Skip to content

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

fix(backend): unblock dry-run Orchestrator + Haiku 4.5 sim default (#13171)

Zamil Majdy09368cd558ab
diff --git a/autogpt_platform/backend/backend/blocks/llm.py b/autogpt_platform/backend/backend/blocks/llm.py
index b2687523ca..14a3263dc2 100644
--- a/autogpt_platform/backend/backend/blocks/llm.py
+++ b/autogpt_platform/backend/backend/blocks/llm.py
@@ -169,6 +169,7 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):
GEMINI_2_5_FLASH = "google/gemini-2.5-flash"
GEMINI_2_0_FLASH = "google/gemini-2.0-flash-001"
GEMINI_3_1_FLASH_LITE_PREVIEW = "google/gemini-3.1-flash-lite-preview"
+ GEMINI_2_5_FLASH_LITE = "google/gemini-2.5-flash-lite"
GEMINI_2_0_FLASH_LITE = "google/gemini-2.0-flash-lite-001"
MISTRAL_LARGE_3 = "mistralai/mistral-large-2512"
MISTRAL_MEDIUM_3_1 = "mistralai/mistral-medium-3.1"
@@ -386,6 +387,15 @@ MODEL_METADATA = {
"Google",
1,
),
+ LlmModel.GEMINI_2_5_FLASH_LITE: ModelMetadata(
+ "open_router",
+ 1048576,
+ 65535,
+ "Gemini 2.5 Flash Lite",
+ "OpenRouter",
+ "Google",
+ 1,
+ ),
LlmModel.GEMINI_2_0_FLASH_LITE: ModelMetadata(
"open_router",
1048576,
diff --git a/autogpt_platform/backend/backend/copilot/config.py b/autogpt_platform/backend/backend/copilot/config.py
index b4141a11ca..6b967e2a11 100644
--- a/autogpt_platform/backend/backend/copilot/config.py
+++ b/autogpt_platform/backend/backend/copilot/config.py
@@ -7,6 +7,7 @@ from urllib.parse import urlparse
from pydantic import AliasChoices, Field, field_validator, model_validator
from pydantic_settings import BaseSettings
+from backend.blocks.llm import LlmModel
from backend.util.clients import OPENROUTER_BASE_URL
@@ -110,10 +111,14 @@ class ChatConfig(BaseSettings):
"via env without code changes.",
)
simulation_model: str = Field(
- default="google/gemini-2.5-flash-lite",
- description="Model for dry-run block simulation (should be fast/cheap with good JSON output). "
- "Gemini 2.5 Flash-Lite is ~3x cheaper than Flash ($0.10/$0.40 vs $0.30/$1.20 per MTok) "
- "with JSON-mode reliability adequate for shape-matching block outputs.",
+ default=LlmModel.CLAUDE_4_5_HAIKU.value,
+ description="Model for dry-run block simulation. Must be a real LlmModel "
+ "slug — OrchestratorBlock's input validates this against the enum, and a "
+ "bad value here breaks every dry-run of an agent that contains an "
+ "Orchestrator. Default is Claude Haiku 4.5 because the Orchestrator "
+ "dry-run picks tools and produces a finish message, so a substitute "
+ "with stronger reasoning gives a more faithful preview than Flash-Lite "
+ "while staying cheap.",
)
api_key: str | None = Field(default=None, description="OpenAI API key")
base_url: str | None = Field(
diff --git a/autogpt_platform/backend/backend/copilot/tools/test_dry_run.py b/autogpt_platform/backend/backend/copilot/tools/test_dry_run.py
index fc44a57c86..602229f381 100644
--- a/autogpt_platform/backend/backend/copilot/tools/test_dry_run.py
+++ b/autogpt_platform/backend/backend/copilot/tools/test_dry_run.py
@@ -5,6 +5,7 @@ from unittest.mock import AsyncMock, MagicMock, patch
import pytest
+from backend.blocks.llm import LlmModel
from backend.copilot.tools.helpers import execute_block
from backend.copilot.tools.models import BlockOutputResponse, ErrorResponse
from backend.copilot.tools.run_block import RunBlockTool
@@ -585,6 +586,9 @@ def test_prepare_dry_run_orchestrator_block():
assert result is not None
# Model is overridden to the simulation model (not the user's model).
assert result["model"] != "gpt-4o"
+ # Simulation model must parse as a real LlmModel so OrchestratorBlock's
+ # Pydantic input validation accepts it.
