str, Any] | None:
+    """Extract outputs from an execution, or return None."""
+    if execution is None:
+        return None
+    return execution.outputs

autogpt_platform/backend/backend/api/features/chat/tools/models.py

@@ -192,6 +192,7 @@ class ExecutionStartedResponse(ToolResponseBase):
     library_agent_id: str | None = None
     library_agent_link: str | None = None
     status: str = "QUEUED"
+    outputs: dict[str, Any] | None = None  # Populated when wait_for_result is used
 
 
 # Auth/error models

autogpt_platform/backend/backend/api/features/chat/tools/run_agent.py

@@ -12,6 +12,7 @@ from backend.api.features.chat.tracking import (
     track_agent_scheduled,
 )
 from backend.api.features.library import db as library_db
+from backend.data.execution import ExecutionStatus
 from backend.data.graph import GraphModel
 from backend.data.model import CredentialsMetaInput
 from backend.data.user import get_user_by_id
@@ -24,6 +25,7 @@ from backend.util.timezone_utils import (
 )
 
 from .base import BaseTool
+from .execution_utils import get_execution_outputs, wait_for_execution
 from .helpers import get_inputs_from_schema
 from .models import (
     AgentDetails,
@@ -70,6 +72,7 @@ class RunAgentInput(BaseModel):
     schedule_name: str = ""
     cron: str = ""
     timezone: str = "UTC"
+    wait_for_result: int = Field(default=0, ge=0, le=300)
 
     @field_validator(
         "username_agent_slug",
@@ -151,6 +154,14 @@ class RunAgentTool(BaseTool):
                     "type": "string",
                     "description": "IANA timezone for schedule (default: UTC)",
                 },
+                "wait_for_result": {
+                    "type": "integer",
+                    "description": (
+                        "Max seconds to wait for execution to complete (0-300). "
+                        "If >0, blocks until the execution finishes or times out. "
+                        "Returns execution outputs when complete."
+                    ),
+                },
             },
             "required": [],
         }
@@ -347,6 +358,7 @@ class RunAgentTool(BaseTool):
                     graph=graph,
                     graph_credentials=graph_credentials,
                     inputs=params.inputs,
+                    wait_for_result=params.wait_for_result,
                 )
 
         except NotFoundError as e:
@@ -430,8 +442,9 @@ class RunAgentTool(BaseTool):
         graph: GraphModel,
         graph_credentials: dict[str, CredentialsMetaInput],
         inputs: dict[str, Any],
+        wait_for_result: int = 0,
     ) -> ToolResponseBase:
-        """Execute an agent immediately."""
+        """Execute an agent immediately, optionally waiting for completion."""
         session_id = session.session_id
 
         # Check rate limits
@@ -468,6 +481,60 @@ class RunAgentTool(BaseTool):
         )
 
         library_agent_link = f"/library/agents/{library_agent.id}"
+
+        # If wait_for_result is specified, wait for execution to complete
+        if wait_for_result > 0:
+            logger.info(
+                f"Waiting up to {wait_for_result}s for execution {execution.id}"
+            )
+            result = await wait_for_execution(
+                user_id=user_id,
+                graph_id=library_agent.graph_id,
+                execution_id=execution.id,
+                timeout_seconds=wait_for_result,
+            )
+            final_status = result.status if result else ExecutionStatus.FAILED
+            outputs = get_execution_outputs(result)
+
+            # Build message based on final status
+            if final_status == ExecutionStatus.COMPLETED:
+                message = (
+                    f"Agent '{library_agent.name}' execution completed successfully. "
+                    f"{MSG_DO_NOT_RUN_AGAIN}"
+                )
+            elif final_status == ExecutionStatus.FAILED:
+                message = (
+                    f"Agent '{library_agent.name}' execution failed. "
+                    f"View details at {library_agent_link}. "
+                    f"{MSG_DO_NOT_RUN_AGAIN}"
+                )
+            elif final_status == ExecutionStatus.TERMINATED:
+                message = (
+                    f"Agent '{library_agent.name}' execution was terminated. "
+                    f"View details at {library_agent_link}. "
+                    f"{MSG_DO_NOT_RUN_AGAIN}"
+                )
+            else:
+                message = (
+                    f"Agent '{library_agent.name}' execution is still {final_status.value} "
+                    f"(timed out after {wait_for_result}s). "
+                    f"View at {library_agent_link}. "
+                    f"{MSG_DO_NOT_RUN_AGAIN}"
+                )
+
+            return ExecutionStartedResponse(
+                message=message,
+                session_id=session_id,
+                execution_id=execution.id,
+                graph_id=library_agent.graph_id,
+                graph_name=library_agent.name,
+                library_agent_id=library_agent.id,
+                library_agent_link=library_agent_link,
+                status=final_status.value,
+                outputs=outputs,
+            )
+
+        # Default: return immediately without waiting
         return ExecutionStartedResponse(
             message=(
                 f"Agent '{library_agent.name}' execution started successfully. "

