Build AI methods with your coding agent, then run them anywhere: as an MCP for chatbots, as a webapp for people, or via API for your software.
feature/Roster-refresh · L-260920-6c3d2b (#1219)
Louis Choquel7eef69c2e086
diff --git a/.claude/skills/test-model/SKILL.md b/.claude/skills/test-model/SKILL.mdindex 010f27bb9..b8b094e74 100644--- a/.claude/skills/test-model/SKILL.md+++ b/.claude/skills/test-model/SKILL.md@@ -24,7 +24,7 @@ Gather from the user (or infer from context):| Field | Description | Example ||-------|-------------|---------|-| **Model name** | The model handle as it appears in backend TOMLs | `gpt-5.2-codex` |+| **Model name** | The model handle as it appears in backend TOMLs | `gpt-5.6-sol` || **Backend** | Which backend to test on | `pipelex_gateway` || **Model type** | `llm`, `img_gen`, `extract`, or `search` | `llm` |diff --git a/.pipelex-dev/test_profiles.toml b/.pipelex-dev/test_profiles.tomlindex 7d0ffd4c6..c7535edd3 100644--- a/.pipelex-dev/test_profiles.toml+++ b/.pipelex-dev/test_profiles.toml@@ -71,6 +71,9 @@ anthropic = ["claude-4.7-opus","claude-4.8-opus","claude-5-sonnet",+ "claude-5-opus",+ "claude-5-fable",+ "claude-5.1-fable",]# --- DeepSeek Models ---@@ -164,23 +167,16 @@ openai = ["gpt-4.1-nano","gpt-4.1-mini","gpt-4.1",- "o1-mini","o1","o3-mini","o3",- "o4-mini","gpt-5-nano","gpt-5-mini",- "gpt-5-chat","gpt-5","gpt-5-codex","gpt-5.1-codex",- "gpt-5.1-codex-max",- "gpt-5.1-chat","gpt-5.1","gpt-5.2",- "gpt-5.2-chat",- "gpt-5.2-codex","gpt-5.3-codex","gpt-5.4","gpt-5.4-pro",diff --git a/.pipelex/inference/backends/anthropic.toml b/.pipelex/inference/backends/anthropic.tomlindex 1e00088a1..dbe8fd8cf 100644--- a/.pipelex/inference/backends/anthropic.toml+++ b/.pipelex/inference/backends/anthropic.toml@@ -147,6 +147,40 @@ max_tokens = 64000inputs = ["text", "images", "pdf"]outputs = ["text", "structured"]max_prompt_images = 100-costs = { input = 3.0, output = 15.0 }+costs = { input = 2.0, output = 10.0 }+thinking_mode = "adaptive"+listed_constraints = ["temperature_unsupported"]++[claude-5-opus]+model_id = "claude-opus-5"+max_tokens = 128000+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+max_prompt_images = 100+costs = { input = 5.0, output = 25.0 }+thinking_mode = "adaptive"+listed_constraints = ["temperature_unsupported"]++[claude-5-fable]+model_id = "claude-fable-5"+max_tokens = 128000+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+max_prompt_images = 100+costs = { input = 10.0, output = 50.0 }+thinking_mode = "adaptive"+listed_constraints = ["temperature_unsupported"]++# --- Claude 5.1 Series --------------------------------------------------------+["claude-5.1-fable"]+model_id = "claude-fable-5-1"+max_tokens = 128000+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+max_prompt_images = 100+costs = { input = 10.0, output = 50.0 }thinking_mode = "adaptive"+# Fable 5.1 refuses tool_choice "tool" and "any", which is what the section default+# instructor/anthropic_tools forces; the reasoning variant leaves tool_choice on auto.+structure_method = "instructor/anthropic_reasoning_tools"listed_constraints = ["temperature_unsupported"]diff --git a/.pipelex/inference/backends/azure_openai.toml b/.pipelex/inference/backends/azure_openai.tomlindex db9a0c183..7649888fe 100644--- a/.pipelex/inference/backends/azure_openai.toml+++ b/.pipelex/inference/backends/azure_openai.toml@@ -8,7 +8,7 @@## Configuration structure:# - Each model is defined in its own section with the model name as the header-# - Headers with dots must be quoted (e.g., ["gpt-4.1"])+# - Headers with dots must be quoted (e.g., ["gpt-5.4"])# - Model costs are in USD per million tokens (input/output)## Documentation: https://docs.pipelex.com@@ -43,140 +43,6 @@ inputs = ["text", "images"]outputs = ["text", "structured"]costs = { input = 0.15, output = 0.6 }-# --- GPT-4.1 Series ------------------------------------------------------------["gpt-4.1"]-model_id = "gpt-4.1-2025-04-14"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 2, output = 8 }--["gpt-4.1-mini"]-model_id = "gpt-4.1-mini-2025-04-14"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 0.4, output = 1.6 }--["gpt-4.1-nano"]-model_id = "gpt-4.1-nano-2025-04-14"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 0.1, output = 0.4 }--# --- o Series -----------------------------------------------------------------[o1-mini]-model_id = "o1-mini-2024-09-12"-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 3.0, output = 12.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[o1]-model_id = "o1-2024-12-17"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 15.0, output = 60.