+ assert LlmModel(result["model"]) is not None
# Capped to min(original, 10); user's 10 passes through unchanged.
assert result["agent_mode_max_iterations"] == 10
assert result["_dry_run_api_key"] == "sk-or-test-key"
diff --git a/autogpt_platform/backend/backend/data/block_cost_config.py b/autogpt_platform/backend/backend/data/block_cost_config.py
index e1be1a0710..0c4fed6a16 100644
--- a/autogpt_platform/backend/backend/data/block_cost_config.py
+++ b/autogpt_platform/backend/backend/data/block_cost_config.py
@@ -143,6 +143,7 @@ MODEL_COST: dict[LlmModel, int] = {
LlmModel.GEMINI_2_5_FLASH: 1,
LlmModel.GEMINI_2_0_FLASH: 1,
LlmModel.GEMINI_3_1_FLASH_LITE_PREVIEW: 1,
+ LlmModel.GEMINI_2_5_FLASH_LITE: 1,
LlmModel.GEMINI_2_0_FLASH_LITE: 1,
LlmModel.MISTRAL_LARGE_3: 2,
LlmModel.MISTRAL_MEDIUM_3_1: 2,
@@ -262,6 +263,7 @@ TOKEN_COST: dict[LlmModel, TokenRate] = {
LlmModel.GEMINI_2_5_FLASH: TokenRate(input=45, output=375),
LlmModel.GEMINI_2_0_FLASH: TokenRate(input=15, output=60),
LlmModel.GEMINI_2_0_FLASH_LITE: TokenRate(input=11, output=45),
+ LlmModel.GEMINI_2_5_FLASH_LITE: TokenRate(input=15, output=60),
LlmModel.GEMINI_3_1_PRO_PREVIEW: TokenRate(input=300, output=1800),
LlmModel.GEMINI_3_FLASH_PREVIEW: TokenRate(input=75, output=450),
LlmModel.GEMINI_3_1_FLASH_LITE_PREVIEW: TokenRate(input=38, output=225),
diff --git a/autogpt_platform/backend/backend/executor/simulator.py b/autogpt_platform/backend/backend/executor/simulator.py
index 5d4770a46c..d61d4b44b4 100644
--- a/autogpt_platform/backend/backend/executor/simulator.py
+++ b/autogpt_platform/backend/backend/executor/simulator.py
@@ -39,6 +39,7 @@ from openai.types import CompletionUsage
from backend.blocks.agent import AgentExecutorBlock
from backend.blocks.io import AgentInputBlock, AgentOutputBlock
+from backend.blocks.llm import LlmModel
from backend.blocks.orchestrator import OrchestratorBlock
from backend.copilot.token_tracking import persist_and_record_usage
from backend.util.clients import get_openai_client
@@ -46,11 +47,14 @@ from backend.util.clients import get_openai_client
logger = logging.getLogger(__name__)
-# Default simulator model — Gemini 2.5 Flash-Lite via OpenRouter. Same provider
-# as Flash ($0.10 / $0.40 per MTok vs $0.30 / $1.20 — ~3× cheaper) with JSON-mode
-# reliability that's more than enough for dry-run shape-matching. Configurable
-# via ChatConfig.simulation_model (CHAT_SIMULATION_MODEL env var).
