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): add Claude Sonnet 5.5 and default the standard tier to it (#15014)
Nicholas Tindlecfcf273de79d
diff --git a/autogpt_platform/backend/.env.default b/autogpt_platform/backend/.env.defaultindex 3fa9179b24..c384361a6f 100644--- a/autogpt_platform/backend/.env.default+++ b/autogpt_platform/backend/.env.default@@ -411,7 +411,7 @@ RMFG_API_KEY=# Greeting generation for the copilot home after onboarding. The prompt is# managed in Langfuse under BRAIN_DUMP_GREETING_PROMPT_NAME when Langfuse# credentials are configured; otherwise a built-in prompt is used.-# BRAIN_DUMP_GREETING_MODEL=anthropic/claude-sonnet-5+# BRAIN_DUMP_GREETING_MODEL=anthropic/claude-sonnet-5-5# BRAIN_DUMP_GREETING_PROMPT_NAME=Brain Dump Greeting# Model that picks which integrations to suggest in the welcome dialog'sdiff --git a/autogpt_platform/backend/backend/api/features/onboarding_dump/intro.py b/autogpt_platform/backend/backend/api/features/onboarding_dump/intro.pyindex e4a8039eec..ee05270683 100644--- a/autogpt_platform/backend/backend/api/features/onboarding_dump/intro.py+++ b/autogpt_platform/backend/backend/api/features/onboarding_dump/intro.py@@ -28,7 +28,7 @@ logger = logging.getLogger(__name__)settings = Settings()-_MODEL = os.environ.get("BRAIN_DUMP_GREETING_MODEL", "anthropic/claude-sonnet-5")+_MODEL = os.environ.get("BRAIN_DUMP_GREETING_MODEL", "anthropic/claude-sonnet-5-5")_TIMEOUT_SECONDS = 30# The Langfuse copy of these instructions wins whenever it is reachable,diff --git a/autogpt_platform/backend/backend/blocks/test/test_llm.py b/autogpt_platform/backend/backend/blocks/test/test_llm.pyindex a81ee6bff7..b2c2440515 100644--- a/autogpt_platform/backend/backend/blocks/test/test_llm.py+++ b/autogpt_platform/backend/backend/blocks/test/test_llm.py@@ -1886,6 +1886,16 @@ class TestLLMModelMissingHandler:assert llm.LLMModel("anthropic/claude-opus-4-7") is llm.LLMModel.CLAUDE_4_7_OPUSassert llm.LLMModel("anthropic/claude-opus-4-6") is llm.LLMModel.CLAUDE_4_6_OPUS+ def test_dot_versioned_point_release_resolves(self) -> None:+ # OpenRouter serves the point releases under dot-versioned slugs+ # (``anthropic/claude-sonnet-5.5``) while the enum value hyphenates+ # them; ``_missing_``'s prefix strip alone can't bridge that, so the+ # alias map carries the dotted form.+ assert (+ llm.LLMModel("anthropic/claude-sonnet-5.5")+ is llm.LLMModel.CLAUDE_5_5_SONNET+ )+def test_unknown_slug_raises(self) -> None:# Bare unknown strings still fail loudly — the alias map is an# additive shortcut, not a silent catch-all.diff --git a/autogpt_platform/backend/backend/copilot/anthropic_rate_card_test.py b/autogpt_platform/backend/backend/copilot/anthropic_rate_card_test.pyindex 5f79e1c120..1b96114c33 100644--- a/autogpt_platform/backend/backend/copilot/anthropic_rate_card_test.py+++ b/autogpt_platform/backend/backend/copilot/anthropic_rate_card_test.py@@ -188,6 +188,37 @@ class TestSonnet5Rates:assert cost == 12.0+class TestSonnet5_5Rates:+ """Sonnet 5.5 is the default standard-tier model, so a missing rate-card+ entry is the expensive failure: direct-Anthropic deployments would cap+ output at the 32K fallback and bill at the Opus fallback (~7.5x)."""++ def test_sonnet_5_5_max_output_from_rate_card(self):+ assert get_max_output_tokens("claude-sonnet-5-5") == 128000++ def test_sonnet_5_5_billed_at_published_rates_without_fallback(self, caplog):+ cost = compute_anthropic_cost_usd(+ model="claude-sonnet-5-5",+ prompt_tokens=1_000_000,+ completion_tokens=1_000_000,+ )+ # Sticker $2/$10 per 1M — the Opus fallback would charge $90.+ assert cost == 12.0+ assert "falling back" not in caplog.text++ @pytest.mark.parametrize("cache_ttl, expected_cost", [("5m", 2.7), ("1h", 4.2)])+ def test_sonnet_5_5_cache_rates(self, cache_ttl, expected_cost):+ cost = compute_anthropic_cost_usd(+ model="claude-sonnet-5-5",+ prompt_tokens=2_000_000,+ completion_tokens=0,+ cache_read_tokens=1_000_000,+ cache_creation_tokens=1_000_000,+ cache_ttl=cache_ttl,+ )+ assert cost == expected_cost++class TestOpus5Rates:"""Opus 5 direct-mode costs must use published rates, not the 3x fallback."""diff --git a/autogpt_platform/backend/backend/copilot/anthropic_rates.json b/autogpt_platform/backend/backend/copilot/anthropic_rates.jsonindex abdb190d7b..1aeb954698 100644--- a/autogpt_platform/backend/backend/copilot/anthropic_rates.json+++ b/autogpt_platform/backend/backend/copilot/anthropic_rates.json@@ -5,14 +5,18 @@"claude-fable-5": {"cache_creation_input_token_cost": 1.25e-05,"cache_creation_input_token_cost_above_1hr": 2e-05,+ "cache_creation_input_token_cost_batches": 6.25e-06,"cache_read_input_token_cost": 1e-06,+ "cache_read_input_token_cost_batches": 5e-07,"input_cost_per_token": 1e-05,+ "input_cost_per_token_batches": 5e-06,"litellm_provider": "anthropic","max_input_tokens": 1000000,"max_output_tokens": 128000,"max_tokens": 128000,"mode": "chat","output_cost_per_token": 5e-05,+ "output_cost_per_token_batches": 2.5e-05,"prompt_cache_min_tokens": 512,"provider_specific_entry": {"us": 1.1@@ -45,14 +49,18 @@"claude-fable-5-1": {"cache_creation_input_token_cost": 1.25e-05,"cache_creation_input_token_cost_above_1hr": 2e-05,+ "cache_creation_input_token_cost_batches": 6.25e-06,"cache_read_input_token_cost": 2.5e-07,+ "cache_read_input_token_cost_batches": 1.25e-07,"input_cost_per_token": 1e-05,+ "input_cost_per_token_batches": 5e-06,"litellm_provider": "anthropic","max_input_tokens": 1000000,"max_output_tokens": 128000,"max_tokens": 128000,"mode": "chat","output_cost_per_token": 5e-05,+ "output_cost_per_token_batches": 2.5e-05,"prompt_cache_min_tokens": 512,"provider_specific_entry": {"us": 1.1@@ -86,14 +94,18 @@"claude-haiku-4-5": {"cache_creation_input_token_cost": 1.25e-06,"cache_creation_input_token_cost_above_1hr": 2e-06,+ "cache_creation_input_token_cost_batches": 