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[o3-mini]-model_id = "o3-mini-2025-01-31"-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 1.1, output = 4.4 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[o3]-model_id = "o3-2025-04-16"-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 2, output = 8 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--# --- GPT-5 Series --------------------------------------------------------------[gpt-5-mini]-model_id = "gpt-5-mini-2025-08-07"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 0.25, output = 2.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[gpt-5-nano]-model_id = "gpt-5-nano-2025-08-07"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 0.05, output = 0.4 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[gpt-5-chat]-model_id = "gpt-5-chat-2025-08-07"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[gpt-5]-model_id = "gpt-5-2025-08-07"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--# --- GPT-5.1 Series --------------------------------------------------------------["gpt-5.1"]-model_id = "gpt-5.1-2025-11-13"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--["gpt-5.1-chat"]-model_id = "gpt-5.1-chat-2025-11-13"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--["gpt-5.1-codex"]-model_id = "gpt-5.1-codex-2025-11-13"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--# --- GPT-5.2 Series --------------------------------------------------------------["gpt-5.2"]-model_id = "gpt-5.2-2025-12-11"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 1.75, output = 14.0 }-thinking_mode = "manual"--["gpt-5.2-chat"]-model_id = "gpt-5.2-chat-2025-12-11"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--["gpt-5.2-codex"]-model_id = "gpt-5.2-codex-2026-01-14"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 1.75, output = 14.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"-# --- GPT-5.3 Series -------------------------------------------------------------["gpt-5.3-codex"]model_id = "gpt-5.3-codex-2026-02-24"diff --git a/.pipelex/inference/backends/openai.toml b/.pipelex/inference/backends/openai.tomlindex ef2ee7ccf..1bea020e0 100644--- a/.pipelex/inference/backends/openai.toml+++ b/.pipelex/inference/backends/openai.toml@@ -8,7 +8,7 @@## Configuration structure:# - Each model is defined in its own section with the model name as the header-# - Headers with dots must be quoted (e.g., ["gpt-4.1"])+# - Headers with dots must be quoted (e.g., ["gpt-5.4"])# - Model costs are in USD per million tokens (input/output)## Documentation: https://docs.pipelex.com@@ -30,178 +30,17 @@ thinking_mode = "none"# LANGUAGE MODELS################################################################################-# --- GPT-3.5 Series ------------------------------------------------------------["gpt-3.5-turbo"]-model_id = "gpt-3.5-turbo-1106"-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 0.5, output = 1.5 }--# --- GPT-4 Series --------------------------------------------------------------[gpt-4]-inputs = ["text"]-outputs = ["text"]-costs = { input = 30.0, output = 60.0 }--[gpt-4-turbo]-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 10.0, output = 30.0 }-# --- GPT-4o Series -------------------------------------------------------------[gpt-4o-2024-11-20]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 2.5, output = 10.0 }-[gpt-4o]inputs = ["text", "images", "pdf"]outputs = ["text", "structured"]costs = { input = 2.5, output = 10.0 }-[gpt-4o-mini-2024-07-18]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 0.15, output = 0.6 }-[gpt-4o-mini]inputs = ["text", "images", "pdf"]outputs = ["text", "structured"]costs = { input = 0.15, output = 0.6 }-# --- GPT-4.1 Series ------------------------------------------------------------["gpt-4.1"]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 2, output = 8 }--["gpt-4.1-mini"]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 0.4, output = 1.6 }--["gpt-4.1-nano"]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 0.1, output = 0.4 }--# --- o Series -----------------------------------------------------------------[o1]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 15.0, output = 60.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[o3-mini]-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 1.1, output = 4.4 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[o3]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 10.0, output = 40.