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): retire deprecated LLM models with family-aware migration (#13089)
Krzysztof Czerwinski48129a9301bc
diff --git a/autogpt_platform/backend/backend/blocks/llm.py b/autogpt_platform/backend/backend/blocks/llm.pyindex 05bca5fa62..b2687523ca 100644--- a/autogpt_platform/backend/backend/blocks/llm.py+++ b/autogpt_platform/backend/backend/blocks/llm.py@@ -131,8 +131,6 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):# OpenAI modelsO3_MINI = "o3-mini"O3 = "o3-2025-04-16"- O1 = "o1"- O1_MINI = "o1-mini"# GPT-5 modelsGPT5_2 = "gpt-5.2-2025-12-11"GPT5_1 = "gpt-5.1-2025-11-13"@@ -144,24 +142,15 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):GPT41_MINI = "gpt-4.1-mini-2025-04-14"GPT4O_MINI = "gpt-4o-mini"GPT4O = "gpt-4o"- GPT4_TURBO = "gpt-4-turbo"# Anthropic models- CLAUDE_4_1_OPUS = "claude-opus-4-1-20250805"- CLAUDE_4_OPUS = "claude-opus-4-20250514"- CLAUDE_4_SONNET = "claude-sonnet-4-20250514"CLAUDE_4_5_OPUS = "claude-opus-4-5-20251101"CLAUDE_4_5_SONNET = "claude-sonnet-4-5-20250929"CLAUDE_4_5_HAIKU = "claude-haiku-4-5-20251001"CLAUDE_4_6_OPUS = "claude-opus-4-6"CLAUDE_4_7_OPUS = "claude-opus-4-7"CLAUDE_4_6_SONNET = "claude-sonnet-4-6"- CLAUDE_3_HAIKU = "claude-3-haiku-20240307"# AI/ML API models- AIML_API_QWEN2_5_72B = "Qwen/Qwen2.5-72B-Instruct-Turbo"- AIML_API_LLAMA3_1_70B = "nvidia/llama-3.1-nemotron-70b-instruct"AIML_API_LLAMA3_3_70B = "meta-llama/Llama-3.3-70B-Instruct-Turbo"- AIML_API_META_LLAMA_3_1_70B = "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo"- AIML_API_LLAMA_3_2_3B = "meta-llama/Llama-3.2-3B-Instruct-Turbo"# Groq modelsLLAMA3_3_70B = "llama-3.3-70b-versatile"LLAMA3_1_8B = "llama-3.1-8b-instant"@@ -174,22 +163,17 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):# OpenRouter modelsOPENAI_GPT_OSS_120B = "openai/gpt-oss-120b"OPENAI_GPT_OSS_20B = "openai/gpt-oss-20b"- GEMINI_2_5_PRO_PREVIEW = "google/gemini-2.5-pro-preview-03-25"GEMINI_2_5_PRO = "google/gemini-2.5-pro"GEMINI_3_1_PRO_PREVIEW = "google/gemini-3.1-pro-preview"GEMINI_3_FLASH_PREVIEW = "google/gemini-3-flash-preview"GEMINI_2_5_FLASH = "google/gemini-2.5-flash"GEMINI_2_0_FLASH = "google/gemini-2.0-flash-001"GEMINI_3_1_FLASH_LITE_PREVIEW = "google/gemini-3.1-flash-lite-preview"- GEMINI_2_5_FLASH_LITE_PREVIEW = "google/gemini-2.5-flash-lite-preview-06-17"GEMINI_2_0_FLASH_LITE = "google/gemini-2.0-flash-lite-001"- MISTRAL_NEMO = "mistralai/mistral-nemo"MISTRAL_LARGE_3 = "mistralai/mistral-large-2512"MISTRAL_MEDIUM_3_1 = "mistralai/mistral-medium-3.1"MISTRAL_SMALL_3_2 = "mistralai/mistral-small-3.2-24b-instruct"CODESTRAL = "mistralai/codestral-2508"- COHERE_COMMAND_R_08_2024 = "cohere/command-r-08-2024"- COHERE_COMMAND_R_PLUS_08_2024 = "cohere/command-r-plus-08-2024"COHERE_COMMAND_A_03_2025 = "cohere/command-a-03-2025"COHERE_COMMAND_A_TRANSLATE_08_2025 = "cohere/command-a-translate-08-2025"COHERE_COMMAND_A_REASONING_08_2025 = "cohere/command-a-reasoning-08-2025"@@ -205,7 +189,6 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):AMAZON_NOVA_LITE_V1 = "amazon/nova-lite-v1"AMAZON_NOVA_MICRO_V1 = "amazon/nova-micro-v1"AMAZON_NOVA_PRO_V1 = "amazon/nova-pro-v1"- MICROSOFT_WIZARDLM_2_8X22B = "microsoft/wizardlm-2-8x22b"MICROSOFT_PHI_4 = "microsoft/phi-4"GRYPHE_MYTHOMAX_L2_13B = "gryphe/mythomax-l2-13b"META_LLAMA_4_SCOUT = "meta-llama/llama-4-scout"@@ -217,19 +200,12 @@ class LlmModel(str, Enum, metaclass=LlmModelMeta):GROK_4_20 = "x-ai/grok-4.20"GROK_4_20_MULTI_AGENT = "x-ai/grok-4.20-multi-agent"GROK_CODE_FAST_1 = "x-ai/grok-code-fast-1"- KIMI_K2 = "moonshotai/kimi-k2"- KIMI_K2_0905 = "moonshotai/kimi-k2-0905"KIMI_K2_5 = "moonshotai/kimi-k2.5"KIMI_K2_6 = "moonshotai/kimi-k2.6"KIMI_K2_THINKING = "moonshotai/kimi-k2-thinking"QWEN3_235B_A22B_THINKING = "qwen/qwen3-235b-a22b-thinking-2507"QWEN3_CODER = "qwen/qwen3-coder"# Z.ai (Zhipu) models- ZAI_GLM_4_32B = "z-ai/glm-4-32b"- ZAI_GLM_4_5 = "z-ai/glm-4.5"- ZAI_GLM_4_5_AIR = "z-ai/glm-4.5-air"- ZAI_GLM_4_5_AIR_FREE = "z-ai/glm-4.5-air:free"- ZAI_GLM_4_5V = "z-ai/glm-4.5v"ZAI_GLM_4_6 = "z-ai/glm-4.6"ZAI_GLM_4_6V = "z-ai/glm-4.6v"ZAI_GLM_4_7 = "z-ai/glm-4.7"@@ -290,12 +266,6 @@ MODEL_METADATA = {LlmModel.O3_MINI: ModelMetadata("openai", 200000, 100000, "O3 Mini", "OpenAI", "OpenAI", 1), # o3-mini-2025-01-31- LlmModel.O1: ModelMetadata(- "openai", 200000, 100000, "O1", "OpenAI", "OpenAI", 3- ), # o1-2024-12-17- LlmModel.O1_MINI: ModelMetadata(- "openai", 128000, 65536, "O1 Mini", "OpenAI", "OpenAI", 2- ), # o1-mini-2024-09-12# GPT-5 modelsLlmModel.GPT5_2: ModelMetadata("openai", 400000, 128000, "GPT-5.2", "OpenAI", "OpenAI", 3@@ -327,19 +297,7 @@ MODEL_METADATA = {LlmModel.GPT4O: ModelMetadata("openai", 128000, 16384, "GPT-4o", "OpenAI", "OpenAI", 2), # gpt-4o-2024-08-06- LlmModel.GPT4_TURBO: ModelMetadata(- "openai", 128000, 4096, "GPT-4 Turbo", "OpenAI", "OpenAI", 3- ), # gpt-4-turbo-2024-04-09# https://docs.anthropic.com/en/docs/about-claude/models- LlmModel.CLAUDE_4_1_OPUS: ModelMetadata(- "anthropic", 200000, 32000, "Claude Opus 4.1", "Anthropic", "Anthropic", 3- ), # claude-opus-4-1-20250805- LlmModel.CLAUDE_4_OPUS: ModelMetadata(- "anthropic", 200000, 32000, "Claude Opus 4", "Anthropic", "Anthropic", 3- ), # claude-4-opus-20250514- LlmModel.CLAUDE_4_SONNET: ModelMetadata(- "anthropic", 200000, 64000, "Claude Sonnet 4", "Anthropic", "Anthropic", 2- ), # claude-4-sonnet-20250514LlmModel.CLAUDE_4_6_OPUS: ModelMetadata("anthropic", 200000, 128000, "Claude Opus 4.6", "Anthropic", "Anthropic", 3), # claude-opus-4-6@@ -358,31 +316,10 @@ MODEL_METADATA = {LlmModel.CLAUDE_4_5_HAIKU: ModelMetadata("anthropic", 200000, 64000, "Claude Haiku 4.5", "Anthropic", "Anthropic", 2), # claude-haiku-4-5-20251001- LlmModel.CLAUDE_3_HAIKU: ModelMetadata(- "anthropic", 200000, 4096, "Claude 3 Haiku", "Anthropic", "Anthropic", 1- ), # claude-3-haiku-20240307# https://docs.aimlapi.com/api-overview/model-database/text-models- LlmModel.AIML_API_QWEN2_5_72B: ModelMetadata(- "aiml_api", 32000, 8000, "Qwen 2.5 72B Instruct Turbo", "AI/ML", "Qwen", 1- ),- LlmModel.AIML_API_LLAMA3_1_70B: ModelMetadata(- "aiml_api",- 128000,- 40000,- "Llama 3.1 Nemotron 70B Instruct",- "AI/ML",- "Nvidia",- 1,- ),LlmModel.AIML_API_LLAMA3_3_70B: ModelMetadata("aiml_api", 128000, None, "Llama 3.3 70B Instruct Turbo", "AI/ML", "Meta", 1),- LlmModel.AIML_API_META_LLAMA_3_1_70B: ModelMetadata(- "aiml_api", 131000, 2000, "Llama 3.1 70B Instruct Turbo", "AI/ML", "Meta", 1- ),- LlmModel.AIML_API_LLAMA_3_2_3B: ModelMetadata(- "aiml_api", 128000, None, "Llama 3.2 3B Instruct Turbo", "AI/ML", "Meta", 1- ),# https://console.groq.com/docs/modelsLlmModel.LLAMA3_3_70B: ModelMetadata("groq", 128000, 32768, "Llama 3.3 70B Versatile", "Groq", "Meta", 1@@ -407,15 +344,6 @@ MODEL_METADATA = {"ollama", 32768, None, "Dolphin Mistral Latest", "Ollama", "Mistral AI", 1),# https://openrouter.ai/models- LlmModel.GEMINI_2_5_PRO_PREVIEW: ModelMetadata(- "open_router",- 1048576,- 65536,- "Gemini 2.5 Pro Preview 03.25",- "OpenRouter",- "Google",- 