-_DEFAULT_SIMULATOR_MODEL = "google/gemini-2.5-flash-lite"
+# Default simulator model — Claude Haiku 4.5 via the platform's OpenRouter
+# credential. Dry-run isn't pure shape-matching for the Orchestrator block:
+# it picks tools and produces a finish message, so the substitute model's
+# reasoning quality affects how faithful the preview is. Haiku 4.5 keeps
+# the substitute small/cheap while giving materially better tool-use
+# decisions than Flash-Lite. Configurable via ChatConfig.simulation_model
+# (CHAT_SIMULATION_MODEL env var) — value must be a real LlmModel slug.
+_DEFAULT_SIMULATOR_MODEL = LlmModel.CLAUDE_4_5_HAIKU.value
# OpenRouter-specific extra_body flag that embeds the real generation cost on
# the response usage object. Same shape used by the baseline copilot service
diff --git a/autogpt_platform/backend/backend/executor/simulator_test.py b/autogpt_platform/backend/backend/executor/simulator_test.py
index d331f1ebc1..00cad55e8a 100644
--- a/autogpt_platform/backend/backend/executor/simulator_test.py
+++ b/autogpt_platform/backend/backend/executor/simulator_test.py
@@ -19,6 +19,7 @@ from openai.types.chat import ChatCompletion
from openai.types.chat.chat_completion import Choice
from openai.types.chat.chat_completion_message import ChatCompletionMessage
+from backend.blocks.llm import LlmModel
from backend.executor.simulator import (
_DEFAULT_SIMULATOR_MODEL,
_extract_cost_usd,
@@ -167,6 +168,9 @@ class TestPrepareDryRun:
assert result["agent_mode_max_iterations"] == 10
assert result["other"] == "val"
assert result["model"] != "gpt-4o" # overridden to simulation model
+ # Simulation model must parse as a real LlmModel so OrchestratorBlock's
+ # Pydantic input validation accepts it.
+ assert LlmModel(result["model"]) is not None
# credentials left as-is so block schema validation passes —
# actual creds injected via extra_exec_kwargs in manager.py
assert "credentials" not in result
@@ -567,10 +571,16 @@ def _sim_completion(*, content: str, usage: CompletionUsage) -> ChatCompletion:
class TestDefaultSimulatorModel:
"""Pin the default model — anyone flipping this without a cost review
- trips the test."""
+ trips the test, and anyone setting it to a non-enum value fails the
+ LlmModel parseability check (the bug class behind SECRT-2368)."""
- def test_default_is_flash_lite(self) -> None:
- assert _DEFAULT_SIMULATOR_MODEL == "google/gemini-2.5-flash-lite"
+ def test_default_is_haiku_4_5(self) -> None:
+ assert _DEFAULT_SIMULATOR_MODEL == "claude-haiku-4-5-20251001"
+
+ def test_default_parses_as_llm_model(self) -> None:
+ # OrchestratorBlock.Input.model is typed as LlmModel and rejects
+ # any default that isn't an enum member — keep this guard tight.
+ assert LlmModel(_DEFAULT_SIMULATOR_MODEL) is LlmModel.CLAUDE_4_5_HAIKU
class TestExtractCostUsd:
diff --git a/docs/integrations/block-integrations/llm.md b/docs/integrations/block-integrations/llm.md
index 0f5070bc7e..f407306bc9 100644
--- a/docs/integrations/block-integrations/llm.md
+++ b/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" \| "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-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-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" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-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/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "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" \| "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-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-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" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-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/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "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" \| "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-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-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" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-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/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "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" \| "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-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-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" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-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/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "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" \| "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-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-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" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-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/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "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" \| "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-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-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" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-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/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "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" \| "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-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-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" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-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/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "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" \| "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-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-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" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-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/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "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" \| "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-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-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" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-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/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "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" \| "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-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-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" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-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/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "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" \| "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-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-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" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-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/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "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" \| "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-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-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" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-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/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "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 |
@@ -721,7 +721,7 @@ _Add technical explanation here._
| 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" \| "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-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-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" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-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/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "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" \| "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-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-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" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-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/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "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 |