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[o4-mini]-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 1.1, output = 4.4 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--# --- GPT-5 Series --------------------------------------------------------------[gpt-5]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[gpt-5-mini]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 0.25, output = 2.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[gpt-5-nano]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 0.05, output = 0.4 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[gpt-5-chat]-model_id = "gpt-5-chat-latest"-inputs = ["text", "images", "pdf"]-outputs = ["text"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[gpt-5-codex]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--# --- GPT-5.1 Series --------------------------------------------------------------["gpt-5.1"]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-thinking_mode = "manual"--["gpt-5.1-chat"]-model_id = "gpt-5.1-chat-latest"-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--["gpt-5.1-codex"]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--["gpt-5.1-codex-max"]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--# --- GPT-5.2 Series --------------------------------------------------------------["gpt-5.2"]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.75, output = 14.0 }-thinking_mode = "manual"--["gpt-5.2-chat"]-model_id = "gpt-5.2-chat-latest"-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.75, output = 14.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--["gpt-5.2-codex"]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.75, output = 14.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"-# --- GPT-5.3 Series -------------------------------------------------------------["gpt-5.3-codex"]inputs = ["text", "images", "pdf"]diff --git a/.pipelex/inference/backends/portkey.toml b/.pipelex/inference/backends/portkey.tomlindex e17965a09..f46825eb1 100644--- a/.pipelex/inference/backends/portkey.toml+++ b/.pipelex/inference/backends/portkey.toml@@ -105,16 +105,6 @@ structure_method = "instructor/openai_responses_tools"thinking_mode = "manual"x-portkey-provider = "@openai"-[o4-mini]-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 1.1, output = 4.4 }-valued_constraints = { fixed_temperature = 1 }-sdk = "portkey_responses"-structure_method = "instructor/openai_responses_tools"-thinking_mode = "manual"-x-portkey-provider = "@openai"-[gpt-5-nano]inputs = ["text", "images", "pdf"]outputs = ["text", "structured"]diff --git a/.pipelex/inference/deck/x_custom_llm_deck.toml b/.pipelex/inference/deck/x_custom_llm_deck.tomlindex b3adf6d9c..a8aecc307 100644--- a/.pipelex/inference/deck/x_custom_llm_deck.toml+++ b/.pipelex/inference/deck/x_custom_llm_deck.toml@@ -34,23 +34,23 @@ for_object = "disabled"## Example (uncomment to use):# [llm.waterfalls]-# premium-llm = ["claude-4.5-opus", "gemini-3.1-pro", "gpt-5.2", "grok-4"]+# premium-llm = ["claude-4.5-opus", "gemini-3.1-pro", "gpt-5.4", "grok-4"]# premium-llm-vision = [# "claude-4.5-opus",# "gemini-3.1-pro",-# "gpt-5.2",+# "gpt-5.4",# "grok-4-fast-reasoning",# ]# premium-llm-structured = [# "claude-4.5-opus",# "gemini-3.1-pro",-# "gpt-5.2",+# "gpt-5.4",# "grok-4",# ]# large-context-llm-code = [# "gemini-3.1-pro",# "claude-4.5-opus",-# "gpt-5.2",+# "gpt-5.4",# "grok-4-fast-reasoning",# ]# large-context-llm-text = ["gemini-2.5-flash", "claude-4.5-sonnet"]diff --git a/.pipelex/inference/routing_profiles.toml b/.pipelex/inference/routing_profiles.tomlindex 2fd6781aa..57407e0a6 100644--- a/.pipelex/inference/routing_profiles.toml+++ b/.pipelex/inference/routing_profiles.toml@@ -152,10 +152,10 @@ default = "pipelex_gateway"description = "Example routing profile using specific models"[profiles.example_routing_using_specific_models.routes]-"gpt-5-nano" = "pipelex_gateway"+"gpt-5.4-nano" = "pipelex_gateway""gpt-4o-mini" = "blackboxai"-"gpt-5-mini" = "openai"-"gpt-5-chat" = "azure_openai"+"gpt-5.4-mini" = "openai"+"gpt-5.5" = "azure_openai""claude-4-sonnet" = "pipelex_gateway""claude-3.7-sonnet" = "blackboxai"diff --git a/CHANGELOG.md b/CHANGELOG.mdindex 302d8ddec..e24e1bc29 100644--- a/CHANGELOG.md+++ b/CHANGELOG.md@@ -4,14 +4,21 @@### Added+- **Claude Opus 5, Claude Fable 5 and Claude Fable 5.1 join the Anthropic backend, and Opus 5 the two hosted profiles**: `claude-5-opus`, `claude-5-fable` and `claude-5.1-fable` are served on Anthropic's own model ids, and all three are reachable on Pipelex Manifold through Bedrock's `global.anthropic.