2,- ),LlmModel.GEMINI_2_5_PRO: ModelMetadata("open_router",1048576,@@ -458,15 +386,6 @@ MODEL_METADATA = {"Google",1,),- LlmModel.GEMINI_2_5_FLASH_LITE_PREVIEW: ModelMetadata(- "open_router",- 1048576,- 65535,- "Gemini 2.5 Flash Lite Preview 06.17",- "OpenRouter",- "Google",- 1,- ),LlmModel.GEMINI_2_0_FLASH_LITE: ModelMetadata("open_router",1048576,@@ -476,9 +395,6 @@ MODEL_METADATA = {"Google",1,),- LlmModel.MISTRAL_NEMO: ModelMetadata(- "open_router", 128000, 4096, "Mistral Nemo", "OpenRouter", "Mistral AI", 1- ),LlmModel.MISTRAL_LARGE_3: ModelMetadata("open_router",262144,@@ -515,12 +431,6 @@ MODEL_METADATA = {"Mistral AI",1,),- LlmModel.COHERE_COMMAND_R_08_2024: ModelMetadata(- "open_router", 128000, 4096, "Command R 08.2024", "OpenRouter", "Cohere", 1- ),- LlmModel.COHERE_COMMAND_R_PLUS_08_2024: ModelMetadata(- "open_router", 128000, 4096, "Command R Plus 08.2024", "OpenRouter", "Cohere", 2- ),LlmModel.COHERE_COMMAND_A_03_2025: ModelMetadata("open_router", 256000, 8192, "Command A 03.2025", "OpenRouter", "Cohere", 2),@@ -614,9 +524,6 @@ MODEL_METADATA = {LlmModel.AMAZON_NOVA_PRO_V1: ModelMetadata("open_router", 300000, 5120, "Nova Pro V1", "OpenRouter", "Amazon", 1),- LlmModel.MICROSOFT_WIZARDLM_2_8X22B: ModelMetadata(- "open_router", 65536, 4096, "WizardLM 2 8x22B", "OpenRouter", "Microsoft", 1- ),LlmModel.MICROSOFT_PHI_4: ModelMetadata("open_router", 16384, 16384, "Phi-4", "OpenRouter", "Microsoft", 1),@@ -662,12 +569,6 @@ MODEL_METADATA = {LlmModel.GROK_CODE_FAST_1: ModelMetadata("open_router", 256000, 10000, "Grok Code Fast 1", "OpenRouter", "xAI", 1),- LlmModel.KIMI_K2: ModelMetadata(- "open_router", 131000, 131000, "Kimi K2", "OpenRouter", "Moonshot AI", 1- ),- LlmModel.KIMI_K2_0905: ModelMetadata(- "open_router", 262144, 262144, "Kimi K2 0905", "OpenRouter", "Moonshot AI", 1- ),LlmModel.KIMI_K2_5: ModelMetadata("open_router", 262144, 262144, "Kimi K2.5", "OpenRouter", "Moonshot AI", 1),@@ -696,21 +597,6 @@ MODEL_METADATA = {"open_router", 262144, 262144, "Qwen 3 Coder", "OpenRouter", "Qwen", 3),# https://openrouter.ai/models?q=z-ai- LlmModel.ZAI_GLM_4_32B: ModelMetadata(- "open_router", 128000, 128000, "GLM 4 32B", "OpenRouter", "Z.ai", 1- ),- LlmModel.ZAI_GLM_4_5: ModelMetadata(- "open_router", 131072, 98304, "GLM 4.5", "OpenRouter", "Z.ai", 2- ),- LlmModel.ZAI_GLM_4_5_AIR: ModelMetadata(- "open_router", 131072, 98304, "GLM 4.5 Air", "OpenRouter", "Z.ai", 1- ),- LlmModel.ZAI_GLM_4_5_AIR_FREE: ModelMetadata(- "open_router", 131072, 96000, "GLM 4.5 Air (Free)", "OpenRouter", "Z.ai", 1- ),- LlmModel.ZAI_GLM_4_5V: ModelMetadata(- "open_router", 65536, 16384, "GLM 4.5V", "OpenRouter", "Z.ai", 2- ),LlmModel.ZAI_GLM_4_6: ModelMetadata("open_router", 204800, 204800, "GLM 4.6", "OpenRouter", "Z.ai", 1),@@ -765,6 +651,42 @@ MODEL_METADATA = {DEFAULT_LLM_MODEL = LlmModel.GPT5_2+# Family-aware mapping for legacy model values that have been retired from the+# `LlmModel` enum. Used by both the Prisma migration that rewrites stored graph+# definitions and by the boot-time safety net (`migrate_llm_models` in+# backend/data/graph.py) so a Claude Opus user lands on a newer Opus instead of+# the global GPT default. Keep this in sync with+# migrations/20260512120000_retire_deprecated_llm_models/migration.sql.+LEGACY_MODEL_MAPPINGS: dict[str, LlmModel] = {+ "claude-3-haiku-20240307": LlmModel.CLAUDE_4_5_HAIKU,+ "claude-opus-4-20250514": LlmModel.CLAUDE_4_7_OPUS,+ "claude-sonnet-4-20250514": LlmModel.CLAUDE_4_6_SONNET,+ "claude-opus-4-1-20250805": LlmModel.CLAUDE_4_7_OPUS,+ "gpt-4-turbo": LlmModel.GPT41,+ "o1": LlmModel.O3,+ "o1-mini": LlmModel.O3_MINI,+ "google/gemini-2.5-pro-preview-03-25": LlmModel.GEMINI_2_5_PRO,+ "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,+ "microsoft/wizardlm-2-8x22b": LlmModel.MICROSOFT_PHI_4,+ "moonshotai/kimi-k2": LlmModel.KIMI_K2_6,+ "moonshotai/kimi-k2-0905": LlmModel.KIMI_K2_6,+ "z-ai/glm-4-32b": LlmModel.ZAI_GLM_4_6,+ "z-ai/glm-4.5": LlmModel.ZAI_GLM_4_6,+ "z-ai/glm-4.5-air": LlmModel.ZAI_GLM_4_7_FLASH,+ "z-ai/glm-4.5-air:free": LlmModel.ZAI_GLM_4_7_FLASH,+ "z-ai/glm-4.5v": LlmModel.ZAI_GLM_4_6V,+ # AI/ML API stragglers — no direct same-family successor on AI/ML's current+ # catalogue, so they all map to the closest open-weight Meta/Llama option+ # that AI/ML still serves.+ "Qwen/Qwen2.5-72B-Instruct-Turbo": LlmModel.AIML_API_LLAMA3_3_70B,+ "nvidia/llama-3.1-nemotron-70b-instruct": LlmModel.AIML_API_LLAMA3_3_70B,+ "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo": LlmModel.AIML_API_LLAMA3_3_70B,+ "meta-llama/Llama-3.2-3B-Instruct-Turbo": LlmModel.AIML_API_LLAMA3_3_70B,+}+for model in LlmModel:if model not in MODEL_METADATA:raise ValueError(f"Missing MODEL_METADATA metadata for model: {model}")diff --git a/autogpt_platform/backend/backend/blocks/test/test_llm.py b/autogpt_platform/backend/backend/blocks/test/test_llm.pyindex 01bfc97012..81285cfe1b 100644--- a/autogpt_platform/backend/backend/blocks/test/test_llm.py+++ b/autogpt_platform/backend/backend/blocks/test/test_llm.py@@ -84,7 +84,7 @@ class TestLLMStatsTracking:response = await llm.llm_call(credentials=anthropic_creds,- llm_model=llm.LlmModel.CLAUDE_3_HAIKU,+ llm_model=llm.LlmModel.CLAUDE_4_5_HAIKU,prompt=[{"role": "user", "content": "Hello"}],max_tokens=100,)diff --git a/autogpt_platform/backend/backend/copilot/config_test.py b/autogpt_platform/backend/backend/copilot/config_test.pyindex eb5f022839..a293af6dbf 100644--- a/autogpt_platform/backend/backend/copilot/config_test.py+++ b/autogpt_platform/backend/backend/copilot/config_test.py@@ -339,11 +339,11 @@ class TestSdkModelVendorCompatibility:api_key=None,base_url=None,use_claude_code_subscription=False,- thinking_standard_model="claude-sonnet-4-20250514",+ thinking_standard_model="claude-sonnet-4-6",thinking_advanced_model="anthropic/claude-opus-4-7",aux_api_key="or-aux-key",)- assert cfg.thinking_standard_model == "claude-sonnet-4-20250514"+ assert cfg.thinking_standard_model == "claude-sonnet-4-6"def test_fast_advanced_model_also_validated(self):with pytest.raises(Exception, match="fast_advanced_model"):diff --git a/autogpt_platform/backend/backend/copilot/model_normalize_test.py b/autogpt_platform/backend/backend/copilot/model_normalize_test.pyindex 8b6a948b75..a6bc6d56e4 100644--- a/autogpt_platform/backend/backend/copilot/model_normalize_test.py+++ b/autogpt_platform/backend/backend/copilot/model_normalize_test.py@@ -61,7 +61,7 @@ class TestNormalizeModelForTransport:)def test_unprefixed_claude_slug_passes(self):- # ``claude-sonnet-4-20250514`` (no vendor prefix) is the+ # ``claude-sonnet-4-6`` (no vendor prefix) is the# Anthropic Messages / OpenAI-compat form — must pass through.cfg = _make_cfg(use_openrouter=False,@@ -70,8 +70,8 @@ class TestNormalizeModelForTransport:use_claude_code_subscription=False,)assert (- normalize_model_for_transport("claude-sonnet-4-20250514", cfg)- == "claude-sonnet-4-20250514"+ normalize_model_for_transport("claude-sonnet-4-6", cfg)+ == "claude-sonnet-4-6")def test_unprefixed_non_anthropic_slug_rejected(self):diff --git a/autogpt_platform/backend/backend/copilot/sdk/e2e_compaction_test.py b/autogpt_platform/backend/backend/copilot/sdk/e2e_compaction_test.pyindex 0fad2aef77..727e6a6d31 100644--- a/autogpt_platform/backend/backend/copilot/sdk/e2e_compaction_test.py+++ b/autogpt_platform/backend/backend/copilot/sdk/e2e_compaction_test.py@@ -250,7 +250,7 @@ class TestCompactionE2E:# --- Step 4: SDK starts streaming ---builder.append_assistant([{"type": "thinking", "thinking": "Let me read file2.py..."