autogpt_platform/backend/backend/blocks/llm.py

@@ -106,6 +106,8 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):
     GPT41_MINI = "gpt-4.1-mini-2025-04-14"
     GPT4O_MINI = "gpt-4o-mini"
     GPT4O = "gpt-4o"
+    GPT4_TURBO = "gpt-4-turbo"
+    GPT3_5_TURBO = "gpt-3.5-turbo"
     # Anthropic models
     CLAUDE_4_1_OPUS = "claude-opus-4-1-20250805"
     CLAUDE_4_OPUS = "claude-opus-4-20250514"
@@ -253,6 +255,12 @@ MODEL_METADATA = {
     LlmModel.GPT4O: ModelMetadata(
         "openai", 128000, 16384, "GPT-4o", "OpenAI", "OpenAI", 2
     ),  # gpt-4o-2024-08-06
+    LlmModel.GPT4_TURBO: ModelMetadata(
+        "openai", 128000, 4096, "GPT-4 Turbo", "OpenAI", "OpenAI", 3
+    ),  # gpt-4-turbo-2024-04-09
+    LlmModel.GPT3_5_TURBO: ModelMetadata(
+        "openai", 16385, 4096, "GPT-3.5 Turbo", "OpenAI", "OpenAI", 1
+    ),  # gpt-3.5-turbo-0125
     # https://docs.anthropic.com/en/docs/about-claude/models
     LlmModel.CLAUDE_4_1_OPUS: ModelMetadata(
         "anthropic", 200000, 32000, "Claude Opus 4.1", "Anthropic", "Anthropic", 3

autogpt_platform/backend/backend/data/block_cost_config.py

@@ -75,6 +75,8 @@ MODEL_COST: dict[LlmModel, int] = {
     LlmModel.GPT41_MINI: 1,
     LlmModel.GPT4O_MINI: 1,
     LlmModel.GPT4O: 3,
+    LlmModel.GPT4_TURBO: 10,
+    LlmModel.GPT3_5_TURBO: 1,
     LlmModel.CLAUDE_4_1_OPUS: 21,
     LlmModel.CLAUDE_4_OPUS: 21,
     LlmModel.CLAUDE_4_SONNET: 5,

autogpt_platform/backend/backend/data/credit_test.py

@@ -79,7 +79,7 @@ async def test_block_credit_usage(server: SpinTestServer):
             node_exec_id="test_node_exec",
             block_id=AITextGeneratorBlock().id,
             inputs={
-                "model": "gpt-4o",
+                "model": "gpt-4-turbo",
                 "credentials": {
                     "id": openai_credentials.id,
                     "provider": openai_credentials.provider,
@@ -100,7 +100,7 @@ async def test_block_credit_usage(server: SpinTestServer):
             graph_exec_id="test_graph_exec",
             node_exec_id="test_node_exec",
             block_id=AITextGeneratorBlock().id,
-            inputs={"model": "gpt-4o", "api_key": "owned_api_key"},
+            inputs={"model": "gpt-4-turbo", "api_key": "owned_api_key"},
             execution_context=ExecutionContext(user_timezone="UTC"),
         ),
     )

autogpt_platform/backend/migrations/20260216120000_migrate_deprecated_gpt4_gpt35_models/migration.sql

@@ -1,42 +0,0 @@
--- Migrate deprecated OpenAI GPT-4-turbo and GPT-3.5-turbo models
--- This updates all AgentNode blocks that use deprecated models
--- OpenAI is retiring these models:
---   - gpt-4-turbo: March 26, 2026 -> migrate to gpt-4o
---   - gpt-3.5-turbo: September 28, 2026 -> migrate to gpt-4o-mini
-
--- Update gpt-4-turbo to gpt-4o (staying in same capability tier)
-UPDATE "AgentNode"
-SET    "constantInput" = JSONB_SET(
-         "constantInput"::jsonb,
-         '{model}',
-         '"gpt-4o"'::jsonb
-       )
-WHERE  "constantInput"::jsonb->>'model' = 'gpt-4-turbo';
-
--- Update gpt-3.5-turbo to gpt-4o-mini (appropriate replacement for lightweight model)
-UPDATE "AgentNode"
-SET    "constantInput" = JSONB_SET(
-         "constantInput"::jsonb,
-         '{model}',
-         '"gpt-4o-mini"'::jsonb
-       )
-WHERE  "constantInput"::jsonb->>'model' = 'gpt-3.5-turbo';
-
--- Update AgentPreset input overrides (stored in AgentNodeExecutionInputOutput)
-UPDATE "AgentNodeExecutionInputOutput"
-SET    "data" = JSONB_SET(
-         "data"::jsonb,
-         '{model}',
-         '"gpt-4o"'::jsonb
-       )
-WHERE  "agentPresetId" IS NOT NULL
-  AND  "data"::jsonb->>'model' = 'gpt-4-turbo';
-
-UPDATE "AgentNodeExecutionInputOutput"
-SET    "data" = JSONB_SET(
-         "data"::jsonb,
-         '{model}',
-         '"gpt-4o-mini"'::jsonb
-       )
-WHERE  "agentPresetId" IS NOT NULL
-  AND  "data"::jsonb->>'model' = 'gpt-3.5-turbo';