*` endpoints, the way every other Claude already is. Only Opus 5 is served on the Pipelex Gateway: Bedrock refuses both Fables through Portkey with `data retention mode 'default' is not available for this model`, a mode no model spec can set, so listing them there would publish handles that fail on every request. All of them take text, images and PDF, cap output at 128k tokens, and think adaptively with the temperature parameter refused. Fable 5.1 additionally declares `structure_method = "instructor/anthropic_reasoning_tools"`, because it rejects the forced `tool_choice` that the backend's default `instructor/anthropic_tools` sends and structured output fails without it.- **The GPT-5.6 series and GPT-6 Astra are served on OpenAI, Azure OpenAI, the Pipelex Gateway and Pipelex Manifold**: `gpt-5.6-sol`, `gpt-5.6-terra`, `gpt-5.6-luna` and `gpt-6-astra` are registered on the two direct backends and, through the remote config, on both hosted routing profiles. All four take text, images and PDF, produce text and structured output, and reason under `thinking_mode = "manual"` with a fixed temperature of 1. The Azure entries carry the dated deployment ids the hosted profiles also use as their wire model ids.### Changed- **`add-model` skill follows the model's nearest sibling**: the skill derives which backend TOMLs, test collection and deck entries a new model belongs in from the model it succeeds, instead of a fixed provider-to-backend table, and checks each backend actually serves the model. It takes the model's facts from the provider's own documentation with OpenRouter as a cross-check, hands the live tests to `/test-model` with a test class per declared capability, and adds the deck and changelog steps and `make ugm` once the gateway catalog carries the model.+### Removed++- **The superseded GPT generations are retired from the rosters we ship (Breaking)**: the GPT-4.1 series, the `o1`, `o3` and `o4` reasoning models and the GPT-5, GPT-5.1 and GPT-5.2 generations are gone from `azure_openai`, from `openai` — which also loses `gpt-3.5-turbo`, `gpt-4`, `gpt-4-turbo`, the codex variants of those generations and the dated `gpt-4o` aliases — and from the gateway and manifold catalogs. `o4-mini` is retired from `portkey` in the same pass, since no other backend served it. None of them is unsupported: they are unlisted, and a project that still wants one keeps it by declaring it in its own backend config. What genuinely retires is their availability on the Pipelex Gateway and Pipelex Manifold, where the roster is ours. `gpt-4o` and `gpt-4o-mini` stay on both direct backends; the retired names that `portkey` and `blackboxai` still declare remain reachable through those, and `openrouter`'s bulk third-party catalog is untouched.+### Fixed+- **Claude Sonnet 5 is priced at its standard rate**: `claude-5-sonnet` carried the $3 / $15 per million tokens it was announced at, but its $2 / $10 introductory rate became the standard price and the scheduled increase was cancelled. The entry is corrected on the Anthropic backend and in both hosted catalogs, so cost reporting and budget ceilings no longer overstate a Sonnet 5 run.+- **A failed publish can be recovered without damaging what already shipped**: `publish-pypi.yml` scopes the signature upload to `dist/*.sigstore.json` so it no longer clobbers the wheel and sdist attached just before it, turns `skip-existing` on for a re-run or a manual dispatch, reuses the build an earlier attempt of the same run stored instead of rebuilding it, and refuses to touch a release whose tag names a commit other than the one being published. The release is now tagged at the commit it ships, named explicitly with `--target`, rather than at the default branch's head.- **A generated image is stored under its own media type, so a store no longer serves it as `binary/octet-stream`**: `GeneratedContentFactory.make_image_content` resolves the effective mime type once and already used it to mint the storage key's extension, but passed no `content_type` to `StorageProviderAbstract.store` on either the direct-bytes path or the fetched-remote one. The S3 provider only sets `ContentType` when it is given one, so every generated image landed untyped and S3 answered `binary/octet-stream` on the way back out — which reached any consumer that trusts the stored type, a same-origin assets route serving the object to a browser among them. Both calls now pass the resolved mime type, so the key's extension, the object's stored type and the reported `mime_type` cannot diverge.diff --git a/docs/building-methods/configure-ai-llm-to-optimize-methods.md b/docs/building-methods/configure-ai-llm-to-optimize-methods.mdindex 8cc6b5362..ea62e0bb4 100644--- a/docs/building-methods/configure-ai-llm-to-optimize-methods.md+++ b/docs/building-methods/configure-ai-llm-to-optimize-methods.md@@ -30,7 +30,7 @@ An LLM handle can be either:best-claude = "claude-4.1-opus"best-gemini = "gemini-2.5-pro"best-mistral = "mistral-large"-base-gpt = "gpt-5"+base-gpt = "gpt-5.5"```The system first looks for direct model names, then checks aliases if no direct match is found. The system handles model routing through backends automatically.