}],- model="claude-sonnet-4-20250514",+ model="claude-sonnet-4-6",)assert builder.entry_count == 9@@ -321,7 +321,7 @@ class TestCompactionE2E:# --- Step 11: More assistant messages after compaction ---builder.append_assistant([{"type": "text", "text": "Here is file2.py:\n\ndef hello():\n pass"}],- model="claude-sonnet-4-20250514",+ model="claude-sonnet-4-6",stop_reason="end_turn",)assert builder.entry_count == 5@@ -493,7 +493,7 @@ class TestCompactionE2E:builder.append_user("Now show file2.py")builder.append_assistant([{"type": "text", "text": "Reading file2.py..."}],- model="claude-sonnet-4-20250514",+ model="claude-sonnet-4-6",)# CLI writes session file with compactiondiff --git a/autogpt_platform/backend/backend/copilot/sdk/p0_guardrails_test.py b/autogpt_platform/backend/backend/copilot/sdk/p0_guardrails_test.pyindex 808e07dbd6..8a91cc08cf 100644--- a/autogpt_platform/backend/backend/copilot/sdk/p0_guardrails_test.py+++ b/autogpt_platform/backend/backend/copilot/sdk/p0_guardrails_test.py@@ -55,7 +55,7 @@ class TestResolveFallbackModel:Anthropic vendors stay routable. Anthropic slugs are passedthrough unchanged in this mode (PR #12878)."""cfg = _make_config(- claude_agent_fallback_model="anthropic/claude-sonnet-4-20250514",+ claude_agent_fallback_model="anthropic/claude-sonnet-4-6",use_openrouter=True,api_key="sk-test",base_url="https://openrouter.ai/api/v1",@@ -65,7 +65,7 @@ class TestResolveFallbackModel:result = _resolve_fallback_model()- assert result == "anthropic/claude-sonnet-4-20250514"+ assert result == "anthropic/claude-sonnet-4-6"def test_dots_replaced_for_direct_anthropic(self):"""Direct Anthropic requires hyphen-separated versions."""diff --git a/autogpt_platform/backend/backend/copilot/sdk/retry_scenarios_test.py b/autogpt_platform/backend/backend/copilot/sdk/retry_scenarios_test.pyindex 6a0532838a..93082fc7e2 100644--- a/autogpt_platform/backend/backend/copilot/sdk/retry_scenarios_test.py+++ b/autogpt_platform/backend/backend/copilot/sdk/retry_scenarios_test.py@@ -1283,7 +1283,7 @@ class TestStreamChatCompletionRetryIntegration:# events) then raise prompt-too-long.text_msg = AssistantMessage(content=[TextBlock(text="partial")],- model="claude-sonnet-4-20250514",+ model="claude-sonnet-4-6",)prompt_err = Exception("prompt is too long (context_length_exceeded)")attempt_count = [0]@@ -1744,7 +1744,7 @@ class TestStreamChatCompletionRetryIntegration:# raises _HandledStreamError(code="transient_api_error").yield AssistantMessage(content=[],- model="claude-sonnet-4-20250514",+ model="claude-sonnet-4-6",error="rate_limit",)yield ResultMessage(diff --git a/autogpt_platform/backend/backend/copilot/sdk/service_helpers_test.py b/autogpt_platform/backend/backend/copilot/sdk/service_helpers_test.pyindex 6bb2eee712..57c2825b6d 100644--- a/autogpt_platform/backend/backend/copilot/sdk/service_helpers_test.py+++ b/autogpt_platform/backend/backend/copilot/sdk/service_helpers_test.py@@ -430,10 +430,7 @@ class TestNormalizeModelName:_normalize_model_name("google/gemini-2.5-flash")def test_already_normalized_unchanged(self, _direct_anthropic_config):- assert (- _normalize_model_name("claude-sonnet-4-20250514")- == "claude-sonnet-4-20250514"- )+ assert _normalize_model_name("claude-sonnet-4-6") == "claude-sonnet-4-6"def test_empty_string_unchanged(self, _direct_anthropic_config):assert _normalize_model_name("") == ""diff --git a/autogpt_platform/backend/backend/copilot/sdk/service_test.py b/autogpt_platform/backend/backend/copilot/sdk/service_test.pyindex 7fe31fbd36..28fd03f8ca 100644--- a/autogpt_platform/backend/backend/copilot/sdk/service_test.py+++ b/autogpt_platform/backend/backend/copilot/sdk/service_test.py@@ -387,10 +387,7 @@ class TestNormalizeModelName:aux_api_key="or-aux-key",)monkeypatch.setattr("backend.copilot.sdk.service.config", cfg)- assert (- _normalize_model_name("claude-sonnet-4-20250514")- == "claude-sonnet-4-20250514"- )+ assert _normalize_model_name("claude-sonnet-4-6") == "claude-sonnet-4-6"class TestResolveSdkModel:diff --git a/autogpt_platform/backend/backend/data/block_cost_config.py b/autogpt_platform/backend/backend/data/block_cost_config.pyindex 7563f5047a..e1be1a0710 100644--- a/autogpt_platform/backend/backend/data/block_cost_config.py+++ b/autogpt_platform/backend/backend/data/block_cost_config.py@@ -110,8 +110,6 @@ from backend.integrations.credentials_store import (MODEL_COST: dict[LlmModel, int] = {LlmModel.O3: 4,LlmModel.O3_MINI: 2,- LlmModel.O1: 16,- LlmModel.O1_MINI: 4,# GPT-5 modelsLlmModel.GPT5_2: 6,LlmModel.GPT5_1: 5,@@ -123,22 +121,13 @@ MODEL_COST: dict[LlmModel, int] = {LlmModel.GPT41_MINI: 1,LlmModel.GPT4O_MINI: 1,LlmModel.GPT4O: 3,- LlmModel.GPT4_TURBO: 10,- LlmModel.CLAUDE_4_1_OPUS: 21,- LlmModel.CLAUDE_4_OPUS: 21,- LlmModel.CLAUDE_4_SONNET: 5,LlmModel.CLAUDE_4_6_OPUS: 14,LlmModel.CLAUDE_4_7_OPUS: 14,LlmModel.CLAUDE_4_6_SONNET: 9,LlmModel.CLAUDE_4_5_HAIKU: 4,LlmModel.CLAUDE_4_5_OPUS: 14,LlmModel.CLAUDE_4_5_SONNET: 9,- LlmModel.CLAUDE_3_HAIKU: 1,- LlmModel.AIML_API_QWEN2_5_72B: 1,- LlmModel.AIML_API_LLAMA3_1_70B: 1,LlmModel.AIML_API_LLAMA3_3_70B: 1,- LlmModel.AIML_API_META_LLAMA_3_1_70B: 1,- LlmModel.AIML_API_LLAMA_3_2_3B: 1,LlmModel.LLAMA3_3_70B: 1,LlmModel.LLAMA3_1_8B: 1,LlmModel.OLLAMA_LLAMA3_3: 1,@@ -148,22 +137,17 @@ MODEL_COST: dict[LlmModel, int] = {LlmModel.OLLAMA_DOLPHIN: 1,LlmModel.OPENAI_GPT_OSS_120B: 1,LlmModel.OPENAI_GPT_OSS_20B: 1,- LlmModel.GEMINI_2_5_PRO_PREVIEW: 4,LlmModel.GEMINI_2_5_PRO: 4,LlmModel.GEMINI_3_1_PRO_PREVIEW: 5,LlmModel.GEMINI_3_FLASH_PREVIEW: 2,LlmModel.GEMINI_2_5_FLASH: 1,LlmModel.GEMINI_2_0_FLASH: 1,LlmModel.GEMINI_3_1_FLASH_LITE_PREVIEW: 1,- LlmModel.GEMINI_2_5_FLASH_LITE_PREVIEW: 1,LlmModel.GEMINI_2_0_FLASH_LITE: 1,- LlmModel.MISTRAL_NEMO: 1,LlmModel.MISTRAL_LARGE_3: 2,LlmModel.MISTRAL_MEDIUM_3_1: 2,LlmModel.MISTRAL_SMALL_3_2: 1,LlmModel.CODESTRAL: 1,- LlmModel.COHERE_COMMAND_R_08_2024: 1,- LlmModel.COHERE_COMMAND_R_PLUS_08_2024: 3,LlmModel.COHERE_COMMAND_A_03_2025: 3,LlmModel.COHERE_COMMAND_A_TRANSLATE_08_2025: 3,LlmModel.COHERE_COMMAND_A_REASONING_08_2025: 6,@@ -179,7 +163,6 @@ MODEL_COST: dict[LlmModel, int] = {LlmModel.AMAZON_NOVA_LITE_V1: 1,LlmModel.AMAZON_NOVA_MICRO_V1: 1,LlmModel.AMAZON_NOVA_PRO_V1: 1,- LlmModel.MICROSOFT_WIZARDLM_2_8X22B: 1,LlmModel.MICROSOFT_PHI_4: 1,LlmModel.GRYPHE_MYTHOMAX_L2_13B: 1,LlmModel.META_LLAMA_4_SCOUT: 1,@@ -195,19 +178,12 @@ MODEL_COST: dict[LlmModel, int] = {LlmModel.GROK_4_20: 5,LlmModel.GROK_4_20_MULTI_AGENT: 5,LlmModel.GROK_CODE_FAST_1: 1,- LlmModel.KIMI_K2: 1,- LlmModel.KIMI_K2_0905: 1,LlmModel.KIMI_K2_5: 1,LlmModel.KIMI_K2_6: 2,LlmModel.KIMI_K2_THINKING: 2,LlmModel.QWEN3_235B_A22B_THINKING: 1,LlmModel.QWEN3_CODER: 9,# Z.ai (Zhipu) models- LlmModel.ZAI_GLM_4_32B: 1,- LlmModel.ZAI_GLM_4_5: 2,- LlmModel.ZAI_GLM_4_5_AIR: 1,- LlmModel.ZAI_GLM_4_5_AIR_FREE: 1,- LlmModel.ZAI_GLM_4_5V: 2,LlmModel.ZAI_GLM_4_6: 1,LlmModel.ZAI_GLM_4_6V: 1,LlmModel.ZAI_GLM_4_7: 1,@@ -247,13 +223,6 @@ class TokenRate(BaseModel):# current credit-to-USD conversion (1 credit ≈ $0.01), with a uniform 1.5x# margin over the published provider price (nearest-integer rounded).TOKEN_COST: dict[LlmModel, TokenRate] = {- # Anthropic Opus legacy ($15/$75/$1.50/$18.75 per 1M).