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.

feat(backend/llm): add Mistral Medium 3.5, Small 4 and Ministral 3, and retire Medium 3.1 and Small 3.2 (#15210)

Reinier van der Leerb9df0fe2993b
diff --git a/autogpt_platform/backend/backend/data/llm_registry/catalog.py b/autogpt_platform/backend/backend/data/llm_registry/catalog.py
index d83a3d04ec..a130d25859 100644
--- a/autogpt_platform/backend/backend/data/llm_registry/catalog.py
+++ b/autogpt_platform/backend/backend/data/llm_registry/catalog.py
@@ -848,6 +848,63 @@ def _build_catalog() -> CatalogPayload:
output_credits_per_1m=135.0,
),
),
+ CatalogModel(
+ slug="mistralai/ministral-14b-2512",
+ display_name="Ministral 3 14B 2512",
+ provider="open_router",
+ creator="mistral-ai",
+ context_window=262144,
+ max_output_tokens=209715,
+ price_tier=1,
+ supports_tools=True,
+ supports_json_output=True,
+ # Live OpenRouter rate as of 2026-10-06: $0.20/$0.20 per 1M,
+ # cache read $0.02/1M.
+ cost=CatalogModelCost(
+ run_credits=1,
+ input_credits_per_1m=30.0,
+ output_credits_per_1m=30.0,
+ cache_read_credits_per_1m=3.0,
+ ),
+ ),
+ CatalogModel(
+ slug="mistralai/ministral-8b-2512",
+ display_name="Ministral 3 8B 2512",
+ provider="open_router",
+ creator="mistral-ai",
+ context_window=262144,
+ max_output_tokens=209715,
+ price_tier=1,
+ supports_tools=True,
+ supports_json_output=True,
+ # Live OpenRouter rate as of 2026-10-06: $0.15/$0.15 per 1M,
+ # cache read $0.015/1M.
+ cost=CatalogModelCost(
+ run_credits=1,
+ input_credits_per_1m=22.5,
+ output_credits_per_1m=22.5,
+ cache_read_credits_per_1m=2.25,
+ ),
+ ),
+ CatalogModel(
+ slug="mistralai/ministral-3b-2512",
+ display_name="Ministral 3 3B 2512",
+ provider="open_router",
+ creator="mistral-ai",
+ context_window=131072,
+ max_output_tokens=104857,
+ price_tier=1,
+ supports_tools=True,
+ supports_json_output=True,
+ # Live OpenRouter rate as of 2026-10-06: $0.10/$0.10 per 1M,
+ # cache read $0.01/1M.
+ cost=CatalogModelCost(
+ run_credits=1,
+ input_credits_per_1m=15.0,
+ output_credits_per_1m=15.0,
+ cache_read_credits_per_1m=1.5,
+ ),
+ ),
CatalogModel(
slug="mistralai/mistral-large-2512",
display_name="Mistral Large 3 2512",
@@ -887,12 +944,34 @@ def _build_catalog() -> CatalogPayload:
creator="mistral-ai",
context_window=131072,
price_tier=2,
+ # Retired by Mistral 2026-08-31 in favour of Medium 3.5.
+ is_enabled=False,
+ fallback_model_slug="mistralai/mistral-medium-3-5",
cost=CatalogModelCost(
run_credits=2,
input_credits_per_1m=60.0,
output_credits_per_1m=300.0,
),
),
+ CatalogModel(
+ slug="mistralai/mistral-medium-3-5",
+ display_name="Mistral Medium 3.5",
+ provider="open_router",
+ creator="mistral-ai",
+ context_window=262144,
+ max_output_tokens=209715,
+ price_tier=2,
+ supports_tools=True,
+ supports_json_output=True,
+ supports_reasoning=True,
+ # Live OpenRouter rate as of 2026-10-06: $1.50/$7.50 per 1M,
+ # no cached rate published.
