Release/v0.0.12

.env.example

@@ -1,2 +1,2 @@
 API_KEY=
-PIPELEX_INFERENCE_API_KEY=
+PIPELEX_GATEWAY_API_KEY=

.pipelex/inference/backends.toml

@@ -10,16 +10,14 @@
 #
 ####################################################################################################
 
-[pipelex_inference]
-display_name = "⭐ Pipelex Inference"
-enabled = true
-endpoint = "https://inference.pipelex.com/v1"
-api_key = "${PIPELEX_INFERENCE_API_KEY}"
+[pipelex_gateway]
+display_name = "⭐ Pipelex Gateway"
+enabled = true                         # Enable after accepting terms via `pipelex init config`
+api_key = "${PIPELEX_GATEWAY_API_KEY}"
 
 [anthropic]
 enabled = false
 api_key = "${ANTHROPIC_API_KEY}"
-claude_4_tokens_limit = 8192
 
 [azure_openai]
 display_name = "Azure OpenAI"
@@ -55,6 +53,11 @@ enabled = false
 endpoint = "https://api.groq.com/openai/v1"
 api_key = "${GROQ_API_KEY}"
 
+[huggingface]
+display_name = "Hugging Face"
+enabled = false
+api_key = "${HF_TOKEN}"
+
 [mistral]
 display_name = "Mistral AI"
 enabled = false
@@ -69,9 +72,21 @@ display_name = "OpenAI"
 enabled = false
 api_key = "${OPENAI_API_KEY}"
 
+[portkey]
+display_name = "Portkey"
+enabled = false
+endpoint = "https://api.portkey.ai/v1"
+api_key = "${PORTKEY_API_KEY}"
+
+[scaleway]
+display_name = "Scaleway"
+enabled = false
+endpoint = "${SCALEWAY_ENDPOINT}"
+api_key = "${SCALEWAY_API_KEY}"
+
 [vertexai]
 display_name = "Google Vertex AI"
-enabled = false
+enabled = false                                            # This is the only one we disable beacuse setting it up requires internet access just to get credentials so it fails in CI sandboxes
 gcp_project_id = "${GCP_PROJECT_ID}"
 gcp_location = "${GCP_LOCATION}"
 gcp_credentials_file_path = "${GCP_CREDENTIALS_FILE_PATH}"
@@ -84,3 +99,10 @@ api_key = "${XAI_API_KEY}"
 
 [internal] # software-only backend, runs internally, without AI
 enabled = true
+
+# Deprecated
+[pipelex_inference]
+display_name = "🛑 Legacy Pipelex Inference"
+enabled = false
+endpoint = "https://inference.pipelex.com/v1"
+api_key = "${PIPELEX_INFERENCE_API_KEY}"

.pipelex/inference/backends/anthropic.toml

@@ -39,19 +39,11 @@ outputs = ["text", "structured"]
 max_prompt_images = 100
 costs = { input = 0.25, output = 1.25 }
 
-[claude-3-opus]
-model_id = "claude-3-opus-20240229"
-max_tokens = 4096
-inputs = ["text", "images"]
-outputs = ["text", "structured"]
-max_prompt_images = 100
-costs = { input = 15.0, output = 75.0 }
-
 # --- Claude 3.7 Series --------------------------------------------------------
 ["claude-3.7-sonnet"]
 model_id = "claude-3-7-sonnet-20250219"
 max_tokens = 8192
-inputs = ["text", "images"]
+inputs = ["text", "images", "pdf"]
 outputs = ["text", "structured"]
 max_prompt_images = 100
 costs = { input = 3.0, output = 15.0 }
@@ -60,15 +52,15 @@ costs = { input = 3.0, output = 15.0 }
 [claude-4-sonnet]
 model_id = "claude-sonnet-4-20250514"
 max_tokens = 64000
-inputs = ["text", "images"]
+inputs = ["text", "images", "pdf"]
 outputs = ["text", "structured"]
 max_prompt_images = 100
 costs = { input = 3.0, output = 15.0 }
 