- LlmModel.CLAUDE_4_1_OPUS: TokenRate(- input=2250, output=11250, cache_read=225, cache_creation=2813- ),- LlmModel.CLAUDE_4_OPUS: TokenRate(- input=2250, output=11250, cache_read=225, cache_creation=2813- ),# Anthropic Opus current ($5/$25/$0.50/$6.25 per 1M).LlmModel.CLAUDE_4_6_OPUS: TokenRate(input=750, output=3750, cache_read=75, cache_creation=938@@ -265,9 +234,6 @@ TOKEN_COST: dict[LlmModel, TokenRate] = {input=750, output=3750, cache_read=75, cache_creation=938),# Anthropic Sonnet ($3/$15/$0.30/$3.75).- LlmModel.CLAUDE_4_SONNET: TokenRate(- input=450, output=2250, cache_read=45, cache_creation=563- ),LlmModel.CLAUDE_4_6_SONNET: TokenRate(input=450, output=2250, cache_read=45, cache_creation=563),@@ -278,8 +244,6 @@ TOKEN_COST: dict[LlmModel, TokenRate] = {LlmModel.CLAUDE_4_5_HAIKU: TokenRate(input=150, output=750, cache_read=15, cache_creation=188),- # Claude 3 Haiku ($0.25/$1.25) — legacy, no cache fields wired.- LlmModel.CLAUDE_3_HAIKU: TokenRate(input=38, output=188),# OpenAILlmModel.GPT5_2: TokenRate(input=263, output=2100),LlmModel.GPT5_1: TokenRate(input=188, output=1500),@@ -291,16 +255,11 @@ TOKEN_COST: dict[LlmModel, TokenRate] = {LlmModel.GPT4O_MINI: TokenRate(input=23, output=90),LlmModel.GPT41: TokenRate(input=300, output=1200),LlmModel.GPT41_MINI: TokenRate(input=60, output=240),- LlmModel.GPT4_TURBO: TokenRate(input=1500, output=4500),LlmModel.O3: TokenRate(input=300, output=1200),LlmModel.O3_MINI: TokenRate(input=165, output=660),- LlmModel.O1: TokenRate(input=2250, output=9000),- LlmModel.O1_MINI: TokenRate(input=165, output=660),# Google Gemini (uses <=200k context tier pricing).LlmModel.GEMINI_2_5_PRO: TokenRate(input=188, output=1500),- LlmModel.GEMINI_2_5_PRO_PREVIEW: TokenRate(input=188, output=1500),LlmModel.GEMINI_2_5_FLASH: TokenRate(input=45, output=375),- LlmModel.GEMINI_2_5_FLASH_LITE_PREVIEW: TokenRate(input=15, output=60),LlmModel.GEMINI_2_0_FLASH: TokenRate(input=15, output=60),LlmModel.GEMINI_2_0_FLASH_LITE: TokenRate(input=11, output=45),LlmModel.GEMINI_3_1_PRO_PREVIEW: TokenRate(input=300, output=1800),@@ -331,15 +290,10 @@ TOKEN_COST: dict[LlmModel, TokenRate] = {LlmModel.MISTRAL_LARGE_3: TokenRate(input=300, output=900),LlmModel.MISTRAL_MEDIUM_3_1: TokenRate(input=60, output=300),LlmModel.MISTRAL_SMALL_3_2: TokenRate(input=15, output=45),- LlmModel.MISTRAL_NEMO: TokenRate(input=5, output=5),LlmModel.CODESTRAL: TokenRate(input=45, output=135),# Cohere- LlmModel.COHERE_COMMAND_R_08_2024: TokenRate(input=23, output=90),- LlmModel.COHERE_COMMAND_R_PLUS_08_2024: TokenRate(input=375, output=1500),LlmModel.COHERE_COMMAND_A_03_2025: TokenRate(input=375, output=1500),# Moonshot Kimi- LlmModel.KIMI_K2: TokenRate(input=90, output=375),- LlmModel.KIMI_K2_0905: TokenRate(input=90, output=375),# K2.5 / K2.6 aren't on Moonshot's direct pricing page today; OpenRouter# passes through $0.44/$2.00 for K2.5 and $0.7448/$4.655 for K2.6.LlmModel.KIMI_K2_5: TokenRate(input=66, output=300),diff --git a/autogpt_platform/backend/backend/data/credit_test.py b/autogpt_platform/backend/backend/data/credit_test.pyindex 5f38be4cc0..1981f33916 100644--- a/autogpt_platform/backend/backend/data/credit_test.py+++ b/autogpt_platform/backend/backend/data/credit_test.py@@ -74,7 +74,7 @@ async def test_block_credit_usage(server: SpinTestServer):node_exec_id="test_node_exec",block_id=AITextGeneratorBlock().id,inputs={- "model": "gpt-4-turbo",+ "model": "gpt-4o","credentials": {"id": openai_credentials.id,"provider": openai_credentials.provider,@@ -95,7 +95,7 @@ async def test_block_credit_usage(server: SpinTestServer):graph_exec_id="test_graph_exec",node_exec_id="test_node_exec",block_id=AITextGeneratorBlock().id,- inputs={"model": "gpt-4-turbo", "api_key": "owned_api_key"},+ inputs={"model": "gpt-4o", "api_key": "owned_api_key"},execution_context=ExecutionContext(user_timezone="UTC"),),)diff --git a/autogpt_platform/backend/backend/data/graph.py b/autogpt_platform/backend/backend/data/graph.pyindex 54ba198936..4ce30059c3 100644--- a/autogpt_platform/backend/backend/data/graph.py+++ b/autogpt_platform/backend/backend/data/graph.py@@ -27,7 +27,7 @@ from backend.blocks import get_block, get_blocksfrom backend.blocks._base import Block, BlockType, EmptySchemafrom backend.blocks.agent import AgentExecutorBlockfrom backend.blocks.io import AgentInputBlock, AgentOutputBlock-from backend.blocks.llm import LlmModel+from backend.blocks.llm import LEGACY_MODEL_MAPPINGS, LlmModelfrom backend.integrations.providers import ProviderNamefrom backend.util import type as type_utilsfrom backend.util.exceptions import GraphNotAccessibleError, GraphNotInLibraryError@@ -1828,49 +1828,127 @@ async def fix_llm_provider_credentials():)-async def migrate_llm_models(migrate_to: LlmModel):- """- Update all LLM models in all AI blocks that don't exist in the enum.- Note: Only updates top level LlmModel SchemaFields of blocks (won't update nested fields).+def _legacy_value_aliases(legacy_value: str, replacement: LlmModel) -> set[str]:+ """Stored-value forms that should map to ``replacement`` for one legacy slug.++ ``LlmModel._missing_`` accepts provider-prefixed inputs at write time, so+ historical rows may carry either the bare slug or ``<provider>/<slug>``+ even when the canonical enum value is unprefixed. Vendor-prefixed legacy+ values (e.g. ``google/...``) need no alias."""- logger.info("Migrating LLM models")- # Scan all blocks and search for LlmModel fields- llm_model_fields: dict[str, str] = {} # {block_id: field_name}+ if "/" in legacy_value:+ return {legacy_value}+ return {legacy_value, f"{replacement.metadata.provider}/{legacy_value}"}- # Search for all LlmModel fields- for block_type in get_blocks().values():- block = block_type()- from pydantic.fields import FieldInfo- fields: dict[str, FieldInfo] = block.input_schema.model_fields+async def migrate_llm_models(fallback: LlmModel):+ """+ Rewrite legacy LLM model values to in-enum equivalents.++ Runs in two passes per LlmModel field:+ 1. Family-aware: for each (legacy_value, replacement) in+ LEGACY_MODEL_MAPPINGS, rewrite that exact legacy value to its mapped+ replacement so e.g. Claude Opus lands on a newer Opus, not the global+ GPT default.