+ cost=CatalogModelCost(
+ run_credits=3,
+ input_credits_per_1m=225.0,
+ output_credits_per_1m=1125.0,
+ ),
+ ),
CatalogModel(
slug="mistralai/mistral-small-3.2-24b-instruct",
display_name="Mistral Small 3.2 24B",
@@ -901,12 +980,35 @@ def _build_catalog() -> CatalogPayload:
context_window=131072,
max_output_tokens=131072,
price_tier=1,
+ # Retired by Mistral 2026-07-31 in favour of Small 4.
+ is_enabled=False,
+ fallback_model_slug="mistralai/mistral-small-2603",
cost=CatalogModelCost(
run_credits=1,
input_credits_per_1m=14.0625,
output_credits_per_1m=37.5,
),
),
+ CatalogModel(
+ slug="mistralai/mistral-small-2603",
+ display_name="Mistral Small 4",
+ provider="open_router",
+ creator="mistral-ai",
+ context_window=262144,
+ max_output_tokens=209715,
+ price_tier=1,
+ supports_tools=True,
+ supports_json_output=True,
+ supports_reasoning=True,
+ # Live OpenRouter rate as of 2026-10-06: $0.15/$0.60 per 1M,
+ # cache read $0.015/1M.
+ cost=CatalogModelCost(
+ run_credits=1,
+ input_credits_per_1m=22.5,
+ output_credits_per_1m=90.0,
+ cache_read_credits_per_1m=2.25,
+ ),
+ ),
CatalogModel(
slug="moonshotai/kimi-k2-thinking",
display_name="Kimi K2 Thinking",
diff --git a/autogpt_platform/backend/backend/data/llm_registry/catalog_test.py b/autogpt_platform/backend/backend/data/llm_registry/catalog_test.py
index 7663f6dab9..eea164108a 100644
--- a/autogpt_platform/backend/backend/data/llm_registry/catalog_test.py
+++ b/autogpt_platform/backend/backend/data/llm_registry/catalog_test.py
@@ -10,8 +10,10 @@ from __future__ import annotations
import json
from pathlib import Path
-from backend.blocks.llm import MODEL_METADATA, LLMModel
-from backend.data.block_cost_config import MODEL_COST, TOKEN_COST
+import pytest
+
+from backend.blocks.llm import MODEL_METADATA, AITextGeneratorBlock, LLMModel
+from backend.data.block_cost_config import BLOCK_COSTS, MODEL_COST, TOKEN_COST
from backend.data.llm_registry.catalog import get_catalog
from backend.data.llm_registry.catalog_model import CATALOG_SCHEMA_VERSION
@@ -579,11 +581,41 @@ def test_gemma_4_31b_it_bills_at_authored_rates():
assert gemma_entry.context_window == 262144
+ "slug, usd_in, usd_out, context_window, max_output_tokens",
+ [
+ ("mistralai/mistral-medium-3-5", 1.50, 7.50, 262144, 209715),
+ ("mistralai/mistral-small-2603", 0.15, 0.60, 262144, 209715),
+ ("mistralai/ministral-14b-2512", 0.20, 0.20, 262144, 209715),
+ ("mistralai/ministral-8b-2512", 0.15, 0.15, 262144, 209715),
+ ("mistralai/ministral-3b-2512", 0.10, 0.10, 131072, 104857),
+ ],
+)
+def test_mistral_lineup_matches_openrouter_listing(
+ slug: str,
+ usd_in: float,
+ usd_out: float,
+ context_window: int,
+ max_output_tokens: int,
+):
+ """The builder's per-1M label shows OpenRouter's USD price (read
+ 2026-10-06), and blocks budget against OpenRouter's window and output cap."""
+ model = LLMModel(slug)
+ entry = next(
+ c
+ for c in BLOCK_COSTS[AITextGeneratorBlock]
+ if c.cost_filter.get("model") == model
+ )
+ assert entry.token_rate is not None
+ assert entry.token_rate.input_usd_per_1m == pytest.approx(usd_in)
+ assert entry.token_rate.output_usd_per_1m == pytest.approx(usd_out)
+ assert MODEL_METADATA[model].context_window == context_window
+ assert MODEL_METADATA[model].max_output_tokens == max_output_tokens
+
+
def test_provider_usd_prices_are_all_or_nothing():
"""A half-authored provider USD price must refuse to construct — it
would silently underprice against the transport family default."""