6.25e-07,"cache_read_input_token_cost": 1e-07,+ "cache_read_input_token_cost_batches": 5e-08,"input_cost_per_token": 1e-06,+ "input_cost_per_token_batches": 5e-07,"litellm_provider": "anthropic","max_input_tokens": 200000,"max_output_tokens": 64000,"max_tokens": 64000,"mode": "chat","output_cost_per_token": 5e-06,+ "output_cost_per_token_batches": 2.5e-06,"prompt_cache_min_tokens": 4096,"source": "https://platform.claude.com/docs/en/about-claude/pricing","supports_assistant_prefill": true,@@ -110,14 +122,18 @@"claude-haiku-4-5-20251001": {"cache_creation_input_token_cost": 1.25e-06,"cache_creation_input_token_cost_above_1hr": 2e-06,+ "cache_creation_input_token_cost_batches": 6.25e-07,"cache_read_input_token_cost": 1e-07,+ "cache_read_input_token_cost_batches": 5e-08,"input_cost_per_token": 1e-06,+ "input_cost_per_token_batches": 5e-07,"litellm_provider": "anthropic","max_input_tokens": 200000,"max_output_tokens": 64000,"max_tokens": 64000,"mode": "chat","output_cost_per_token": 5e-06,+ "output_cost_per_token_batches": 2.5e-06,"prompt_cache_min_tokens": 4096,"supports_assistant_prefill": true,"supports_computer_use": true,@@ -133,14 +149,18 @@"claude-mythos-5": {"cache_creation_input_token_cost": 1.25e-05,"cache_creation_input_token_cost_above_1hr": 2e-05,+ "cache_creation_input_token_cost_batches": 6.25e-06,"cache_read_input_token_cost": 1e-06,+ "cache_read_input_token_cost_batches": 5e-07,"input_cost_per_token": 1e-05,+ "input_cost_per_token_batches": 5e-06,"litellm_provider": "anthropic","max_input_tokens": 1000000,"max_output_tokens": 128000,"max_tokens": 128000,"mode": "chat","output_cost_per_token": 5e-05,+ "output_cost_per_token_batches": 2.5e-05,"prompt_cache_min_tokens": 512,"provider_specific_entry": {"us": 1.1@@ -173,14 +193,18 @@"claude-mythos-5-1": {"cache_creation_input_token_cost": 1.25e-05,"cache_creation_input_token_cost_above_1hr": 2e-05,+ "cache_creation_input_token_cost_batches": 6.25e-06,"cache_read_input_token_cost": 2.5e-07,+ "cache_read_input_token_cost_batches": 1.25e-07,"input_cost_per_token": 1e-05,+ "input_cost_per_token_batches": 5e-06,"litellm_provider": "anthropic","max_input_tokens": 1000000,"max_output_tokens": 128000,"max_tokens": 128000,"mode": "chat","output_cost_per_token": 5e-05,+ "output_cost_per_token_batches": 2.5e-05,"prompt_cache_min_tokens": 512,"provider_specific_entry": {"us": 1.1@@ -254,14 +278,18 @@"claude-opus-4-5": {"cache_creation_input_token_cost": 6.25e-06,"cache_creation_input_token_cost_above_1hr": 1e-05,+ "cache_creation_input_token_cost_batches": 3.125e-06,"cache_read_input_token_cost": 5e-07,+ "cache_read_input_token_cost_batches": 2.5e-07,"input_cost_per_token": 5e-06,+ "input_cost_per_token_batches": 2.5e-06,"litellm_provider": "anthropic","max_input_tokens": 200000,"max_output_tokens": 64000,"max_tokens": 64000,"mode": "chat","output_cost_per_token": 2.5e-05,+ "output_cost_per_token_batches": 1.25e-05,"prompt_cache_min_tokens": 4096,"search_context_cost_per_query": {"search_context_size_high": 0.01,@@ -285,14 +313,18 @@"claude-opus-4-5-20251101": {"cache_creation_input_token_cost": 6.25e-06,"cache_creation_input_token_cost_above_1hr": 1e-05,+ "cache_creation_input_token_cost_batches": 3.125e-06,"cache_read_input_token_cost": 5e-07,+ "cache_read_input_token_cost_batches": 2.5e-07,"input_cost_per_token": 5e-06,+ "input_cost_per_token_batches": 2.5e-06,"litellm_provider": "anthropic","max_input_tokens": 200000,"max_output_tokens": 64000,"max_tokens": 64000,"mode": "chat","output_cost_per_token": 2.5e-05,+ "output_cost_per_token_batches": 1.25e-05,"prompt_cache_min_tokens": 4096,"search_context_cost_per_query": {"search_context_size_high": 0.01,@@ -315,14 +347,18 @@"claude-opus-4-6": {"cache_creation_input_token_cost": 6.25e-06,"cache_creation_input_token_cost_above_1hr": 1e-05,+ "cache_creation_input_token_cost_batches": 3.125e-06,"cache_read_input_token_cost": 5e-07,+ "cache_read_input_token_cost_batches": 2.5e-07,"input_cost_per_token": 5e-06,+ "input_cost_per_token_batches": 2.5e-06,"litellm_provider": "anthropic","max_input_tokens": 1000000,"max_output_tokens": 128000,"max_tokens": 128000,"mode": "chat","output_cost_per_token": 2.5e-05,+ "output_cost_per_token_batches": 1.25e-05,"prompt_cache_min_tokens": 4096,"provider_specific_entry": {"us": 1.1@@ -354,14 +390,18 @@"claude-opus-4-6-20260205": {"cache_creation_input_token_cost": 6.25e-06,"cache_creation_input_token_cost_above_1hr": 1e-05,+ "cache_creation_input_token_cost_batches": 3.125e-06,"cache_read_input_token_cost": 5e-07,+ "cache_read_input_token_cost_batches": 2.5e-07,"input_cost_per_token": 5e-06,+ "input_cost_per_token_batches": 2.5e-06,"litellm_provider": "anthropic","max_input_tokens": 1000000,"max_output_tokens": 128000,"max_tokens": 128000,"mode": "chat","output_cost_per_token": 2.5e-05,+ "output_cost_per_token_batches": 1.25e-05,"prompt_cache_min_tokens": 4096,"provider_specific_entry": {"us": 1.1@@ -392,14 +432,18 @@"claude-opus-4-7": {"cache_creation_input_token_cost": 6.25e-06,"cache_creation_input_token_cost_above_1hr": 1e-05,+ "cache_creation_input_token_cost_batches": 3.125e-06,"cache_read_input_token_cost": 5e-07,+ "cache_read_input_token_cost_batches": 2.5e-07,"input_cost_per_token": 5e-06,+ "input_cost_per_token_batches": 2.5e-06,"litellm_provider": "anthropic","max_input_tokens": 1000000,"max_output_tokens": 128000,"max_tokens": 128000,"mode": "chat","output_cost_per_token": 2.5e-05,+ "output_cost_per_token_batches": 1.25e-05,"prompt_cache_min_tokens": 2048,"provider_specific_entry": {"us": 1.1@@ -432,14 +476,18 @@"claude-opus-4-7-20260416": {"cache_creation_input_token_cost": 6.25e-06,"cache_creation_input_token_cost_above_1hr": 1e-05,+ "cache_creation_input_token_cost_batches": 3.125e-06,"cache_read_input_token_cost": 5e-07,+ "cache_read_input_token_cost_batches": 