+ 2. Catch-all: any value still out-of-enum gets ``fallback``.++ Both passes run against two tables:+ * ``AgentNode.constantInput`` — saved graph definitions (scoped by+ ``agentBlockId`` because we know the LlmModel field name per block).+ * ``AgentNodeExecutionInputOutput.data`` where ``agentPresetId`` is set —+ preset input overrides; scoped only by the field-value match since+ preset rows don't carry the block id.- # Collect top-level LlmModel fields- for field_name, field in fields.items():- if field.annotation == LlmModel:- llm_model_fields[block.id] = field_name+ Note: Only updates top level LlmModel SchemaFields of blocks (won't update nested fields).+ """+ logger.info("Migrating LLM models")+ llm_model_fields = _find_llm_model_fields()+ if not llm_model_fields:+ return- # Convert enum values to a list of strings for the SQL queryenum_values = [v.value for v in LlmModel]escaped_enum_values = repr(tuple(enum_values)) # hack but works- # Update each block- for id, path in llm_model_fields.items():- query = f"""- UPDATE {{schema_prefix}}"AgentNode"- SET "constantInput" = jsonb_set("constantInput", $1, to_jsonb($2), true)- WHERE "agentBlockId" = $3- AND "constantInput" ? ($4)::text- AND "constantInput"->>($4)::text NOT IN {escaped_enum_values}- """+ node_targeted_query = """+ UPDATE {schema_prefix}"AgentNode"+ SET "constantInput" = jsonb_set("constantInput", $1, to_jsonb($2), true)+ WHERE "agentBlockId" = $3+ AND "constantInput" ? ($4)::text+ AND "constantInput"->>($4)::text = $5+ """+ node_fallback_query = f"""+ UPDATE {{schema_prefix}}"AgentNode"+ SET "constantInput" = jsonb_set("constantInput", $1, to_jsonb($2), true)+ WHERE "agentBlockId" = $3+ AND "constantInput" ? ($4)::text+ AND "constantInput"->>($4)::text NOT IN {escaped_enum_values}+ """+ preset_targeted_query = """+ UPDATE {schema_prefix}"AgentNodeExecutionInputOutput"+ SET "data" = jsonb_set("data"::jsonb, $1, to_jsonb($2), true)+ WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb ? ($3)::text+ AND "data"::jsonb->>($3)::text = $4+ """+ preset_fallback_query = f"""+ UPDATE {{schema_prefix}}"AgentNodeExecutionInputOutput"+ SET "data" = jsonb_set("data"::jsonb, $1, to_jsonb($2), true)+ WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb ? ($3)::text+ AND "data"::jsonb->>($3)::text NOT IN {escaped_enum_values}+ """+ # AgentNode pass — per (block_id, field_name).+ for block_id, path in llm_model_fields.items():+ for legacy_value, replacement in LEGACY_MODEL_MAPPINGS.items():+ for stored_value in _legacy_value_aliases(legacy_value, replacement):+ await execute_raw_with_schema(+ node_targeted_query,+ [path],+ replacement.value,+ block_id,+ path,+ stored_value,+ )await execute_raw_with_schema(- query,+ node_fallback_query,[path],- migrate_to.value,- id,+ fallback.value,+ block_id,path,)+ # AgentPreset pass — per unique field name. Preset rows don't carry+ # ``agentBlockId``, but the field-value match is tight enough on its own+ # because no non-LLM block stores one of our retired slugs.+ for path in set(llm_model_fields.values()):+ for legacy_value, replacement in LEGACY_MODEL_MAPPINGS.items():+ for stored_value in _legacy_value_aliases(legacy_value, replacement):+ await execute_raw_with_schema(+ preset_targeted_query,+ [path],+ replacement.value,+ path,+ stored_value,+ )+ await execute_raw_with_schema(+ preset_fallback_query,+ [path],+ fallback.value,+ path,+ )+++def _find_llm_model_fields() -> dict[str, str]:+ """Return ``{block_id: field_name}`` for every top-level LlmModel field."""+ llm_model_fields: dict[str, str] = {}+ for block_type in get_blocks().values():+ block = block_type()+ for field_name, field in block.input_schema.model_fields.items():+ if field.annotation == LlmModel:+ llm_model_fields[block.id] = field_name+ return llm_model_fields+# Simple placeholder class for deleted/missing blocksclass _UnknownBlockBase(Block):diff --git a/autogpt_platform/backend/backend/data/graph_test.py b/autogpt_platform/backend/backend/data/graph_test.pyindex 9d10ed16e2..db65647af0 100644--- a/autogpt_platform/backend/backend/data/graph_test.py+++ b/autogpt_platform/backend/backend/data/graph_test.py@@ -13,12 +13,14 @@ from backend.api.model import CreateGraphfrom backend.blocks._base import BlockSchema, BlockSchemaInputfrom backend.blocks.basic import StoreValueBlockfrom backend.blocks.io import AgentInputBlock, AgentOutputBlock+from backend.blocks.llm import LEGACY_MODEL_MAPPINGS, LlmModelfrom backend.data.graph import (Graph,GraphModel,Link,Node,get_graph,+ migrate_llm_models,validate_graph_execution_permissions,)from backend.data.model import SchemaField@@ -2182,9 +2184,6 @@ async def test_migrate_llm_models_uses_schema_prefix_placeholder():so environments where the Prisma datasource lands in `public` (no?schema=platform on DATABASE_URL) don't blow up with`relation "platform.AgentNode" does not exist`."""- from backend.blocks.llm import LlmModel- from backend.data.graph import migrate_llm_models-with patch("backend.data.graph.execute_raw_with_schema",new_callable=AsyncMock,@@ -2199,3 +2198,63 @@ async def test_migrate_llm_models_uses_schema_prefix_placeholder():"DATABASE_URL has no ?schema= param.")assert 'platform."AgentNode"' not in query_template+++async def test_migrate_llm_models_matches_provider_prefixed_legacy_values():+ """Regression: migrate_llm_models must rewrite provider-prefixed stored+ values (e.g. ``anthropic/claude-sonnet-4-20250514``) to the family-aware+ replacement, not let them fall through to the global ``fallback`` model.++ ``LlmModel._missing_`` accepts prefixed inputs at write time, so historical+ rows may carry either the bare or prefixed form."""+ bare_legacy_value = "claude-sonnet-4-20250514"+ expected_replacement = LEGACY_MODEL_MAPPINGS[bare_legacy_value].value+ prefixed_legacy_value = f"anthropic/{bare_legacy_value}"++ with patch(+ "backend.data.graph.execute_raw_with_schema",+ new_callable=AsyncMock,+ ) as mock_execute:+ await migrate_llm_models(next(iter(LlmModel)))++ # Targeted query has 5 SQL params ($1..$5), so its call has 6 positional+ # args: (query, [path], replacement, block_id, path, stored_value).+ targeted_pairs = {+ (call.args[2], call.args[5]) # (replacement, stored_value)+ for call in mock_execute.await_args_list+ if len(call.args) == 6+ }++ assert (expected_replacement, bare_legacy_value) in targeted_pairs, (+ f"bare legacy slug {bare_legacy_value!r} not rewritten to "+ f"{expected_replacement!r}"+ )+ assert (expected_replacement, prefixed_legacy_value) in targeted_pairs, (+ f"provider-prefixed legacy slug {prefixed_legacy_value!r} not "+ f"rewritten to {expected_replacement!r} — prefixed forms must hit the "+ "family-aware pass, not the global fallback."+ )+++async def test_migrate_llm_models_covers_preset_overrides():+ """Regression: migrate_llm_models must also rewrite legacy values stored+ in ``AgentNodeExecutionInputOutput.data`` for preset overrides. The SQL+ migration handles that table, but the boot-time safety net used to skip+ it — leaving stale model values in presets when the SQL migration hadn't+ yet run."""+ with patch(+ "backend.data.graph.execute_raw_with_schema",+ new_callable=AsyncMock,+ ) as mock_execute:+ await migrate_llm_models(next(iter(LlmModel)))++ queries = [call.args[0] for call in mock_execute.await_args_list]+ assert any(+ '"AgentNodeExecutionInputOutput"' in q and '"agentPresetId" IS NOT NULL' in q+ for q in queries+ ), (+ "migrate_llm_models must run UPDATEs against AgentNodeExecutionInputOutput "+ "for preset rows, not just AgentNode.constantInput."+ )diff --git a/autogpt_platform/backend/backend/util/prompt_test.py b/autogpt_platform/backend/backend/util/prompt_test.pyindex 0c39f329c6..9461dbb944 100644--- a/autogpt_platform/backend/backend/util/prompt_test.py+++ b/autogpt_platform/backend/backend/util/prompt_test.py@@ -981,10 +981,10 @@ class TestCompressResultDataclass:class TestGetContextWindow:def test_claude_opus(self) -> None:- assert get_context_window("claude-opus-4-20250514") == 200_000+ assert get_context_window("claude-opus-4-7") == 200_000def test_claude_sonnet(self) -> None:- assert get_context_window("claude-sonnet-4-20250514") == 200_000+ assert get_context_window("claude-sonnet-4-6") == 200_000def test_openrouter_prefix(self) -> None:assert get_context_window("anthropic/claude-opus-4-6") == 200_000diff --git a/autogpt_platform/backend/migrations/20260512120000_retire_deprecated_llm_models/migration.sql b/autogpt_platform/backend/migrations/20260512120000_retire_deprecated_llm_models/migration.sqlnew file mode 100644index 0000000000..953f534646--- /dev/null+++ b/autogpt_platform/backend/migrations/20260512120000_retire_deprecated_llm_models/migration.sql@@ -0,0 +1,498 @@+-- Retire deprecated LLM models with family-aware migration.+--+-- Each block updates two tables:+-- * "AgentNode"."constantInput" — saved graph definitions.+-- * "AgentNodeExecutionInputOutput"."data" where "agentPresetId" IS NOT NULL —+-- preset overrides.+--+-- Mappings are family-aware: Claude Opus → newer Opus, Claude Sonnet → newer+-- Sonnet, Gemini Flash → newer Flash, etc. The boot-time safety net+-- (`migrate_llm_models` in backend/data/graph.py) applies the same mapping so+-- environments stay consistent even before this migration runs.+--+-- For bare Anthropic/OpenAI slugs we also match the provider-prefixed form+-- (e.g. `anthropic/claude-sonnet-4-20250514`) because `LlmModel._missing_`+-- accepts prefixed inputs at write time, so historical rows may carry either+-- form.+--+-- AI/ML API stragglers (Qwen/Qwen2.5-72B-Instruct-Turbo,+-- nvidia/llama-3.1-nemotron-70b-instruct,+-- meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo,+-- meta-llama/Llama-3.2-3B-Instruct-Turbo) have no direct same-family successor+-- on AI/ML's current catalogue, so they all map to+-- meta-llama/Llama-3.3-70B-Instruct-Turbo, which AI/ML still serves and is the+-- closest open-weight Meta/Llama generation.++-- claude-3-haiku-20240307 -> claude-haiku-4-5-20251001+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"claude-haiku-4-5-20251001"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' IN (+ 'claude-3-haiku-20240307',+ 'anthropic/claude-3-haiku-20240307'+ );++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"claude-haiku-4-5-20251001"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' IN (+ 'claude-3-haiku-20240307',+ 'anthropic/claude-3-haiku-20240307'+ );++-- claude-opus-4-20250514 -> claude-opus-4-7+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"claude-opus-4-7"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' IN (+ 'claude-opus-4-20250514',+ 'anthropic/claude-opus-4-20250514'+ );++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"claude-opus-4-7"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' IN (+ 'claude-opus-4-20250514',+ 'anthropic/claude-opus-4-20250514'+ );++-- claude-sonnet-4-20250514 -> claude-sonnet-4-6+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"claude-sonnet-4-6"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' IN (+ 'claude-sonnet-4-20250514',+ 'anthropic/claude-sonnet-4-20250514'+ );++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"claude-sonnet-4-6"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' IN (+ 'claude-sonnet-4-20250514',+ 'anthropic/claude-sonnet-4-20250514'+ );++-- claude-opus-4-1-20250805 -> claude-opus-4-7+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"claude-opus-4-7"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' IN (+ 'claude-opus-4-1-20250805',+ 'anthropic/claude-opus-4-1-20250805'+ );++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"claude-opus-4-7"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' IN (+ 'claude-opus-4-1-20250805',+ 'anthropic/claude-opus-4-1-20250805'+ );++-- gpt-4-turbo -> gpt-4.1-2025-04-14+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"gpt-4.1-2025-04-14"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' IN (+ 'gpt-4-turbo',+ 'openai/gpt-4-turbo'+ );++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"gpt-4.1-2025-04-14"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' IN (+ 'gpt-4-turbo',+ 'openai/gpt-4-turbo'+ );++-- o1 -> o3-2025-04-16+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"o3-2025-04-16"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' IN (+ 'o1',+ 'openai/o1'+ );++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"o3-2025-04-16"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' IN (+ 'o1',+ 'openai/o1'+ );++-- o1-mini -> o3-mini+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"o3-mini"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' IN (+ 'o1-mini',+ 'openai/o1-mini'+ );++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"o3-mini"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' IN (+ 'o1-mini',+ 'openai/o1-mini'+ );++-- google/gemini-2.5-pro-preview-03-25 -> google/gemini-2.5-pro+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"google/gemini-2.5-pro"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'google/gemini-2.5-pro-preview-03-25';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"google/gemini-2.5-pro"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'google/gemini-2.5-pro-preview-03-25';++-- google/gemini-2.5-flash-lite-preview-06-17 -> google/gemini-2.5-flash+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"google/gemini-2.5-flash"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'google/gemini-2.5-flash-lite-preview-06-17';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"google/gemini-2.5-flash"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'google/gemini-2.5-flash-lite-preview-06-17';++-- cohere/command-r-08-2024 -> cohere/command-a-03-2025+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"cohere/command-a-03-2025"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'cohere/command-r-08-2024';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"cohere/command-a-03-2025"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'cohere/command-r-08-2024';++-- cohere/command-r-plus-08-2024 -> cohere/command-a-03-2025+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"cohere/command-a-03-2025"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'cohere/command-r-plus-08-2024';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"cohere/command-a-03-2025"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'cohere/command-r-plus-08-2024';++-- mistralai/mistral-nemo -> mistralai/mistral-small-3.2-24b-instruct+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"mistralai/mistral-small-3.2-24b-instruct"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'mistralai/mistral-nemo';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"mistralai/mistral-small-3.2-24b-instruct"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'mistralai/mistral-nemo';++-- microsoft/wizardlm-2-8x22b -> microsoft/phi-4+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"microsoft/phi-4"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'microsoft/wizardlm-2-8x22b';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"microsoft/phi-4"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'microsoft/wizardlm-2-8x22b';++-- moonshotai/kimi-k2 -> moonshotai/kimi-k2.6+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"moonshotai/kimi-k2.6"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'moonshotai/kimi-k2';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"moonshotai/kimi-k2.6"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'moonshotai/kimi-k2';++-- moonshotai/kimi-k2-0905 -> moonshotai/kimi-k2.6+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"moonshotai/kimi-k2.6"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'moonshotai/kimi-k2-0905';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"moonshotai/kimi-k2.6"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'moonshotai/kimi-k2-0905';++-- z-ai/glm-4-32b -> z-ai/glm-4.6+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"z-ai/glm-4.6"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'z-ai/glm-4-32b';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"z-ai/glm-4.6"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'z-ai/glm-4-32b';++-- z-ai/glm-4.5 -> z-ai/glm-4.6+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"z-ai/glm-4.6"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'z-ai/glm-4.5';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"z-ai/glm-4.6"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'z-ai/glm-4.5';++-- z-ai/glm-4.5-air -> z-ai/glm-4.7-flash+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"z-ai/glm-4.7-flash"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'z-ai/glm-4.5-air';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"z-ai/glm-4.7-flash"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'z-ai/glm-4.5-air';++-- z-ai/glm-4.5-air:free -> z-ai/glm-4.7-flash+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"z-ai/glm-4.7-flash"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'z-ai/glm-4.5-air:free';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"z-ai/glm-4.7-flash"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'z-ai/glm-4.5-air:free';++-- z-ai/glm-4.5v -> z-ai/glm-4.6v+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"z-ai/glm-4.6v"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'z-ai/glm-4.5v';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"z-ai/glm-4.6v"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'z-ai/glm-4.5v';++-- Qwen/Qwen2.5-72B-Instruct-Turbo -> meta-llama/Llama-3.3-70B-Instruct-Turbo+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"meta-llama/Llama-3.3-70B-Instruct-Turbo"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'Qwen/Qwen2.5-72B-Instruct-Turbo';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"meta-llama/Llama-3.3-70B-Instruct-Turbo"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'Qwen/Qwen2.5-72B-Instruct-Turbo';++-- nvidia/llama-3.1-nemotron-70b-instruct -> meta-llama/Llama-3.3-70B-Instruct-Turbo+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"meta-llama/Llama-3.3-70B-Instruct-Turbo"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'nvidia/llama-3.1-nemotron-70b-instruct';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"meta-llama/Llama-3.3-70B-Instruct-Turbo"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'nvidia/llama-3.1-nemotron-70b-instruct';++-- meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo -> meta-llama/Llama-3.3-70B-Instruct-Turbo+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"meta-llama/Llama-3.3-70B-Instruct-Turbo"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"meta-llama/Llama-3.3-70B-Instruct-Turbo"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo';++-- meta-llama/Llama-3.2-3B-Instruct-Turbo -> meta-llama/Llama-3.3-70B-Instruct-Turbo+UPDATE "AgentNode"+SET "constantInput" = JSONB_SET(+ "constantInput"::jsonb,+ '{model}',+ '"meta-llama/Llama-3.3-70B-Instruct-Turbo"'::jsonb+ )+WHERE "constantInput"::jsonb->>'model' = 'meta-llama/Llama-3.2-3B-Instruct-Turbo';++UPDATE "AgentNodeExecutionInputOutput"+SET "data" = JSONB_SET(+ "data"::jsonb,+ '{model}',+ '"meta-llama/Llama-3.3-70B-Instruct-Turbo"'::jsonb+ )+WHERE "agentPresetId" IS NOT NULL+ AND "data"::jsonb->>'model' = 'meta-llama/Llama-3.2-3B-Instruct-Turbo';diff --git a/docs/integrations/block-integrations/llm.md b/docs/integrations/block-integrations/llm.mdindex 741da79631..0f5070bc7e 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" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "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/wizardlm-2-8x22b" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "moonshotai/kimi-k2-0905" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4-32b" \| "z-ai/glm-4.5" \| "z-ai/glm-4.5-air" \| "z-ai/glm-4.5-air:free" \| "z-ai/glm-4.5v" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |+| model | The language model to use for evaluating the condition. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |### Outputs@@ -103,7 +103,7 @@ The block sends the entire conversation history to the chosen LLM, including sys|-------|-------------|------|----------|| prompt | The prompt to send to the language model. | str | No || messages | List of messages in the conversation. | List[Any] | Yes |-| model | The language model to use for the conversation. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "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/wizardlm-2-8x22b" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "moonshotai/kimi-k2-0905" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4-32b" \| "z-ai/glm-4.5" \| "z-ai/glm-4.5-air" \| "z-ai/glm-4.5-air:free" \| "z-ai/glm-4.5v" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |+| model | The language model to use for the conversation. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No || max_tokens | The maximum number of tokens to generate in the chat completion. | int | No || ollama_host | Ollama host for local models | str | No |@@ -257,7 +257,7 @@ The block formulates a prompt based on the given focus or source data, sends it|-------|-------------|------|----------|| focus | The focus of the list to generate. | str | No || source_data | The data to generate the list from. | str | No |-| model | The language model to use for generating the list. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "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/wizardlm-2-8x22b" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "moonshotai/kimi-k2-0905" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4-32b" \| "z-ai/glm-4.5" \| "z-ai/glm-4.5-air" \| "z-ai/glm-4.5-air:free" \| "z-ai/glm-4.5v" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |+| model | The language model to use for generating the list. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No || max_retries | Maximum number of retries for generating a valid list. | int | No || force_json_output | Whether to force the LLM to produce a JSON-only response. This can increase the block's reliability, but may also reduce the quality of the response because it prohibits the LLM from reasoning before providing its JSON response. | bool | No || max_tokens | The maximum number of tokens to generate in the chat completion. | int | No |@@ -424,7 +424,7 @@ The block sends the input prompt to a chosen LLM, along with any system prompts| prompt | The prompt to send to the language model. | str | Yes || expected_format | Expected format of the response. If provided, the response will be validated against this format. The keys should be the expected fields in the response, and the values should be the description of the field. | Dict[str, str] | Yes || list_result | Whether the response should be a list of objects in the expected format. | bool | No |-| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "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/wizardlm-2-8x22b" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "moonshotai/kimi-k2-0905" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4-32b" \| "z-ai/glm-4.5" \| "z-ai/glm-4.5-air" \| "z-ai/glm-4.5-air:free" \| "z-ai/glm-4.5v" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |+| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No || force_json_output | Whether to force the LLM to produce a JSON-only response. This can increase the block's reliability, but may also reduce the quality of the response because it prohibits the LLM from reasoning before providing its JSON response. | bool | No || sys_prompt | The system prompt to provide additional context to the model. | str | No || conversation_history | The conversation history to provide context for the prompt. | List[Dict[str, Any]] | No |@@ -464,7 +464,7 @@ The block sends the input prompt to a chosen LLM, processes the response, and re| Input | Description | Type | Required ||-------|-------------|------|----------|| prompt | The prompt to send to the language model. You can use any of the {keys} from Prompt Values to fill in the prompt with values from the prompt values dictionary by putting them in curly braces. | str | Yes |-| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "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/wizardlm-2-8x22b" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "moonshotai/kimi-k2-0905" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4-32b" \| "z-ai/glm-4.5" \| "z-ai/glm-4.5-air" \| "z-ai/glm-4.5-air:free" \| "z-ai/glm-4.5v" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |+| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No || sys_prompt | The system prompt to provide additional context to the model. | str | No || retry | Number of times to retry the LLM call if the response does not match the expected format. | int | No || prompt_values | Values used to fill in the prompt. The values can be used in the prompt by putting them in a double curly braces, e.g. {{variable_name}}. | Dict[str, str] | No |@@ -501,7 +501,7 @@ The block splits the input text into smaller chunks, sends each chunk to an LLM| Input | Description | Type | Required ||-------|-------------|------|----------|| text | The text to summarize. | str | Yes |-| model | The language model to use for summarizing the text. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "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/wizardlm-2-8x22b" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "moonshotai/kimi-k2-0905" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4-32b" \| "z-ai/glm-4.5" \| "z-ai/glm-4.5-air" \| "z-ai/glm-4.5-air:free" \| "z-ai/glm-4.5v" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |+| model | The language model to use for summarizing the text. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No || focus | The topic to focus on in the summary | str | No || style | The style of the summary to generate. | "concise" \| "detailed" \| "bullet points" \| "numbered list" | No || max_tokens | The maximum number of tokens to generate in the chat completion. | int | No |@@ -721,7 +721,7 @@ _Add technical explanation here._| Input | Description | Type | Required ||-------|-------------|------|----------|| prompt | The prompt to send to the language model. | str | Yes |-| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "o1" \| "o1-mini" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "gpt-4-turbo" \| "claude-opus-4-1-20250805" \| "claude-opus-4-20250514" \| "claude-sonnet-4-20250514" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "claude-3-haiku-20240307" \| "Qwen/Qwen2.5-72B-Instruct-Turbo" \| "nvidia/llama-3.1-nemotron-70b-instruct" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "meta-llama/Meta-Llama-3.1-70B-Instruct-Turbo" \| "meta-llama/Llama-3.2-3B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro-preview-03-25" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.5-flash-lite-preview-06-17" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-nemo" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-r-08-2024" \| "cohere/command-r-plus-08-2024" \| "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/wizardlm-2-8x22b" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2" \| "moonshotai/kimi-k2-0905" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4-32b" \| "z-ai/glm-4.5" \| "z-ai/glm-4.5-air" \| "z-ai/glm-4.5-air:free" \| "z-ai/glm-4.5v" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |+| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-sonnet-4-6" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-2.0-flash-lite-001" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No || multiple_tool_calls | Whether to allow multiple tool calls in a single response. | bool | No || sys_prompt | The system prompt to provide additional context to the model. | str | No || conversation_history | The conversation history to provide context for the prompt. | List[Dict[str, Any]] | No |