@@ -83,7 +83,7 @@ description = "Generate a creative response"inputs = { question = "Question" }output = "Response"model = {- model = "gpt-4-turbo", # Using inline LLM settings+ model = "gpt-5.4", # Using inline LLM settingstemperature = 0.8,}prompt = """diff --git a/docs/configuration/config-technical/inference-backend-config.md b/docs/configuration/config-technical/inference-backend-config.mdindex fe1305952..82b974482 100644--- a/docs/configuration/config-technical/inference-backend-config.md+++ b/docs/configuration/config-technical/inference-backend-config.md@@ -305,11 +305,11 @@ inputs = ["text", "images"]outputs = ["text", "structured"]costs = { input = 0.15, output = 0.6 }-[gpt-4-turbo]-model_id = "gpt-4-turbo"-inputs = ["text"]+["gpt-5.4"]+model_id = "gpt-5.4"+inputs = ["text", "images", "pdf"]outputs = ["text", "structured"]-costs = { input = 10.0, output = 30.0 }+costs = { input = 2.5, output = 15.0 }[gpt-image-1]model_id = "gpt-image-1"@@ -651,7 +651,7 @@ for_object = "@my-custom-alias"# Add custom waterfalls - lists of models tried in order[llm.waterfalls]-premium-llm = ["claude-4.5-opus", "gemini-3.1-pro", "gpt-5.2"]+premium-llm = ["claude-4.5-opus", "gemini-3.1-pro", "gpt-5.4"]small-llm = ["gemini-2.5-flash-lite", "gpt-4o-mini", "claude-3-haiku"]```@@ -665,7 +665,7 @@ document_extractor = ["azure-document-intelligence", "mistral-document-ai-2505"]When using waterfalls in `.mthds` files, prefix them with `~`:```toml-model = "~premium-llm" # Will try claude-4.5-opus, then gemini-3.1-pro, then gpt-5.2+model = "~premium-llm" # Will try claude-4.5-opus, then gemini-3.1-pro, then gpt-5.4model = "~small-llm" # Will try gemini-2.5-flash-lite, then gpt-4o-mini, etc.```diff --git a/docs/features/gateway.md b/docs/features/gateway.mdindex 5172fe784..efd22e20a 100644--- a/docs/features/gateway.md+++ b/docs/features/gateway.md@@ -24,8 +24,8 @@ Get your Gateway API key at [app.pipelex.com](https://app.pipelex.com/) or [joinDirect integration with major providers using your own API keys:-- **OpenAI** — GPT-4o, GPT-4.1, o1, o3, o4-mini, etc.-- **Anthropic** — Claude Sonnet 4, Claude Haiku, etc.+- **OpenAI** — GPT-4o, GPT-5.4, GPT-5.5, GPT-5.6, GPT-6, etc.+- **Anthropic** — Claude Opus 5, Claude Fable 5, Claude Sonnet 5, etc.- **Google** — Gemini 2.5 Pro, Gemini 2.5 Flash, etc.- **Mistral** — Mistral Large, Mistral Medium, etc.- **Azure OpenAI** — Azure-hosted OpenAI modelsdiff --git a/docs/setup/telemetry.md b/docs/setup/telemetry.mdindex a2fce9854..6a7f6d853 100644--- a/docs/setup/telemetry.md+++ b/docs/setup/telemetry.md@@ -14,7 +14,7 @@ When you use **Pipelex Gateway** as your inference backend, identified telemetry**What we collect:**-- Model names used (e.g., `gpt-5.2`, `claude-4.5-sonnet`) and parameters+- Model names used (e.g., `gpt-5.4`, `claude-4.5-sonnet`) and parameters- Pipe types (e.g., `PipeLLM`, `PipeSequence`, etc.)- Token counts (input/output)- Latency metricsdiff --git a/docs/under-the-hood/reasoning-controls.md b/docs/under-the-hood/reasoning-controls.mdindex 3bce89e39..a01c7edfd 100644--- a/docs/under-the-hood/reasoning-controls.md+++ b/docs/under-the-hood/reasoning-controls.md@@ -87,13 +87,13 @@ Effort maps to a `ThinkingLevel` enum sent to the Google SDK:model = { model = "gemini-3.1-pro", temperature = 0.3, reasoning_effort = "high" }```-**GPT-5.2 — manual mode**+**GPT-5.4 — manual mode**Effort maps directly to OpenAI's `reasoning_effort` parameter:```toml# Manual: effort "max" -> reasoning_effort = "xhigh" in the SDK call-model = { model = "gpt-5.2", temperature = 0.1, reasoning_effort = "max" }+model = { model = "gpt-5.4", temperature = 0.1, reasoning_effort = "max" }```!!! note "Structured Generation"diff --git a/pipelex/kit/configs/inference/backends/anthropic.toml b/pipelex/kit/configs/inference/backends/anthropic.tomlindex 1e00088a1..dbe8fd8cf 100644--- a/pipelex/kit/configs/inference/backends/anthropic.toml+++ b/pipelex/kit/configs/inference/backends/anthropic.toml@@ -147,6 +147,40 @@ max_tokens = 64000inputs = ["text", "images", "pdf"]outputs = ["text", "structured"]max_prompt_images = 100-costs = { input = 3.0, output = 15.0 }+costs = { input = 2.0, output = 10.0 }+thinking_mode = "adaptive"+listed_constraints = ["temperature_unsupported"]++[claude-5-opus]+model_id = "claude-opus-5"+max_tokens = 128000+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+max_prompt_images = 100+costs = { input = 5.0, output = 25.0 }+thinking_mode = "adaptive"+listed_constraints = ["temperature_unsupported"]++[claude-5-fable]+model_id = "claude-fable-5"+max_tokens = 128000+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+max_prompt_images = 100+costs = { input = 10.0, output = 50.0 }+thinking_mode = "adaptive"+listed_constraints = ["temperature_unsupported"]++# --- Claude 5.1 Series --------------------------------------------------------+["claude-5.1-fable"]+model_id = "claude-fable-5-1"+max_tokens = 128000+inputs = ["text", "images", "pdf"]+outputs = ["text", "structured"]+max_prompt_images = 100+costs = { input = 10.0, output = 50.0 }thinking_mode = "adaptive"+# Fable 5.1 refuses tool_choice "tool" and "any", which is what the section default+# instructor/anthropic_tools forces; the reasoning variant leaves tool_choice on auto.+structure_method = "instructor/anthropic_reasoning_tools"listed_constraints = ["temperature_unsupported"]diff --git a/pipelex/kit/configs/inference/backends/azure_openai.toml b/pipelex/kit/configs/inference/backends/azure_openai.tomlindex db9a0c183..7649888fe 100644--- a/pipelex/kit/configs/inference/backends/azure_openai.toml+++ b/pipelex/kit/configs/inference/backends/azure_openai.toml@@ -8,7 +8,7 @@## Configuration structure:# - Each model is defined in its own section with the model name as the header-# - Headers with dots must be quoted (e.g., ["gpt-4.1"])+# - Headers with dots must be quoted (e.g., ["gpt-5.4"])# - Model costs are in USD per million tokens (input/output)## Documentation: https://docs.pipelex.com@@ -43,140 +43,6 @@ inputs = ["text", "images"]outputs = ["text", "structured"]costs = { input = 0.15, output = 0.6 }-# --- GPT-4.1 Series ------------------------------------------------------------["gpt-4.1"]-model_id = "gpt-4.1-2025-04-14"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 2, output = 8 }--["gpt-4.1-mini"]-model_id = "gpt-4.1-mini-2025-04-14"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 0.4, output = 1.6 }--["gpt-4.1-nano"]-model_id = "gpt-4.1-nano-2025-04-14"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 0.1, output = 0.4 }--# --- o Series -----------------------------------------------------------------[o1-mini]-model_id = "o1-mini-2024-09-12"-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 3.0, output = 12.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[o1]-model_id = "o1-2024-12-17"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 15.0, output = 60.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[o3-mini]-model_id = "o3-mini-2025-01-31"-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 1.1, output = 4.4 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[o3]-model_id = "o3-2025-04-16"-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 2, output = 8 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--# --- GPT-5 Series --------------------------------------------------------------[gpt-5-mini]-model_id = "gpt-5-mini-2025-08-07"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 0.25, output = 2.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[gpt-5-nano]-model_id = "gpt-5-nano-2025-08-07"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 0.05, output = 0.4 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[gpt-5-chat]-model_id = "gpt-5-chat-2025-08-07"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[gpt-5]-model_id = "gpt-5-2025-08-07"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--# --- GPT-5.1 Series --------------------------------------------------------------["gpt-5.1"]-model_id = "gpt-5.1-2025-11-13"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--["gpt-5.1-chat"]-model_id = "gpt-5.1-chat-2025-11-13"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--["gpt-5.1-codex"]-model_id = "gpt-5.1-codex-2025-11-13"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--# --- GPT-5.2 Series --------------------------------------------------------------["gpt-5.2"]-model_id = "gpt-5.2-2025-12-11"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 1.75, output = 14.0 }-thinking_mode = "manual"--["gpt-5.2-chat"]-model_id = "gpt-5.2-chat-2025-12-11"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--["gpt-5.2-codex"]-model_id = "gpt-5.2-codex-2026-01-14"-inputs = ["text", "images"]-outputs = ["text", "structured"]-costs = { input = 1.75, output = 14.