2.5e-07,"input_cost_per_token": 5e-06,+ "input_cost_per_token_batches": 2.5e-06,"litellm_provider": "anthropic","max_input_tokens": 1000000,"max_output_tokens": 128000,"max_tokens": 128000,"mode": "chat","output_cost_per_token": 2.5e-05,+ "output_cost_per_token_batches": 1.25e-05,"prompt_cache_min_tokens": 2048,"provider_specific_entry": {"us": 1.1@@ -471,14 +519,18 @@"claude-opus-4-8": {"cache_creation_input_token_cost": 6.25e-06,"cache_creation_input_token_cost_above_1hr": 1e-05,+ "cache_creation_input_token_cost_batches": 3.125e-06,"cache_read_input_token_cost": 5e-07,+ "cache_read_input_token_cost_batches": 2.5e-07,"input_cost_per_token": 5e-06,+ "input_cost_per_token_batches": 2.5e-06,"litellm_provider": "anthropic","max_input_tokens": 1000000,"max_output_tokens": 128000,"max_tokens": 128000,"mode": "chat","output_cost_per_token": 2.5e-05,+ "output_cost_per_token_batches": 1.25e-05,"prompt_cache_min_tokens": 1024,"provider_specific_entry": {"fast": 2.0,@@ -514,14 +566,18 @@"claude-opus-5": {"cache_creation_input_token_cost": 6.25e-06,"cache_creation_input_token_cost_above_1hr": 1e-05,+ "cache_creation_input_token_cost_batches": 3.125e-06,"cache_read_input_token_cost": 5e-07,+ "cache_read_input_token_cost_batches": 2.5e-07,"input_cost_per_token": 5e-06,+ "input_cost_per_token_batches": 2.5e-06,"litellm_provider": "anthropic","max_input_tokens": 1000000,"max_output_tokens": 128000,"max_tokens": 128000,"mode": "chat","output_cost_per_token": 2.5e-05,+ "output_cost_per_token_batches": 1.25e-05,"prompt_cache_min_tokens": 512,"provider_specific_entry": {"fast": 2.0,@@ -557,14 +613,18 @@"claude-opus-5-5": {"cache_creation_input_token_cost": 5e-06,"cache_creation_input_token_cost_above_1hr": 8e-06,+ "cache_creation_input_token_cost_batches": 2.5e-06,"cache_read_input_token_cost": 2e-07,+ "cache_read_input_token_cost_batches": 1e-07,"input_cost_per_token": 4e-06,+ "input_cost_per_token_batches": 2e-06,"litellm_provider": "anthropic","max_input_tokens": 1000000,"max_output_tokens": 128000,"max_tokens": 128000,"mode": "chat","output_cost_per_token": 2e-05,+ "output_cost_per_token_batches": 1e-05,"prompt_cache_min_tokens": 512,"provider_specific_entry": {"fast": 2.0@@ -602,10 +662,16 @@"cache_creation_input_token_cost_above_1hr": 6e-06,"cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,+ "cache_creation_input_token_cost_above_200k_tokens_batches": 3.75e-06,+ "cache_creation_input_token_cost_batches": 1.875e-06,"cache_read_input_token_cost": 3e-07,"cache_read_input_token_cost_above_200k_tokens": 6e-07,+ "cache_read_input_token_cost_above_200k_tokens_batches": 3e-07,+ "cache_read_input_token_cost_batches": 1.5e-07,"input_cost_per_token": 3e-06,"input_cost_per_token_above_200k_tokens": 6e-06,+ "input_cost_per_token_above_200k_tokens_batches": 3e-06,+ "input_cost_per_token_batches": 1.5e-06,"litellm_provider": "anthropic","max_input_tokens": 1000000,"max_output_tokens": 64000,@@ -613,6 +679,8 @@"mode": "chat","output_cost_per_token": 1.5e-05,"output_cost_per_token_above_200k_tokens": 2.25e-05,+ "output_cost_per_token_above_200k_tokens_batches": 1.125e-05,+ "output_cost_per_token_batches": 7.5e-06,"prompt_cache_min_tokens": 1024,"search_context_cost_per_query": {"search_context_size_high": 0.01,@@ -636,10 +704,16 @@"cache_creation_input_token_cost_above_1hr": 6e-06,"cache_creation_input_token_cost_above_1hr_above_200k_tokens": 1.2e-05,"cache_creation_input_token_cost_above_200k_tokens": 7.5e-06,+ "cache_creation_input_token_cost_above_200k_tokens_batches": 3.75e-06,+ "cache_creation_input_token_cost_batches": 1.875e-06,"cache_read_input_token_cost": 3e-07,"cache_read_input_token_cost_above_200k_tokens": 6e-07,+ "cache_read_input_token_cost_above_200k_tokens_batches": 3e-07,+ "cache_read_input_token_cost_batches": 1.5e-07,"input_cost_per_token": 3e-06,"input_cost_per_token_above_200k_tokens": 6e-06,+ "input_cost_per_token_above_200k_tokens_batches": 3e-06,+ "input_cost_per_token_batches": 1.5e-06,"litellm_provider": "anthropic","max_input_tokens": 1000000,"max_output_tokens": 64000,@@ -647,6 +721,8 @@"mode": "chat","output_cost_per_token": 1.5e-05,"output_cost_per_token_above_200k_tokens": 2.25e-05,+ "output_cost_per_token_above_200k_tokens_batches": 1.125e-05,+ "output_cost_per_token_batches": 7.5e-06,"prompt_cache_min_tokens": 1024,"search_context_cost_per_query": {"search_context_size_high": 0.01,@@ -700,14 +776,18 @@"claude-sonnet-4-6": {"cache_creation_input_token_cost": 3.75e-06,"cache_creation_input_token_cost_above_1hr": 6e-06,+ "cache_creation_input_token_cost_batches": 1.875e-06,"cache_read_input_token_cost": 3e-07,+ "cache_read_input_token_cost_batches": 1.5e-07,"input_cost_per_token": 3e-06,+ "input_cost_per_token_batches": 1.5e-06,"litellm_provider": "anthropic","max_input_tokens": 1000000,"max_output_tokens": 128000,"max_tokens": 128000,"mode": "chat","output_cost_per_token": 1.5e-05,+ "output_cost_per_token_batches": 7.5e-06,"prompt_cache_min_tokens": 1024,"provider_specific_entry": {"us": 1.1@@ -738,14 +818,18 @@"claude-sonnet-5": {"cache_creation_input_token_cost": 2.5e-06,"cache_creation_input_token_cost_above_1hr": 4e-06,+ "cache_creation_input_token_cost_batches": 1.25e-06,"cache_read_input_token_cost": 2e-07,+ "cache_read_input_token_cost_batches": 1e-07,"input_cost_per_token": 2e-06,+ "input_cost_per_token_batches": 1e-06,"litellm_provider": "anthropic","max_input_tokens": 1000000,"max_output_tokens": 128000,"max_tokens": 128000,"mode": "chat","output_cost_per_token": 1e-05,+ "output_cost_per_token_batches": 5e-06,"prompt_cache_min_tokens": 1024,"provider_specific_entry": {"us": 1.1@@ -774,6 +858,52 @@"supports_tool_choice": true,"supports_vision": true,"supports_xhigh_reasoning_effort": true+ },+ "claude-sonnet-5-5": {+ "cache_creation_input_token_cost": 2.5e-06,+ "cache_creation_input_token_cost_above_1hr": 4e-06,+ "cache_creation_input_token_cost_batches": 1.25e-06,+ "cache_read_input_token_cost": 2e-07,+ "cache_read_input_token_cost_batches": 1e-07,+ "input_cost_per_token": 2e-06,+ "input_cost_per_token_batches": 1e-06,+ "litellm_provider": "anthropic",+ "max_input_tokens": 1000000,+ "max_output_tokens": 128000,+ "max_tokens": 128000,+ "mode": "chat",+ "output_cost_per_token": 1e-05,+ "output_cost_per_token_batches": 5e-06,+ "prompt_cache_min_tokens": 512,+ "provider_specific_entry": {+ "us": 1.1+ },+ "search_context_cost_per_query": {+ "search_context_size_high": 0.01,+ "search_context_size_low": 0.01,+ "search_context_size_medium": 0.01+ },+ "source": "https://platform.claude.com/docs/en/models/sonnet-5-5/overview",+ "supports_adaptive_thinking": true,+ "supports_anthropic_compaction": true,+ "supports_assistant_prefill": false,+ "supports_computer_use": true,+ "supports_forced_tool_use": false,+ "supports_function_calling": true,+ "supports_max_reasoning_effort": true,+ "supports_mid_conversation_system": true,+ "supports_native_structured_output": true,+ "supports_output_config": true,+ "supports_pdf_input": true,+ "supports_prompt_caching": true,+ "supports_reasoning": true,+ "supports_response_schema": true,+ "supports_sampling_params": false,+ "supports_tool_choice": true,+ "supports_vision": true,+ "supports_web_search": true,+ "supports_xhigh_reasoning_effort": true,+ "thinking_always_on": true}}}diff --git a/autogpt_platform/backend/backend/copilot/baseline/transcript_integration_test.py b/autogpt_platform/backend/backend/copilot/baseline/transcript_integration_test.pyindex 96a2d000f9..4855364e7c 100644--- a/autogpt_platform/backend/backend/copilot/baseline/transcript_integration_test.py+++ b/autogpt_platform/backend/backend/copilot/baseline/transcript_integration_test.py@@ -108,7 +108,7 @@ class TestResolveBaselineModel:assert (ChatConfig.model_fields["fast_standard_model"].default- == "anthropic/claude-sonnet-5"+ == "anthropic/claude-sonnet-5-5")def test_fast_advanced_default_is_opus(self):diff --git a/autogpt_platform/backend/backend/copilot/config.py b/autogpt_platform/backend/backend/copilot/config.pyindex e3d80914dd..02d23e4a10 100644--- a/autogpt_platform/backend/backend/copilot/config.py+++ b/autogpt_platform/backend/backend/copilot/config.py@@ -203,7 +203,7 @@ class ChatConfig(BaseSettings):# ``CHAT_FAST_MODEL``) are preserved via ``validation_alias`` so# existing deployments continue to override the same effective cell.fast_standard_model: str = Field(- default="anthropic/claude-sonnet-5",+ default="anthropic/claude-sonnet-5-5",validation_alias=AliasChoices("CHAT_FAST_STANDARD_MODEL","CHAT_FAST_MODEL",@@ -221,7 +221,7 @@ class ChatConfig(BaseSettings):"the cloud default — see ``_apply_local_aux_models``.",)thinking_standard_model: str = Field(- default="anthropic/claude-sonnet-5",+ default="anthropic/claude-sonnet-5-5",validation_alias=AliasChoices("CHAT_THINKING_STANDARD_MODEL","CHAT_MODEL",diff --git a/autogpt_platform/backend/backend/copilot/config_test.py b/autogpt_platform/backend/backend/copilot/config_test.pyindex 1d8dbd3636..4310a70b5f 100644--- a/autogpt_platform/backend/backend/copilot/config_test.py+++ b/autogpt_platform/backend/backend/copilot/config_test.py@@ -246,7 +246,7 @@ class TestSdkModelVendorCompatibility:# aux check.aux_api_key="or-aux-key",)- assert cfg.thinking_standard_model == "anthropic/claude-sonnet-5"+ assert cfg.thinking_standard_model == "anthropic/claude-sonnet-5-5"def test_openrouter_with_kimi_override_succeeds(self):"""Kimi slug round-trips cleanly when OpenRouter is on — exercised@@ -593,7 +593,7 @@ class TestLocalAuxModels:def test_cloud_transport_does_not_inherit(self):"""Cloud transports leave the per-field cloud defaults alone — anoperator might genuinely want gpt-4o-mini for titles even though- their primary model is anthropic/claude-sonnet-5."""+ their primary model is anthropic/claude-sonnet-5-5."""cfg = ChatConfig(use_openrouter=True,api_key="or-key",diff --git a/autogpt_platform/backend/backend/copilot/opus_5_test.py b/autogpt_platform/backend/backend/copilot/opus_5_test.pyindex 795c272c5d..fb3ed7bb49 100644--- a/autogpt_platform/backend/backend/copilot/opus_5_test.py+++ b/autogpt_platform/backend/backend/copilot/opus_5_test.py@@ -41,7 +41,7 @@ async def test_thinking_advanced_routes_opus_5_5_without_catalog_refusal(expected = "anthropic/claude-opus-5-5" if use_openrouter else "claude-opus-5-5"assert normalize_model_for_transport(route.model, cfg) == expectedassert cfg.fast_advanced_model == "anthropic/claude-opus-5-5"- assert cfg.thinking_standard_model == "anthropic/claude-sonnet-5"+ assert cfg.thinking_standard_model == "anthropic/claude-sonnet-5-5"def test_opus_5_has_public_metadata_and_provider_prices():diff --git a/autogpt_platform/backend/backend/copilot/sdk/cli_openrouter_compat_test.py b/autogpt_platform/backend/backend/copilot/sdk/cli_openrouter_compat_test.pyindex 4ded125dbe..2e209c0a61 100644--- a/autogpt_platform/backend/backend/copilot/sdk/cli_openrouter_compat_test.py+++ b/autogpt_platform/backend/backend/copilot/sdk/cli_openrouter_compat_test.py@@ -457,10 +457,11 @@ def _assert_no_forbidden_patterns(@pytest.mark.asyncio@pytest.mark.xfail(- reason="CLI 2.1.281 (SDK 0.2.159) still sends the "+ reason="CLI 2.1.284 (SDK 0.2.161) still sends the ""context-management-2025-06-27 beta header against a non-Anthropic base ""URL without CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1 (observed, same as "- "CLI 2.1.97 / SDK 0.1.58). This is expected — the env var guard in "+ "CLI 2.1.97 / SDK 0.1.58; the 2.1.284 bundle still carries the beta "+ "string). This is expected — the env var guard in ""test_disable_experimental_betas_env_var_strips_headers is the real ""regression test.",strict=True,diff --git a/autogpt_platform/backend/backend/copilot/sdk/sdk_compat_test.py b/autogpt_platform/backend/backend/copilot/sdk/sdk_compat_test.pyindex 6fee679d7a..642fbf3e98 100644--- a/autogpt_platform/backend/backend/copilot/sdk/sdk_compat_test.py+++ b/autogpt_platform/backend/backend/copilot/sdk/sdk_compat_test.py@@ -280,6 +280,15 @@ _KNOWN_GOOD_BUNDLED_CLI_VERSIONS: frozenset[str] = frozenset(# body keys. Verified via cli_openrouter_compat_test.py."2.1.281", # claude-agent-sdk 0.2.159 -- 2.1.280+ is required for# claude-opus-5-5. Verified via cli_openrouter_compat_test.py.