 [claude-4-opus]
 model_id = "claude-opus-4-20250514"
 max_tokens = 32000
-inputs = ["text", "images"]
+inputs = ["text", "images", "pdf"]
 outputs = ["text", "structured"]
 max_prompt_images = 100
 costs = { input = 3.0, output = 15.0 }
@@ -77,7 +69,7 @@ costs = { input = 3.0, output = 15.0 }
 ["claude-4.1-opus"]
 model_id = "claude-opus-4-1-20250805"
 max_tokens = 32000
-inputs = ["text", "images"]
+inputs = ["text", "images", "pdf"]
 outputs = ["text", "structured"]
 max_prompt_images = 100
 costs = { input = 3.0, output = 15.0 }
@@ -86,15 +78,23 @@ costs = { input = 3.0, output = 15.0 }
 ["claude-4.5-sonnet"]
 model_id = "claude-sonnet-4-5-20250929"
 max_tokens = 64000
-inputs = ["text", "images"]
+inputs = ["text", "images", "pdf"]
 outputs = ["text", "structured"]
 max_prompt_images = 100
 costs = { input = 3.0, output = 15.0 }
 
 ["claude-4.5-haiku"]
 model_id = "claude-haiku-4-5-20251001"
 max_tokens = 64000
-inputs = ["text", "images"]
+inputs = ["text", "images", "pdf"]
 outputs = ["text", "structured"]
 max_prompt_images = 100
 costs = { input = 1.0, output = 5.0 }
+
+["claude-4.5-opus"]
+model_id = "claude-opus-4-5-20251101"
+max_tokens = 64000
+inputs = ["text", "images", "pdf"]
+outputs = ["text", "structured"]
+max_prompt_images = 100
+costs = { input = 5.0, output = 25.0 }

.pipelex/inference/backends/azure_openai.toml

@@ -22,9 +22,9 @@
 
 [defaults]
 model_type = "llm"
-sdk = "azure_openai"
+sdk = "azure_openai_responses"
 prompting_target = "openai"
-structure_method = "instructor/openai_tools"
+structure_method = "instructor/openai_responses_tools"
 
 ################################################################################
 # LANGUAGE MODELS
@@ -68,62 +68,146 @@ model_id = "o1-mini-2024-09-12"
 inputs = ["text"]
 outputs = ["text", "structured"]
 costs = { input = 3.0, output = 12.0 }
-constraints = ["temperature_must_be_1"]
+valued_constraints = { fixed_temperature = 1 }
 
 [o1]
 model_id = "o1-2024-12-17"
 inputs = ["text", "images"]
 outputs = ["text", "structured"]
 costs = { input = 15.0, output = 60.0 }
-constraints = ["temperature_must_be_1"]
+valued_constraints = { fixed_temperature = 1 }
 
 [o3-mini]
 model_id = "o3-mini-2025-01-31"
 inputs = ["text"]
 outputs = ["text", "structured"]
 costs = { input = 1.1, output = 4.4 }
-constraints = ["temperature_must_be_1"]
+valued_constraints = { fixed_temperature = 1 }
 
 [o3]
 model_id = "o3-2025-04-16"
 inputs = ["text"]
 outputs = ["text", "structured"]
 costs = { input = 2, output = 8 }
-constraints = ["temperature_must_be_1"]
+valued_constraints = { fixed_temperature = 1 }
 
 # --- 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 }
 
 [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 }
 
 [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 }
 
 [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 }
+
+# --- 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 }
+
+["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 }
+
+["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 }
+
+# --- 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 }
+
+["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 }
 
 ################################################################################
 # IMAGE GENERATION MODELS
 ################################################################################
 
 # --- OpenAI Image Generation --------------------------------------------------
 [gpt-image-1]
+sdk = "azure_rest_img_gen"
 model_type = "img_gen"
 model_id = "gpt-image-1-2025-04-15"
 inputs = ["text"]
 outputs = ["image"]
-costs = { input = 0.04, output = 0.0 }
+costs = { input = 10, output = 40 }
+
+[gpt-image-1.rules]
+prompt = "positive_only"
+num_images = "gpt"
+aspect_ratio = "gpt"
+background = "gpt"
+inference = "gpt"
+safety_checker = "unavailable"
+output_format = "gpt"
+
+[gpt-image-1-mini]
+sdk = "azure_rest_img_gen"
+model_type = "img_gen"
+model_id = "gpt-image-1-mini-2025-10-06"
+inputs = ["text"]
+outputs = ["image"]
+costs = { input = 2.5, output = 8 }
+
+[gpt-image-1-mini.rules]
+prompt = "positive_only"
+num_images = "gpt"
+aspect_ratio = "gpt"
+background = "gpt"
+inference = "gpt"
+safety_checker = "unavailable"
+output_format = "gpt"
+
+["gpt-image-1.5"]
+sdk = "azure_rest_img_gen"
+model_type = "img_gen"
+model_id = "gpt-image-1.5-2025-12-16"
+inputs = ["text"]
+outputs = ["image"]
+costs = { input = 8, output = 32 }
+
+["gpt-image-1.5".rules]
+prompt = "positive_only"
+num_images = "gpt"
+aspect_ratio = "gpt"
+background = "gpt"
+inference = "gpt"
+safety_checker = "unavailable"
+output_format = "gpt"

.pipelex/inference/backends/bedrock.toml

@@ -60,7 +60,7 @@ costs = { input = 3.0, output = 15.0 }
 sdk = "bedrock_anthropic"
 model_id = "us.anthropic.claude-3-7-sonnet-20250219-v1:0"
 max_tokens = 8192
-inputs = ["text", "images"]
+inputs = ["text", "images", "pdf"]
 outputs = ["text", "structured"]
 max_prompt_images = 100
 costs = { input = 3.0, output = 15.0 }
@@ -69,7 +69,7 @@ costs = { input = 3.0, output = 15.0 }
 sdk = "bedrock_anthropic"
 model_id = "us.anthropic.claude-sonnet-4-20250514-v1:0"
 max_tokens = 64000
-inputs = ["text", "images"]
+inputs = ["text", "images", "pdf"]
 outputs = ["text", "structured"]
 max_prompt_images = 100
 costs = { input = 3.0, output = 15.0 }
@@ -78,7 +78,7 @@ costs = { input = 3.0, output = 15.0 }
 sdk = "bedrock_anthropic"
 model_id = "us.anthropic.claude-opus-4-20250514-v1:0"
 max_tokens = 32000
-inputs = ["text", "images"]
+inputs = ["text", "images", "pdf"]
 outputs = ["text", "structured"]
 max_prompt_images = 100
 costs = { input = 3.0, output = 15.0 }
@@ -87,25 +87,34 @@ costs = { input = 3.0, output = 15.0 }
 sdk = "bedrock_anthropic"
 model_id = "us.anthropic.claude-opus-4-1-20250805-v1:0"
 max_tokens = 32000
-inputs = ["text", "images"]
+inputs = ["text", "images", "pdf"]
 outputs = ["text", "structured"]
 max_prompt_images = 100
 costs = { input = 3.0, output = 15.0 }
 
 ["claude-4.5-sonnet"]
 sdk = "bedrock_anthropic"
 model_id = "us.anthropic.claude-sonnet-4-5-20250929-v1:0"
-max_tokens = 8192
-inputs = ["text", "images"]
+max_tokens = 64000
+inputs = ["text", "images", "pdf"]
 outputs = ["text", "structured"]
 max_prompt_images = 100
 costs = { input = 3.0, output = 15.0 }
 
 ["claude-4.5-haiku"]
 sdk = "bedrock_anthropic"
 model_id = "us.anthropic.claude-haiku-4-5-20251001-v1:0"
-max_tokens = 8192
-inputs = ["text", "images"]
+max_tokens = 64000
+inputs = ["text", "images", "pdf"]
 outputs = ["text", "structured"]
 max_prompt_images = 100
 costs = { input = 1.0, output = 5.0 }
+
+["claude-4.5-opus"]
+sdk = "bedrock_anthropic"
+model_id = "global.anthropic.claude-opus-4-5-20251101-v1:0"
+max_tokens = 64000
+inputs = ["text", "images", "pdf"]
+outputs = ["text", "structured"]
+max_prompt_images = 100
+costs = { input = 5.0, output = 25.0 }