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(llm-catalog): add DeepSeek V4.1 Flash (#14530)
Nicholas Tindleee29815c568f
diff --git a/autogpt_platform/backend/backend/data/llm_registry/catalog.py b/autogpt_platform/backend/backend/data/llm_registry/catalog.pyindex 12a0cbdbde..c1a296b41a 100644--- a/autogpt_platform/backend/backend/data/llm_registry/catalog.py+++ b/autogpt_platform/backend/backend/data/llm_registry/catalog.py@@ -479,6 +479,21 @@ def _build_catalog() -> CatalogPayload:run_credits=1, input_credits_per_1m=21.0, output_credits_per_1m=42.0),),+ CatalogModel(+ slug="deepseek/deepseek-v4.1-flash",+ display_name="DeepSeek V4.1 Flash",+ provider="open_router",+ creator="deepseek",+ context_window=1048576,+ max_output_tokens=384000,+ price_tier=1,+ cost=CatalogModelCost(+ run_credits=1,+ input_credits_per_1m=22.5,+ output_credits_per_1m=90.0,+ cache_read_credits_per_1m=0.45,+ ),+ ),CatalogModel(slug="google/gemini-2.0-flash-001",display_name="Gemini 2.0 Flash 001",diff --git a/autogpt_platform/backend/backend/data/llm_registry/catalog_test.py b/autogpt_platform/backend/backend/data/llm_registry/catalog_test.pyindex 849fcd5cef..52643bcc84 100644--- a/autogpt_platform/backend/backend/data/llm_registry/catalog_test.py+++ b/autogpt_platform/backend/backend/data/llm_registry/catalog_test.py@@ -283,6 +283,26 @@ def test_qwen3_8_max_0902_bills_at_authored_rates():assert qwen_max_entry.context_window == 262144+def test_deepseek_v4_1_flash_bills_at_authored_rates():+ """DeepSeek V4.1 Flash (OpenRouter, DeepSeek list price $0.15/$0.60 per+ 1M, $0.003/1M cached input) — flat tier and per-1M projections must+ match the authored catalog entry."""+ flash = LLMModel("deepseek/deepseek-v4.1-flash")+ assert MODEL_COST[flash] == 1+ assert TOKEN_COST[flash].model_dump() == {+ "input": 22.5,+ "output": 90.0,+ "cache_read": 0.45,+ "cache_creation": 0.0,+ }+ assert MODEL_METADATA[flash].max_output_tokens == 384000+ flash_entry = next(+ m for m in CATALOG.models if m.slug == "deepseek/deepseek-v4.1-flash"+ )+ assert flash_entry.price_tier == 1+ assert flash_entry.context_window == 1048576++def test_provider_usd_prices_are_all_or_nothing():"""A half-authored provider USD price must refuse to construct — itwould silently underprice against the transport family default."""diff --git a/autogpt_platform/backend/backend/data/llm_registry/llm_models.py b/autogpt_platform/backend/backend/data/llm_registry/llm_models.pyindex b6cece61b5..ec82c1aefd 100644--- a/autogpt_platform/backend/backend/data/llm_registry/llm_models.py+++ b/autogpt_platform/backend/backend/data/llm_registry/llm_models.py@@ -212,6 +212,7 @@ class LLMModel(str, Enum, metaclass=LLMModelMeta):COHERE_COMMAND_A_VISION_07_2025 = "cohere/command-a-vision-07-2025"DEEPSEEK_CHAT = "deepseek/deepseek-chat" # Actually: DeepSeek V3DEEPSEEK_R1_0528 = "deepseek/deepseek-r1-0528"+ DEEPSEEK_V4_1_FLASH = "deepseek/deepseek-v4.1-flash"PERPLEXITY_SONAR = "perplexity/sonar"PERPLEXITY_SONAR_PRO = "perplexity/sonar-pro"PERPLEXITY_SONAR_REASONING_PRO = "perplexity/sonar-reasoning-pro"diff --git a/docs/integrations/block-integrations/llm.md b/docs/integrations/block-integrations/llm.mdindex 54f70b17a4..9efba7950f 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-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-5" \| "claude-sonnet-4-6" \| "claude-sonnet-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" \| "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" \| "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-4.20-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" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "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-5" \| "claude-sonnet-4-6" \| "claude-sonnet-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" \| "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" \| "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" \| "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-4.20-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" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "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-5" \| "claude-sonnet-4-6" \| "claude-sonnet-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" \| "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" \| "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-4.20-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" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "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-5" \| "claude-sonnet-4-6" \| "claude-sonnet-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" \| "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" \| "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" \| "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-4.20-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" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "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-5" \| "claude-sonnet-4-6" \| "claude-sonnet-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" \| "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" \| "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-4.20-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" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "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-5" \| "claude-sonnet-4-6" \| "claude-sonnet-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" \| "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" \| "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" \| "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-4.20-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" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "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-5" \| "claude-sonnet-4-6" \| "claude-sonnet-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" \| "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" \| "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-4.20-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" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "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-5" \| "claude-sonnet-4-6" \| "claude-sonnet-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" \| "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" \| "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" \| "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-4.20-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" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "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-5" \| "claude-sonnet-4-6" \| "claude-sonnet-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" \| "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" \| "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-4.20-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" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "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-5" \| "claude-sonnet-4-6" \| "claude-sonnet-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" \| "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" \| "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" \| "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-4.20-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" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "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-5" \| "claude-sonnet-4-6" \| "claude-sonnet-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" \| "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" \| "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-4.20-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" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "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-5" \| "claude-sonnet-4-6" \| "claude-sonnet-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" \| "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" \| "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" \| "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-4.20-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" \| "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 |@@ -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-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-5" \| "claude-sonnet-4-6" \| "claude-sonnet-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" \| "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" \| "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-4.20-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" \| "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" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "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-5" \| "claude-sonnet-4-6" \| "claude-sonnet-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" \| "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" \| "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" \| "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-4.20-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" \| "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 |