+ "2.1.284", # claude-agent-sdk 0.2.161 -- 2.1.284+ is required for+ # claude-sonnet-5-5: the 2.1.281 bundle carries no+ # sonnet-5-5 entry (inspected the bundled binary), so the+ # CLI rejects the slug the same way 2.1.279 rejected+ # claude-opus-5-5. Still ships the+ # context-management-2025-06-27 beta string, so the+ # build_sdk_env() CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS+ # guard remains required -- see+ # cli_openrouter_compat_test.py, which CI runs.})diff --git a/autogpt_platform/backend/backend/copilot/sonnet_5_5_test.py b/autogpt_platform/backend/backend/copilot/sonnet_5_5_test.pynew file mode 100644index 0000000000..086cb8a9c5--- /dev/null+++ b/autogpt_platform/backend/backend/copilot/sonnet_5_5_test.py@@ -0,0 +1,74 @@+"""Sonnet 5.5 is the shipped standard-tier default on both paths.++Mirrors ``opus_5_test.py`` for the advanced tier: the failure this guards+against is a default that routes but is not catalogued, where+``_registry_refuses`` silently downgrades the request and the only trace+is a warning nobody reads.+"""++import os++import pytest++import backend.copilot.model_router as router+import backend.data.llm_registry.registry as registry+from backend.copilot.config import ChatConfig+from backend.copilot.model_normalize import normalize_model_for_transport+from backend.util.settings import BehaveAs++[email protected](autouse=True)+def isolated_catalog_and_config(monkeypatch):+ for key in os.environ:+ if key.startswith("CHAT_"):+ monkeypatch.delenv(key)+ for field in ("_dynamic_models", "_date_stripped_models", "_routes"):+ monkeypatch.setattr(registry, field, {})+ monkeypatch.setattr(registry, "_loaded", False)+ monkeypatch.setattr(router.settings.config, "behave_as", BehaveAs.CLOUD)+ registry.load_catalog()++[email protected]("path", ["thinking", "fast"])[email protected]("use_openrouter", [True, False])+async def test_standard_tier_routes_sonnet_5_5_without_catalog_refusal(+ path, use_openrouter, caplog, mocker+):+ cfg = ChatConfig(+ use_local=False,+ use_openrouter=use_openrouter,+ use_claude_code_subscription=False,+ api_key="test-key",+ aux_api_key="test-key",+ )+ mocker.patch.object(router, "get_feature_flag_value", return_value=None)+ route = await router.resolve_model_route(path, "standard", "user", config=cfg)++ assert route.model == "anthropic/claude-sonnet-5-5"+ assert route.source == "env"+ assert "refused" not in caplog.text+ expected = "anthropic/claude-sonnet-5-5" if use_openrouter else "claude-sonnet-5-5"+ assert normalize_model_for_transport(route.model, cfg) == expected+++def test_sonnet_5_5_has_public_metadata_and_provider_prices():+ model = router.catalog_lookup("anthropic/claude-sonnet-5-5")+ assert model is not None+ assert model.is_enabled+ assert model.visibility == "GA"+ assert model.display_name == "Claude Sonnet 5.5"+ assert model.metadata.context_window == 200_000+ assert model.metadata.max_output_tokens == 128_000+ assert model.supports_tools and model.supports_reasoning+ assert model.cost is not None+ assert model.cost.provider_input_usd_per_1m == 2.0+ assert model.cost.provider_output_usd_per_1m == 10.0+++def test_sonnet_5_stays_listed_after_the_default_moves():+ """Superseded, not removed: existing graphs pinned to Sonnet 5 keep+ running and the builder keeps offering it."""+ model = router.catalog_lookup("anthropic/claude-sonnet-5")+ assert model is not None+ assert model.is_enabled+ assert model.visibility == "GA"diff --git a/autogpt_platform/backend/backend/data/llm_registry/catalog.py b/autogpt_platform/backend/backend/data/llm_registry/catalog.pyindex d29b4c9134..ea1869c4e2 100644--- a/autogpt_platform/backend/backend/data/llm_registry/catalog.py+++ b/autogpt_platform/backend/backend/data/llm_registry/catalog.py@@ -289,6 +289,36 @@ def _build_catalog() -> CatalogPayload:provider_output_usd_per_1m=15.00,),),+ CatalogModel(+ slug="claude-sonnet-5-5",+ display_name="Claude Sonnet 5.5",+ provider="anthropic",+ creator="anthropic",+ # Same compaction-cap convention as the rest of the Claude+ # 5 family: native window is 1M, capped at 200K here.+ context_window=200000,+ max_output_tokens=128000,+ price_tier=3,+ supports_tools=True,+ supports_json_output=True,+ supports_reasoning=True,+ # Sticker price $2/$10 per Mtok, undercutting Sonnet 5's+ # $3/$15 sticker. Cache read $0.20/1M, cache write (5m)+ # $2.50/1M, (1h) $4.00/1M. Verified 2026-09-28 against+ # Anthropic's sonnet-5-5 docs, the vendored rate card and+ # OpenRouter's live listing — no intro-pricing end date is+ # published, unlike Sonnet 5. Credits at the standard 1.5x+ # margin.+ cost=CatalogModelCost(+ run_credits=9,+ input_credits_per_1m=300.0,+ output_credits_per_1m=1500.0,+ cache_read_credits_per_1m=30.0,+ cache_creation_credits_per_1m=375.0,+ provider_input_usd_per_1m=2.00,+ provider_output_usd_per_1m=10.00,+ ),+ ),CatalogModel(slug="claude-fable-5-1",display_name="Claude Fable 5.1",diff --git a/autogpt_platform/backend/backend/data/llm_registry/catalog_test.py b/autogpt_platform/backend/backend/data/llm_registry/catalog_test.pyindex ea6b6ac695..1a88931633 100644--- a/autogpt_platform/backend/backend/data/llm_registry/catalog_test.py+++ b/autogpt_platform/backend/backend/data/llm_registry/catalog_test.py@@ -190,6 +190,25 @@ def test_claude_sonnet_5_bills_at_authored_rates():assert MODEL_METADATA[s5].max_output_tokens == 128000+def test_claude_sonnet_5_5_bills_at_authored_rates():+ """Claude Sonnet 5.5 (Anthropic sticker $2/$10 per 1M, undercutting+ Sonnet 5's $3/$15) — flat tier and per-1M projections must match the+ authored catalog entry. This is the default standard-tier copilot+ model, so a silent repricing here moves every standard chat."""