- import pytest
-
from backend.data.llm_registry.catalog_model import CatalogModelCost
with pytest.raises(ValueError, match="must be set together"):
diff --git a/autogpt_platform/backend/backend/data/llm_registry/llm_models.py b/autogpt_platform/backend/backend/data/llm_registry/llm_models.py
index 4fe5ec7ec3..d7869ed271 100644
--- a/autogpt_platform/backend/backend/data/llm_registry/llm_models.py
+++ b/autogpt_platform/backend/backend/data/llm_registry/llm_models.py
@@ -212,7 +212,12 @@ class LLMModel(str, Enum, metaclass=LLMModelMeta):
MISTRAL_LARGE_3 = "mistralai/mistral-large-2512"
MISTRAL_LARGE_4 = "mistralai/mistral-large-4-0"
MISTRAL_MEDIUM_3_1 = "mistralai/mistral-medium-3.1"
+ MISTRAL_MEDIUM_3_5 = "mistralai/mistral-medium-3-5"
MISTRAL_SMALL_3_2 = "mistralai/mistral-small-3.2-24b-instruct"
+ MISTRAL_SMALL_4 = "mistralai/mistral-small-2603"
+ MINISTRAL_3_14B = "mistralai/ministral-14b-2512"
+ MINISTRAL_3_8B = "mistralai/ministral-8b-2512"
+ MINISTRAL_3_3B = "mistralai/ministral-3b-2512"
CODESTRAL = "mistralai/codestral-2508"
COHERE_COMMAND_A_03_2025 = "cohere/command-a-03-2025"
COHERE_COMMAND_A_TRANSLATE_08_2025 = "cohere/command-a-translate-08-2025"
@@ -463,7 +468,8 @@ LEGACY_MODEL_MAPPINGS: dict[str, LLMModel] = {
"google/gemini-2.5-flash-lite-preview-06-17": LLMModel.GEMINI_2_5_FLASH,
"cohere/command-r-08-2024": LLMModel.COHERE_COMMAND_A_03_2025,
"cohere/command-r-plus-08-2024": LLMModel.COHERE_COMMAND_A_03_2025,
- "mistralai/mistral-nemo": LLMModel.MISTRAL_SMALL_3_2,
+ # nemo's prior target Small 3.2 is also retired; route to its successor.
+ "mistralai/mistral-nemo": LLMModel.MISTRAL_SMALL_4,
"microsoft/wizardlm-2-8x22b": LLMModel.MICROSOFT_PHI_4,
"moonshotai/kimi-k2": LLMModel.KIMI_K2_6,
"moonshotai/kimi-k2-0905": LLMModel.KIMI_K2_6,
diff --git a/autogpt_platform/backend/backend/data/llm_registry/llm_models_test.py b/autogpt_platform/backend/backend/data/llm_registry/llm_models_test.py
index c4bac51510..7f719e8b84 100644
--- a/autogpt_platform/backend/backend/data/llm_registry/llm_models_test.py
+++ b/autogpt_platform/backend/backend/data/llm_registry/llm_models_test.py
@@ -32,9 +32,11 @@ def test_kill_switched_model_hidden_from_picker_metadata(monkeypatch):
assert LLMModel(victim.value) is victim
-def test_all_models_visible_when_none_disabled():
+def test_picker_shows_every_model_not_hidden():
metadata = _schema_metadata()
- assert len(metadata) == len(list(LLMModel))
+ assert (
+ set(metadata) == {m.value for m in LLMModel} - llm_models._PICKER_HIDDEN_SLUGS
+ )
def test_opus_5_is_selectable_in_blocks():
diff --git a/docs/integrations/block-integrations/llm.md b/docs/integrations/block-integrations/llm.md
index 7f243bbb41..9172a3702f 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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6.1-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "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-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "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-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-large-4-0" \| "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" \| "deepseek/deepseek-v4.1-flash" \| "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" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "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-4.7" \| "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" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "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" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6.1-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "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-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "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-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-large-4-0" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-medium-3-5" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/mistral-small-2603" \| "mistralai/ministral-14b-2512" \| "mistralai/ministral-8b-2512" \| "mistralai/ministral-3b-2512" \| "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" \| "deepseek/deepseek-v4.1-flash" \| "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" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "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-4.7" \| "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" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "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" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6.1-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "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-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "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-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-large-4-0" \| "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" \| "deepseek/deepseek-v4.1-flash" \| "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" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "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-4.7" \| "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" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "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" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6.1-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "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-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "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-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-large-4-0" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-medium-3-5" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/mistral-small-2603" \| "mistralai/ministral-14b-2512" \| "mistralai/ministral-8b-2512" \| "mistralai/ministral-3b-2512" \| "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" \| "deepseek/deepseek-v4.1-flash" \| "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" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "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-4.7" \| "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" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "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" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6.1-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "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-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "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-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-large-4-0" \| "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" \| "deepseek/deepseek-v4.1-flash" \| "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" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "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-4.7" \| "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" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "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" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6.1-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "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-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "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-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-large-4-0" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-medium-3-5" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/mistral-small-2603" \| "mistralai/ministral-14b-2512" \| "mistralai/ministral-8b-2512" \| "mistralai/ministral-3b-2512" \| "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" \| "deepseek/deepseek-v4.1-flash" \| "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" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "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-4.7" \| "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" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "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" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6.1-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "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-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "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-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-large-4-0" \| "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" \| "deepseek/deepseek-v4.1-flash" \| "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" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "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-4.7" \| "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" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "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" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6.1-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "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-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "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-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-large-4-0" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-medium-3-5" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/mistral-small-2603" \| "mistralai/ministral-14b-2512" \| "mistralai/ministral-8b-2512" \| "mistralai/ministral-3b-2512" \| "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" \| "deepseek/deepseek-v4.1-flash" \| "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" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "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-4.7" \| "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" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "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" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6.1-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "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-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "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-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-large-4-0" \| "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" \| "deepseek/deepseek-v4.1-flash" \| "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" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "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-4.7" \| "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" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "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" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6.1-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "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-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "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-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-large-4-0" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-medium-3-5" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/mistral-small-2603" \| "mistralai/ministral-14b-2512" \| "mistralai/ministral-8b-2512" \| "mistralai/ministral-3b-2512" \| "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" \| "deepseek/deepseek-v4.1-flash" \| "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" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "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-4.7" \| "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" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "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" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6.1-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "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-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "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-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-large-4-0" \| "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" \| "deepseek/deepseek-v4.1-flash" \| "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" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "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-4.7" \| "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" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "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" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6.1-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "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-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "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-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-large-4-0" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-medium-3-5" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/mistral-small-2603" \| "mistralai/ministral-14b-2512" \| "mistralai/ministral-8b-2512" \| "mistralai/ministral-3b-2512" \| "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" \| "deepseek/deepseek-v4.1-flash" \| "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" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "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-4.7" \| "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" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "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" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "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 |
@@ -724,7 +724,7 @@ In the default `built_in` execution mode, configure `agent_mode_max_iterations`
| 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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6.1-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "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-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "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-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-large-4-0" \| "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" \| "deepseek/deepseek-v4.1-flash" \| "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" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "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-4.7" \| "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" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "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" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6.1-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "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-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "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-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-large-4-0" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-medium-3-5" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/mistral-small-2603" \| "mistralai/ministral-14b-2512" \| "mistralai/ministral-8b-2512" \| "mistralai/ministral-3b-2512" \| "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" \| "deepseek/deepseek-v4.1-flash" \| "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" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "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-4.7" \| "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" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "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" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "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 |