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"-# --- GPT-5.3 Series -------------------------------------------------------------["gpt-5.3-codex"]model_id = "gpt-5.3-codex-2026-02-24"diff --git a/pipelex/kit/configs/inference/backends/openai.toml b/pipelex/kit/configs/inference/backends/openai.tomlindex ef2ee7ccf..1bea020e0 100644--- a/pipelex/kit/configs/inference/backends/openai.toml+++ b/pipelex/kit/configs/inference/backends/openai.toml@@ -8,7 +8,7 @@## Configuration structure:# - Each model is defined in its own section with the model name as the header-# - Headers with dots must be quoted (e.g., ["gpt-4.1"])+# - Headers with dots must be quoted (e.g., ["gpt-5.4"])# - Model costs are in USD per million tokens (input/output)## Documentation: https://docs.pipelex.com@@ -30,178 +30,17 @@ thinking_mode = "none"# LANGUAGE MODELS################################################################################-# --- GPT-3.5 Series ------------------------------------------------------------["gpt-3.5-turbo"]-model_id = "gpt-3.5-turbo-1106"-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 0.5, output = 1.5 }--# --- GPT-4 Series --------------------------------------------------------------[gpt-4]-inputs = ["text"]-outputs = ["text"]-costs = { input = 30.0, output = 60.0 }--[gpt-4-turbo]-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 10.0, output = 30.0 }-# --- GPT-4o Series -------------------------------------------------------------[gpt-4o-2024-11-20]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 2.5, output = 10.0 }-[gpt-4o]inputs = ["text", "images", "pdf"]outputs = ["text", "structured"]costs = { input = 2.5, output = 10.0 }-[gpt-4o-mini-2024-07-18]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 0.15, output = 0.6 }-[gpt-4o-mini]inputs = ["text", "images", "pdf"]outputs = ["text", "structured"]costs = { input = 0.15, output = 0.6 }-# --- GPT-4.1 Series ------------------------------------------------------------["gpt-4.1"]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 2, output = 8 }--["gpt-4.1-mini"]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 0.4, output = 1.6 }--["gpt-4.1-nano"]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 0.1, output = 0.4 }--# --- o Series -----------------------------------------------------------------[o1]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 15.0, output = 60.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[o3-mini]-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 1.1, output = 4.4 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[o3]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 10.0, output = 40.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[o4-mini]-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 1.1, output = 4.4 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--# --- GPT-5 Series --------------------------------------------------------------[gpt-5]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[gpt-5-mini]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 0.25, output = 2.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[gpt-5-nano]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 0.05, output = 0.4 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[gpt-5-chat]-model_id = "gpt-5-chat-latest"-inputs = ["text", "images", "pdf"]-outputs = ["text"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--[gpt-5-codex]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--# --- GPT-5.1 Series --------------------------------------------------------------["gpt-5.1"]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-thinking_mode = "manual"--["gpt-5.1-chat"]-model_id = "gpt-5.1-chat-latest"-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--["gpt-5.1-codex"]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--["gpt-5.1-codex-max"]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.25, output = 10.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--# --- GPT-5.2 Series --------------------------------------------------------------["gpt-5.2"]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.75, output = 14.0 }-thinking_mode = "manual"--["gpt-5.2-chat"]-model_id = "gpt-5.2-chat-latest"-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.75, output = 14.