+ s55 = LLMModel("claude-sonnet-5-5")+ assert MODEL_COST[s55] == 9+ assert TOKEN_COST[s55].model_dump() == {+ "input": 300.0,+ "output": 1500.0,+ "cache_read": 30.0,+ "cache_creation": 375.0,+ }+ assert MODEL_METADATA[s55].max_output_tokens == 128000+ s55_entry = next(m for m in CATALOG.models if m.slug == "claude-sonnet-5-5")+ assert s55_entry.price_tier == 3+ assert s55_entry.context_window == 200000++def test_claude_opus_5_bills_at_authored_rates():opus = LLMModel("claude-opus-5")assert MODEL_COST[opus] == 14diff --git a/autogpt_platform/backend/backend/data/llm_registry/llm_models.py b/autogpt_platform/backend/backend/data/llm_registry/llm_models.pyindex ea9eeb2fc0..34a5708459 100644--- a/autogpt_platform/backend/backend/data/llm_registry/llm_models.py+++ b/autogpt_platform/backend/backend/data/llm_registry/llm_models.py@@ -182,6 +182,7 @@ class LLMModel(str, Enum, metaclass=LLMModelMeta):CLAUDE_5_5_OPUS = "claude-opus-5-5"CLAUDE_4_6_SONNET = "claude-sonnet-4-6"CLAUDE_5_SONNET = "claude-sonnet-5"+ CLAUDE_5_5_SONNET = "claude-sonnet-5-5"CLAUDE_5_1_FABLE = "claude-fable-5-1"# AI/ML API modelsAIML_API_LLAMA3_3_70B = "meta-llama/Llama-3.3-70B-Instruct-Turbo"@@ -327,9 +328,12 @@ class LLMModel(str, Enum, metaclass=LLMModelMeta):# (``claude-haiku-4-5-20251001`` → ``anthropic/claude-haiku-4-5``). The# generic provider-prefix strip in ``_missing_`` can't reverse the date# truncation, so map the OpenRouter slugs to ``LLMModel`` members here.-# Only models whose canonical enum value carries a ``-YYYYMMDD`` snapshot-# suffix need entries; values without a snapshot (4.6/4.7+) are already-# covered by the prefix-strip path alone. Stored as ``LLMModel`` instances+# Models whose canonical enum value carries a ``-YYYYMMDD`` snapshot+# suffix need entries, as do the dot-versioned point releases+# (``anthropic/claude-sonnet-5.5`` → ``claude-sonnet-5-5``) — ``_missing_``+# strips the vendor prefix but does not rewrite dots. Plain values without+# either (4.6/4.7+, ``claude-sonnet-5``) are covered by the prefix-strip+# path alone. Stored as ``LLMModel`` instances# (not strings) so a rename or snapshot rotation on the enum follows the# alias automatically — a stale entry becomes a load-time ``AttributeError``# rather than a silent ``_missing_`` miss at runtime.@@ -337,6 +341,7 @@ _OPENROUTER_ALIASES: Mapping[str, LLMModel] = {"anthropic/claude-haiku-4-5": LLMModel.CLAUDE_4_5_HAIKU,"anthropic/claude-opus-4-5": LLMModel.CLAUDE_4_5_OPUS,"anthropic/claude-sonnet-4-5": LLMModel.CLAUDE_4_5_SONNET,+ "anthropic/claude-sonnet-5.5": LLMModel.CLAUDE_5_5_SONNET,"openai/gpt-5.4": LLMModel.GPT5_4,"openai/gpt-5.4-mini": LLMModel.GPT5_4_MINI,"openai/gpt-5.4-nano": LLMModel.GPT5_4_NANO,diff --git a/autogpt_platform/backend/poetry.lock b/autogpt_platform/backend/poetry.lockindex 0da9b43def..3b2517fd6a 100644--- a/autogpt_platform/backend/poetry.lock+++ b/autogpt_platform/backend/poetry.lock@@ -983,18 +983,17 @@ files = [[[package]]name = "claude-agent-sdk"-version = "0.2.159"+version = "0.2.161"description = "Python SDK for Claude Code"optional = falsepython-versions = ">=3.10"groups = ["main"]files = [- {file = "claude_agent_sdk-0.2.159-py3-none-macosx_11_0_arm64.whl", hash = "sha256:ba7f152560dca5001a0bc46ed13b7da14eb14b419faed25bb1af821bfa95d3de"},- {file = "claude_agent_sdk-0.2.159-py3-none-macosx_11_0_x86_64.whl", hash = "sha256:87f553fda74e2f57e00f2bcb1705ab9311a937f97571f4f9eceea2bd411b6e32"},- {file = "claude_agent_sdk-0.2.159-py3-none-manylinux_2_17_aarch64.whl", hash = "sha256:b03683d12d217b0b6c189c88a3d260a045171e7fdc9f23e2d0dfb05ff3276834"},- {file = "claude_agent_sdk-0.2.159-py3-none-manylinux_2_17_x86_64.whl", hash = "sha256:d3ba57c187b07c87702b94e2b62dd7c61ed874899defcbb35bb5cef4cb94ace1"},- {file = "claude_agent_sdk-0.2.159-py3-none-win_amd64.whl", hash = "sha256:cc1b92ae56f42ade2d083ef2d2e5edb4aa8c7a6d856818a9b8f60cf6ae746f3a"},- {file = "claude_agent_sdk-0.2.159.tar.gz", hash = "sha256:e1905e2637b27971bb561bb6ad317aeb3d50619be5261bfa7ff2e9c2be0f0fd1"},+ {file = "claude_agent_sdk-0.2.161-py3-none-macosx_11_0_arm64.whl", hash = "sha256:127c18a790dc9f77cc2d648f932e11b06cd3325c4b3de7a73d3bcf3d3b74b8bc"},+ {file = "claude_agent_sdk-0.2.161-py3-none-macosx_11_0_x86_64.whl", hash = "sha256:599e1c8ccb4d48ed57999b48e80937d6a6aefbc52b0c0cda1291aea21df29e3e"},+ {file = "claude_agent_sdk-0.2.161-py3-none-manylinux_2_17_aarch64.whl", hash = "sha256:18081d3277c07a71891bd15d1496387d9efc5f04a6b482ae3a03e7a0b8067069"},+ {file = "claude_agent_sdk-0.2.161-py3-none-manylinux_2_17_x86_64.whl", hash = "sha256:b854e46d2889a51e1a77978711a05c757e63064bd5d8f89bcf74bb507babfc2c"},+ {file = "claude_agent_sdk-0.2.161.tar.gz", hash = "sha256:284a1372ec3af133578009ab2b821a238272dbf17d687a58be9df918d7b3ae89"},][package.dependencies]diff --git a/autogpt_platform/backend/pyproject.toml b/autogpt_platform/backend/pyproject.tomlindex 946a07921f..6bf6d1be61 100644--- a/autogpt_platform/backend/pyproject.toml+++ b/autogpt_platform/backend/pyproject.toml@@ -19,7 +19,7 @@ autogpt-libs = { path = "../autogpt_libs", develop = true }bcrypt = "^5.0.0"bleach = { extras = ["css"], version = "^6.2.0" }cachetools = "^5.5.0"-claude-agent-sdk = "^0.2.159" # Bundled CLI 2.1.280+ is required for claude-opus-5-5. 2.1.98+ fixes the --resume + excludeDynamicSections crash that used to force a per-turn 33K cache write. CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1 strips the context-management beta, which OpenRouter rejects. See sdk_compat_test.py.+claude-agent-sdk = "^0.2.159" # Bundled CLI 2.1.284+ is required for claude-sonnet-5-5 (2.1.280+ for claude-opus-5-5); the lock pins 0.2.161. 2.1.98+ fixes the --resume + excludeDynamicSections crash that used to force a per-turn 33K cache write. CLAUDE_CODE_DISABLE_EXPERIMENTAL_BETAS=1 strips the context-management beta, which OpenRouter rejects. See sdk_compat_test.py.click = "^8.2.0"cryptography = ">=46,<51"discord-py = "^2.5.2"diff --git a/docs/integrations/block-integrations/llm.md b/docs/integrations/block-integrations/llm.mdindex f8c155bb21..903243b6cb 100644--- a/docs/integrations/block-integrations/llm.md+++ b/docs/integrations/block-integrations/llm.md@@ -65,7 +65,7 @@ The result routes data to yes_output or no_output, enabling intelligent branchin| condition | A plaintext English description of the condition to evaluate | str | Yes || yes_value | (Optional) Value to output if the condition is true. If not provided, input_value will be used. | Yes Value | No || no_value | (Optional) Value to output if the condition is false. If not provided, input_value will be used. | No Value | No |-| model | The language model to use for evaluating the condition. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-fable-5-1" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "deepseek/deepseek-v4.1-flash" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.7" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |+| model | The language model to use for evaluating the condition. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "deepseek/deepseek-v4.1-flash" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.7" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |### Outputs@@ -103,7 +103,7 @@ The block sends the entire conversation history to the chosen LLM, including sys|-------|-------------|------|----------|| prompt | The prompt to send to the language model. | str | No || messages | List of messages in the conversation. | List[Any] | Yes |-| model | The language model to use for the conversation. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-fable-5-1" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "deepseek/deepseek-v4.1-flash" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.7" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |+| model | The language model to use for the conversation. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "deepseek/deepseek-v4.1-flash" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.7" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No || max_tokens | The maximum number of tokens to generate in the chat completion. | int | No || ollama_host | Ollama host for local models | str | No |@@ -257,7 +257,7 @@ The block formulates a prompt based on the given focus or source data, sends it|-------|-------------|------|----------|| focus | The focus of the list to generate. | str | No || source_data | The data to generate the list from. | str | No |-| model | The language model to use for generating the list. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-fable-5-1" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "deepseek/deepseek-v4.1-flash" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.7" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |+| model | The language model to use for generating the list. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "deepseek/deepseek-v4.1-flash" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.7" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No || max_retries | Maximum number of retries for generating a valid list. | int | No || force_json_output | Whether to force the LLM to produce a JSON-only response. This can increase the block's reliability, but may also reduce the quality of the response because it prohibits the LLM from reasoning before providing its JSON response. | bool | No || max_tokens | The maximum number of tokens to generate in the chat completion. | int | No |@@ -424,7 +424,7 @@ The block sends the input prompt to a chosen LLM, along with any system prompts| prompt | The prompt to send to the language model. | str | Yes || expected_format | Expected format of the response. If provided, the response will be validated against this format. The keys should be the expected fields in the response, and the values should be the description of the field. | Dict[str, str] | Yes || list_result | Whether the response should be a list of objects in the expected format. | bool | No |-| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-fable-5-1" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "deepseek/deepseek-v4.1-flash" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.7" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |+| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "deepseek/deepseek-v4.1-flash" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.7" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No || force_json_output | Whether to force the LLM to produce a JSON-only response. This can increase the block's reliability, but may also reduce the quality of the response because it prohibits the LLM from reasoning before providing its JSON response. | bool | No || sys_prompt | The system prompt to provide additional context to the model. | str | No || conversation_history | The conversation history to provide context for the prompt. | List[Dict[str, Any]] | No |@@ -464,7 +464,7 @@ The block sends the input prompt to a chosen LLM, processes the response, and re| Input | Description | Type | Required ||-------|-------------|------|----------|| prompt | The prompt to send to the language model. You can use any of the {keys} from Prompt Values to fill in the prompt with values from the prompt values dictionary by putting them in curly braces. | str | Yes |-| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-fable-5-1" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "deepseek/deepseek-v4.1-flash" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.7" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |+| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "deepseek/deepseek-v4.1-flash" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.7" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No || sys_prompt | The system prompt to provide additional context to the model. | str | No || retry | Number of times to retry the LLM call if the response does not match the expected format. | int | No || prompt_values | Values used to fill in the prompt. The values can be used in the prompt by putting them in a double curly braces, e.g. {{variable_name}}. | Dict[str, str] | No |@@ -501,7 +501,7 @@ The block splits the input text into smaller chunks, sends each chunk to an LLM| Input | Description | Type | Required ||-------|-------------|------|----------|| text | The text to summarize. | str | Yes |-| model | The language model to use for summarizing the text. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-fable-5-1" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "deepseek/deepseek-v4.1-flash" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.7" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |+| model | The language model to use for summarizing the text. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "deepseek/deepseek-v4.1-flash" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.7" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No || focus | The topic to focus on in the summary | str | No || style | The style of the summary to generate. | "concise" \| "detailed" \| "bullet points" \| "numbered list" | No || max_tokens | The maximum number of tokens to generate in the chat completion. | int | No |@@ -724,7 +724,7 @@ In the default `built_in` execution mode, configure `agent_mode_max_iterations`| Input | Description | Type | Required ||-------|-------------|------|----------|| prompt | The prompt to send to the language model. | str | Yes |-| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-fable-5-1" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "deepseek/deepseek-v4.1-flash" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.7" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No |+| model | The language model to use for answering the prompt. | "o3-mini" \| "o3-2025-04-16" \| "gpt-5.2-2025-12-11" \| "gpt-5.1-2025-11-13" \| "gpt-5-2025-08-07" \| "gpt-5-mini-2025-08-07" \| "o4-mini" \| "o3-pro" \| "o1" \| "o1-mini" \| "gpt-6-astra" \| "gpt-6-sol" \| "gpt-6-luna" \| "gpt-5.6-sol" \| "gpt-5.6-terra" \| "gpt-5.6-luna" \| "gpt-5.5-2026-04-23" \| "gpt-5.5-pro" \| "gpt-5.4-2026-03-05" \| "gpt-5.4-mini-2026-03-17" \| "gpt-5.4-nano-2026-03-17" \| "gpt-5.4-pro" \| "gpt-5.3-chat-latest" \| "gpt-5.3-codex" \| "gpt-5.2-pro" \| "gpt-5.1-codex" \| "gpt-5-pro" \| "gpt-4.1-nano" \| "gpt-5-nano-2025-08-07" \| "gpt-5-chat-latest" \| "gpt-4.1-2025-04-14" \| "gpt-4.1-mini-2025-04-14" \| "gpt-4o-mini" \| "gpt-4o" \| "claude-opus-4-5-20251101" \| "claude-sonnet-4-5-20250929" \| "claude-haiku-4-5-20251001" \| "claude-opus-4-6" \| "claude-opus-4-7" \| "claude-opus-4-8" \| "claude-opus-5" \| "claude-opus-5-5" \| "claude-sonnet-4-6" \| "claude-sonnet-5" \| "claude-sonnet-5-5" \| "claude-fable-5-1" \| "meta-llama/Llama-3.3-70B-Instruct-Turbo" \| "llama-3.3-70b-versatile" \| "llama-3.1-8b-instant" \| "llama3.3" \| "llama3.2" \| "llama3" \| "llama3.1:405b" \| "dolphin-mistral:latest" \| "openai/gpt-oss-120b" \| "openai/gpt-oss-20b" \| "google/gemini-2.5-pro" \| "google/gemini-3.1-pro-preview" \| "google/gemini-3-flash-preview" \| "google/gemini-2.5-flash" \| "google/gemini-2.0-flash-001" \| "google/gemini-3.1-flash-lite-preview" \| "google/gemini-3.8-flash" \| "google/gemini-2.5-flash-lite" \| "google/gemini-2.0-flash-lite-001" \| "google/gemma-4-31b-it" \| "mistralai/mistral-large-2512" \| "mistralai/mistral-medium-3.1" \| "mistralai/mistral-small-3.2-24b-instruct" \| "mistralai/codestral-2508" \| "cohere/command-a-03-2025" \| "cohere/command-a-translate-08-2025" \| "cohere/command-a-reasoning-08-2025" \| "cohere/command-a-vision-07-2025" \| "deepseek/deepseek-chat" \| "deepseek/deepseek-r1-0528" \| "deepseek/deepseek-v4.1-flash" \| "perplexity/sonar" \| "perplexity/sonar-pro" \| "perplexity/sonar-reasoning-pro" \| "perplexity/sonar-deep-research" \| "nousresearch/hermes-3-llama-3.1-405b" \| "nousresearch/hermes-3-llama-3.1-70b" \| "amazon/nova-lite-v1" \| "amazon/nova-micro-v1" \| "amazon/nova-pro-v1" \| "microsoft/phi-4" \| "gryphe/mythomax-l2-13b" \| "inclusionai/ling-3.0-flash-vl" \| "meta-llama/llama-4-scout" \| "meta-llama/llama-4-maverick" \| "meta/muse-spark-1.3" \| "meta/muse-spark-1.3-contributor" \| "x-ai/grok-3" \| "x-ai/grok-4" \| "x-ai/grok-4-fast" \| "x-ai/grok-4.1-fast" \| "x-ai/grok-4.20" \| "x-ai/grok-4.7" \| "x-ai/grok-4.20-multi-agent" \| "x-ai/grok-code-fast-1" \| "moonshotai/kimi-k2.5" \| "moonshotai/kimi-k2.6" \| "moonshotai/kimi-k2-thinking" \| "moonshotai/kimi-k3" \| "qwen/qwen3-235b-a22b-thinking-2507" \| "qwen/qwen3-coder" \| "qwen/qwen3.8-max-0902" \| "qwen/qwen3.8-flash" \| "xiaomi/mimo-v2.6-pro" \| "xiaomi/mimo-v2.6-flash" \| "z-ai/glm-4.6" \| "z-ai/glm-4.6v" \| "z-ai/glm-4.7" \| "z-ai/glm-4.7-flash" \| "z-ai/glm-5" \| "z-ai/glm-5-turbo" \| "z-ai/glm-5v-turbo" \| "z-ai/glm-5.3" \| "sakana/fugu-ultra-v2" \| "inception/mercury-2.5" \| "tencent/hy4-preview" \| "unbiased/pareto" \| "Llama-4-Scout-17B-16E-Instruct-FP8" \| "Llama-4-Maverick-17B-128E-Instruct-FP8" \| "Llama-3.3-8B-Instruct" \| "Llama-3.3-70B-Instruct" \| "v0-1.5-md" \| "v0-1.5-lg" \| "v0-1.0-md" | No || 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 |