docs/integrations/block-integrations/llm.md

@@ -65,7 +65,7 @@ The result routes data to yes_output or no_output, enabling intelligent branchin
 | condition | A plaintext English description of the condition to evaluate | str | Yes |
 | yes_value | (Optional) Value to output if the condition is true. If not provided, input_value will be used. | Yes Value | No |
 | no_value | (Optional) Value to output if the condition is false. If not provided, input_value will be used. | No Value | No |
-| model | The language model to use for evaluating the condition. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
+| model | The language model to use for evaluating the condition. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
 
 ### Outputs
 
@@ -103,7 +103,7 @@ The block sends the entire conversation history to the chosen LLM, including sys
 |-------|-------------|------|----------|
 | prompt | The prompt to send to the language model. | str | No |
 | messages | List of messages in the conversation. | List[Any] | Yes |
-| model | The language model to use for the conversation. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
+| model | The language model to use for the conversation. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
 | max_tokens | The maximum number of tokens to generate in the chat completion. | int | No |
 | ollama_host | Ollama host for local  models | str | No |
 
@@ -257,7 +257,7 @@ The block formulates a prompt based on the given focus or source data, sends it
 |-------|-------------|------|----------|
 | focus | The focus of the list to generate. | str | No |
 | source_data | The data to generate the list from. | str | No |
-| model | The language model to use for generating the list. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
+| model | The language model to use for generating the list. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
 | max_retries | Maximum number of retries for generating a valid list. | int | No |
 | force_json_output | Whether to force the LLM to produce a JSON-only response. This can increase the block's reliability, but may also reduce the quality of the response because it prohibits the LLM from reasoning before providing its JSON response. | bool | No |
 | max_tokens | The maximum number of tokens to generate in the chat completion. | int | No |
@@ -424,7 +424,7 @@ The block sends the input prompt to a chosen LLM, along with any system prompts
 | prompt | The prompt to send to the language model. | str | Yes |
 | expected_format | Expected format of the response. If provided, the response will be validated against this format. The keys should be the expected fields in the response, and the values should be the description of the field. | Dict[str, str] | Yes |
 | list_result | Whether the response should be a list of objects in the expected format. | bool | No |
-| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
+| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
 | force_json_output | Whether to force the LLM to produce a JSON-only response. This can increase the block's reliability, but may also reduce the quality of the response because it prohibits the LLM from reasoning before providing its JSON response. | bool | No |
 | sys_prompt | The system prompt to provide additional context to the model. | str | No |
 | conversation_history | The conversation history to provide context for the prompt. | List[Dict[str, Any]] | No |
@@ -464,7 +464,7 @@ The block sends the input prompt to a chosen LLM, processes the response, and re
 | Input | Description | Type | Required |
 |-------|-------------|------|----------|
 | prompt | The prompt to send to the language model. You can use any of the {keys} from Prompt Values to fill in the prompt with values from the prompt values dictionary by putting them in curly braces. | str | Yes |
-| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
+| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
 | sys_prompt | The system prompt to provide additional context to the model. | str | No |
 | retry | Number of times to retry the LLM call if the response does not match the expected format. | int | No |
 | prompt_values | Values used to fill in the prompt. The values can be used in the prompt by putting them in a double curly braces, e.g. {{variable_name}}. | Dict[str, str] | No |
@@ -501,7 +501,7 @@ The block splits the input text into smaller chunks, sends each chunk to an LLM
 | Input | Description | Type | Required |
 |-------|-------------|------|----------|
 | text | The text to summarize. | str | Yes |
-| model | The language model to use for summarizing the text. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
+| model | The language model to use for summarizing the text. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
 | focus | The topic to focus on in the summary | str | No |
 | style | The style of the summary to generate. | "concise" \| "detailed" \| "bullet points" \| "numbered list" | No |
 | max_tokens | The maximum number of tokens to generate in the chat completion. | int | No |
@@ -763,7 +763,7 @@ Configure agent_mode_max_iterations to control loop behavior: 0 for single decis
 | Input | Description | Type | Required |
 |-------|-------------|------|----------|
 | prompt | The prompt to send to the language model. | str | Yes |
-| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
+| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "gpt-3.5-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-3-pro-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/wizardlm-2-8x22b" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |
 | multiple_tool_calls | Whether to allow multiple tool calls in a single response. | bool | No |
 | sys_prompt | The system prompt to provide additional context to the model. | str | No |
 | conversation_history | The conversation history to provide context for the prompt. | List[Dict[str, Any]] | No |