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"--["gpt-5.2-codex"]-inputs = ["text", "images", "pdf"]-outputs = ["text", "structured"]-costs = { input = 1.75, output = 14.0 }-valued_constraints = { fixed_temperature = 1 }-thinking_mode = "manual"-# --- GPT-5.3 Series -------------------------------------------------------------["gpt-5.3-codex"]inputs = ["text", "images", "pdf"]diff --git a/pipelex/kit/configs/inference/backends/portkey.toml b/pipelex/kit/configs/inference/backends/portkey.tomlindex e17965a09..f46825eb1 100644--- a/pipelex/kit/configs/inference/backends/portkey.toml+++ b/pipelex/kit/configs/inference/backends/portkey.toml@@ -105,16 +105,6 @@ structure_method = "instructor/openai_responses_tools"thinking_mode = "manual"x-portkey-provider = "@openai"-[o4-mini]-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 1.1, output = 4.4 }-valued_constraints = { fixed_temperature = 1 }-sdk = "portkey_responses"-structure_method = "instructor/openai_responses_tools"-thinking_mode = "manual"-x-portkey-provider = "@openai"-[gpt-5-nano]inputs = ["text", "images", "pdf"]outputs = ["text", "structured"]diff --git a/pipelex/kit/configs/inference/deck/x_custom_llm_deck.toml b/pipelex/kit/configs/inference/deck/x_custom_llm_deck.tomlindex 5ad13b82b..d751552d1 100644--- a/pipelex/kit/configs/inference/deck/x_custom_llm_deck.toml+++ b/pipelex/kit/configs/inference/deck/x_custom_llm_deck.toml@@ -35,23 +35,23 @@ for_object = "disabled"# Example (uncomment to use):# [llm.waterfalls]-# premium-llm = ["claude-4.5-opus", "gemini-3.1-pro", "gpt-5.2", "grok-4"]+# premium-llm = ["claude-4.5-opus", "gemini-3.1-pro", "gpt-5.4", "grok-4"]# premium-llm-vision = [# "claude-4.5-opus",# "gemini-3.1-pro",-# "gpt-5.2",+# "gpt-5.4",# "grok-4-fast-reasoning",# ]# premium-llm-structured = [# "claude-4.5-opus",# "gemini-3.1-pro",-# "gpt-5.2",+# "gpt-5.4",# "grok-4",# ]# large-context-llm-code = [# "gemini-3.1-pro",# "claude-4.5-opus",-# "gpt-5.2",+# "gpt-5.4",# "grok-4-fast-reasoning",# ]# large-context-llm-text = ["gemini-2.5-flash", "claude-4.5-sonnet"]diff --git a/pipelex/kit/configs/inference/routing_profiles.toml b/pipelex/kit/configs/inference/routing_profiles.tomlindex 2fd6781aa..57407e0a6 100644--- a/pipelex/kit/configs/inference/routing_profiles.toml+++ b/pipelex/kit/configs/inference/routing_profiles.toml@@ -152,10 +152,10 @@ default = "pipelex_gateway"description = "Example routing profile using specific models"[profiles.example_routing_using_specific_models.routes]-"gpt-5-nano" = "pipelex_gateway"+"gpt-5.4-nano" = "pipelex_gateway""gpt-4o-mini" = "blackboxai"-"gpt-5-mini" = "openai"-"gpt-5-chat" = "azure_openai"+"gpt-5.4-mini" = "openai"+"gpt-5.5" = "azure_openai""claude-4-sonnet" = "pipelex_gateway""claude-3.7-sonnet" = "blackboxai"diff --git a/pipelex/migration/goldens/inference-backend/[email protected] b/pipelex/migration/goldens/inference-backend/[email protected]index e17965a09..f46825eb1 100644--- a/pipelex/migration/goldens/inference-backend/[email protected]+++ b/pipelex/migration/goldens/inference-backend/[email protected]@@ -105,16 +105,6 @@ structure_method = "instructor/openai_responses_tools"thinking_mode = "manual"x-portkey-provider = "@openai"-[o4-mini]-inputs = ["text"]-outputs = ["text", "structured"]-costs = { input = 1.1, output = 4.4 }-valued_constraints = { fixed_temperature = 1 }-sdk = "portkey_responses"-structure_method = "instructor/openai_responses_tools"-thinking_mode = "manual"-x-portkey-provider = "@openai"-[gpt-5-nano]inputs = ["text", "images", "pdf"]outputs = ["text", "structured"]diff --git a/tests/unit/pipelex/cogt/model_backends/test_backend_boot_tolerance.py b/tests/unit/pipelex/cogt/model_backends/test_backend_boot_tolerance.pyindex 81453b213..343044243 100644--- a/tests/unit/pipelex/cogt/model_backends/test_backend_boot_tolerance.py+++ b/tests/unit/pipelex/cogt/model_backends/test_backend_boot_tolerance.py@@ -233,8 +233,8 @@ class TestAStaleBackendDirectory:they can act on; "migration did not help" would name nothing."""openai_file = self._backends_dir(machine) / "openai.toml"- plant_on_model(path=openai_file, table_header='["gpt-3.5-turbo"]', key="foo", value="1")- plant_on_model(path=openai_file, table_header="[gpt-4o]")+ plant_on_model(path=openai_file, table_header="[gpt-4o]", key="foo", value="1")+ plant_on_model(path=openai_file, table_header='["gpt-5.5"]')retry = mocker.spy(InferenceBackendLibrary, "_local_model_specs_the_ledger_can_explain")with pytest.raises(InferenceBackendLibraryError) as exc_info: