feat!: standardize base_url for inference

docs/docs/providers/inference/remote_azure.mdx

@@ -24,15 +24,15 @@ https://learn.microsoft.com/en-us/azure/ai-foundry/openai/overview
 | `allowed_models` | `list[str] \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `bool` | No | False | Whether to refresh models periodically from the provider |
 | `api_key` | `SecretStr \| None` | No |  | Authentication credential for the provider |
-| `api_base` | `HttpUrl` | No |  | Azure API base for Azure (e.g., https://your-resource-name.openai.azure.com) |
+| `base_url` | `HttpUrl \| None` | No |  | Azure API base for Azure (e.g., https://your-resource-name.openai.azure.com/openai/v1) |
 | `api_version` | `str \| None` | No |  | Azure API version for Azure (e.g., 2024-12-01-preview) |
 | `api_type` | `str \| None` | No | azure | Azure API type for Azure (e.g., azure) |
 
 ## Sample Configuration
 
 ```yaml
 api_key: ${env.AZURE_API_KEY:=}
-api_base: ${env.AZURE_API_BASE:=}
+base_url: ${env.AZURE_API_BASE:=}
 api_version: ${env.AZURE_API_VERSION:=}
 api_type: ${env.AZURE_API_TYPE:=}
 ```

docs/docs/providers/inference/remote_cerebras.mdx

@@ -17,11 +17,11 @@ Cerebras inference provider for running models on Cerebras Cloud platform.
 | `allowed_models` | `list[str] \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `bool` | No | False | Whether to refresh models periodically from the provider |
 | `api_key` | `SecretStr \| None` | No |  | Authentication credential for the provider |
-| `base_url` | `str` | No | https://api.cerebras.ai | Base URL for the Cerebras API |
+| `base_url` | `HttpUrl \| None` | No | https://api.cerebras.ai/v1 | Base URL for the Cerebras API |
 
 ## Sample Configuration
 
 ```yaml
-base_url: https://api.cerebras.ai
+base_url: https://api.cerebras.ai/v1
 api_key: ${env.CEREBRAS_API_KEY:=}
 ```

docs/docs/providers/inference/remote_databricks.mdx

@@ -17,11 +17,11 @@ Databricks inference provider for running models on Databricks' unified analytic
 | `allowed_models` | `list[str] \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `bool` | No | False | Whether to refresh models periodically from the provider |
 | `api_token` | `SecretStr \| None` | No |  | The Databricks API token |
-| `url` | `str \| None` | No |  | The URL for the Databricks model serving endpoint |
+| `base_url` | `HttpUrl \| None` | No |  | The URL for the Databricks model serving endpoint (should include /serving-endpoints path) |
 
 ## Sample Configuration
 
 ```yaml
-url: ${env.DATABRICKS_HOST:=}
+base_url: ${env.DATABRICKS_HOST:=}
 api_token: ${env.DATABRICKS_TOKEN:=}
 ```

docs/docs/providers/inference/remote_fireworks.mdx

@@ -17,11 +17,11 @@ Fireworks AI inference provider for Llama models and other AI models on the Fire
 | `allowed_models` | `list[str] \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `bool` | No | False | Whether to refresh models periodically from the provider |
 | `api_key` | `SecretStr \| None` | No |  | Authentication credential for the provider |
-| `url` | `str` | No | https://api.fireworks.ai/inference/v1 | The URL for the Fireworks server |
+| `base_url` | `HttpUrl \| None` | No | https://api.fireworks.ai/inference/v1 | The URL for the Fireworks server |
 
 ## Sample Configuration
 
 ```yaml
-url: https://api.fireworks.ai/inference/v1
+base_url: https://api.fireworks.ai/inference/v1
 api_key: ${env.FIREWORKS_API_KEY:=}
 ```

docs/docs/providers/inference/remote_groq.mdx

@@ -17,11 +17,11 @@ Groq inference provider for ultra-fast inference using Groq's LPU technology.
 | `allowed_models` | `list[str] \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `bool` | No | False | Whether to refresh models periodically from the provider |
 | `api_key` | `SecretStr \| None` | No |  | Authentication credential for the provider |
-| `url` | `str` | No | https://api.groq.com | The URL for the Groq AI server |
+| `base_url` | `HttpUrl \| None` | No | https://api.groq.com/openai/v1 | The URL for the Groq AI server |
 
 ## Sample Configuration
 
 ```yaml
-url: https://api.groq.com
+base_url: https://api.groq.com/openai/v1
 api_key: ${env.GROQ_API_KEY:=}
 ```

docs/docs/providers/inference/remote_llama-openai-compat.mdx

@@ -17,11 +17,11 @@ Llama OpenAI-compatible provider for using Llama models with OpenAI API format.
 | `allowed_models` | `list[str] \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `bool` | No | False | Whether to refresh models periodically from the provider |
 | `api_key` | `SecretStr \| None` | No |  | Authentication credential for the provider |
-| `openai_compat_api_base` | `str` | No | https://api.llama.com/compat/v1/ | The URL for the Llama API server |
+| `base_url` | `HttpUrl \| None` | No | https://api.llama.com/compat/v1/ | The URL for the Llama API server |
 
 ## Sample Configuration
 
 ```yaml
-openai_compat_api_base: https://api.llama.com/compat/v1/
+base_url: https://api.llama.com/compat/v1/
 api_key: ${env.LLAMA_API_KEY}
 ```

docs/docs/providers/inference/remote_nvidia.mdx

@@ -17,15 +17,13 @@ NVIDIA inference provider for accessing NVIDIA NIM models and AI services.
 | `allowed_models` | `list[str] \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `bool` | No | False | Whether to refresh models periodically from the provider |
 | `api_key` | `SecretStr \| None` | No |  | Authentication credential for the provider |
-| `url` | `str` | No | https://integrate.api.nvidia.com | A base url for accessing the NVIDIA NIM |
+| `base_url` | `HttpUrl \| None` | No | https://integrate.api.nvidia.com/v1 | A base url for accessing the NVIDIA NIM |
 | `timeout` | `int` | No | 60 | Timeout for the HTTP requests |
-| `append_api_version` | `bool` | No | True | When set to false, the API version will not be appended to the base_url. By default, it is true. |
 | `rerank_model_to_url` | `dict[str, str]` | No | `{'nv-rerank-qa-mistral-4b:1': 'https://ai.api.nvidia.com/v1/retrieval/nvidia/reranking', 'nvidia/nv-rerankqa-mistral-4b-v3': 'https://ai.api.nvidia.com/v1/retrieval/nvidia/nv-rerankqa-mistral-4b-v3/reranking', 'nvidia/llama-3.2-nv-rerankqa-1b-v2': 'https://ai.api.nvidia.com/v1/retrieval/nvidia/llama-3_2-nv-rerankqa-1b-v2/reranking'}` | Mapping of rerank model identifiers to their API endpoints.  |
 
 ## Sample Configuration
 
 ```yaml
-url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
+base_url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com/v1}
 api_key: ${env.NVIDIA_API_KEY:=}
-append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
 ```

docs/docs/providers/inference/remote_ollama.mdx

@@ -16,10 +16,10 @@ Ollama inference provider for running local models through the Ollama runtime.
 |-------|------|----------|---------|-------------|
 | `allowed_models` | `list[str] \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `bool` | No | False | Whether to refresh models periodically from the provider |
-| `url` | `str` | No | http://localhost:11434 |  |
+| `base_url` | `HttpUrl \| None` | No | http://localhost:11434/v1 |  |
 
 ## Sample Configuration
 
 ```yaml
-url: ${env.OLLAMA_URL:=http://localhost:11434}
+base_url: ${env.OLLAMA_URL:=http://localhost:11434/v1}
 ```

docs/docs/providers/inference/remote_openai.mdx

@@ -17,7 +17,7 @@ OpenAI inference provider for accessing GPT models and other OpenAI services.
 | `allowed_models` | `list[str] \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `bool` | No | False | Whether to refresh models periodically from the provider |
 | `api_key` | `SecretStr \| None` | No |  | Authentication credential for the provider |
-| `base_url` | `str` | No | https://api.openai.com/v1 | Base URL for OpenAI API |
+| `base_url` | `HttpUrl \| None` | No | https://api.openai.com/v1 | Base URL for OpenAI API |
 
 ## Sample Configuration
 

docs/docs/providers/inference/remote_passthrough.mdx

@@ -17,11 +17,11 @@ Passthrough inference provider for connecting to any external inference service
 | `allowed_models` | `list[str] \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `bool` | No | False | Whether to refresh models periodically from the provider |
 | `api_key` | `SecretStr \| None` | No |  | Authentication credential for the provider |
-| `url` | `str` | No |  | The URL for the passthrough endpoint |
+| `base_url` | `HttpUrl \| None` | No |  | The URL for the passthrough endpoint |
 
 ## Sample Configuration
 
 ```yaml
-url: ${env.PASSTHROUGH_URL}
+base_url: ${env.PASSTHROUGH_URL}
 api_key: ${env.PASSTHROUGH_API_KEY}
 ```

docs/docs/providers/inference/remote_runpod.mdx

@@ -17,11 +17,11 @@ RunPod inference provider for running models on RunPod's cloud GPU platform.
 | `allowed_models` | `list[str] \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `bool` | No | False | Whether to refresh models periodically from the provider |
 | `api_token` | `SecretStr \| None` | No |  | The API token |
-| `url` | `str \| None` | No |  | The URL for the Runpod model serving endpoint |
+| `base_url` | `HttpUrl \| None` | No |  | The URL for the Runpod model serving endpoint |
 
 ## Sample Configuration
 
 ```yaml
-url: ${env.RUNPOD_URL:=}
+base_url: ${env.RUNPOD_URL:=}
 api_token: ${env.RUNPOD_API_TOKEN}
 ```

docs/docs/providers/inference/remote_sambanova.mdx

@@ -17,11 +17,11 @@ SambaNova inference provider for running models on SambaNova's dataflow architec
 | `allowed_models` | `list[str] \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `bool` | No | False | Whether to refresh models periodically from the provider |
 | `api_key` | `SecretStr \| None` | No |  | Authentication credential for the provider |
-| `url` | `str` | No | https://api.sambanova.ai/v1 | The URL for the SambaNova AI server |
+| `base_url` | `HttpUrl \| None` | No | https://api.sambanova.ai/v1 | The URL for the SambaNova AI server |
 
 ## Sample Configuration
 
 ```yaml
-url: https://api.sambanova.ai/v1
+base_url: https://api.sambanova.ai/v1
 api_key: ${env.SAMBANOVA_API_KEY:=}
 ```

docs/docs/providers/inference/remote_tgi.mdx

@@ -16,10 +16,10 @@ Text Generation Inference (TGI) provider for HuggingFace model serving.
 |-------|------|----------|---------|-------------|
 | `allowed_models` | `list[str] \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `bool` | No | False | Whether to refresh models periodically from the provider |
-| `url` | `str` | No |  | The URL for the TGI serving endpoint |
+| `base_url` | `HttpUrl \| None` | No |  | The URL for the TGI serving endpoint (should include /v1 path) |
 
 ## Sample Configuration
 
 ```yaml
-url: ${env.TGI_URL:=}
+base_url: ${env.TGI_URL:=}
 ```

docs/docs/providers/inference/remote_together.mdx

@@ -17,11 +17,11 @@ Together AI inference provider for open-source models and collaborative AI devel
 | `allowed_models` | `list[str] \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `bool` | No | False | Whether to refresh models periodically from the provider |
 | `api_key` | `SecretStr \| None` | No |  | Authentication credential for the provider |
-| `url` | `str` | No | https://api.together.xyz/v1 | The URL for the Together AI server |
+| `base_url` | `HttpUrl \| None` | No | https://api.together.xyz/v1 | The URL for the Together AI server |
 
 ## Sample Configuration
 
 ```yaml
-url: https://api.together.xyz/v1
+base_url: https://api.together.xyz/v1
 api_key: ${env.TOGETHER_API_KEY:=}
 ```

docs/docs/providers/inference/remote_vllm.mdx

@@ -17,14 +17,14 @@ Remote vLLM inference provider for connecting to vLLM servers.
 | `allowed_models` | `list[str] \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `bool` | No | False | Whether to refresh models periodically from the provider |
 | `api_token` | `SecretStr \| None` | No |  | The API token |
-| `url` | `str \| None` | No |  | The URL for the vLLM model serving endpoint |
+| `base_url` | `HttpUrl \| None` | No |  | The URL for the vLLM model serving endpoint |
 | `max_tokens` | `int` | No | 4096 | Maximum number of tokens to generate. |
 | `tls_verify` | `bool \| str` | No | True | Whether to verify TLS certificates. Can be a boolean or a path to a CA certificate file. |
 
 ## Sample Configuration
 
 ```yaml
-url: ${env.VLLM_URL:=}
+base_url: ${env.VLLM_URL:=}
 max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
 api_token: ${env.VLLM_API_TOKEN:=fake}
 tls_verify: ${env.VLLM_TLS_VERIFY:=true}

docs/docs/providers/inference/remote_watsonx.mdx

@@ -17,14 +17,14 @@ IBM WatsonX inference provider for accessing AI models on IBM's WatsonX platform
 | `allowed_models` | `list[str] \| None` | No |  | List of models that should be registered with the model registry. If None, all models are allowed. |
 | `refresh_models` | `bool` | No | False | Whether to refresh models periodically from the provider |
 | `api_key` | `SecretStr \| None` | No |  | Authentication credential for the provider |
-| `url` | `str` | No | https://us-south.ml.cloud.ibm.com | A base url for accessing the watsonx.ai |
+| `base_url` | `HttpUrl \| None` | No | https://us-south.ml.cloud.ibm.com | A base url for accessing the watsonx.ai |
 | `project_id` | `str \| None` | No |  | The watsonx.ai project ID |
 | `timeout` | `int` | No | 60 | Timeout for the HTTP requests |
 
 ## Sample Configuration
 
 ```yaml
-url: ${env.WATSONX_BASE_URL:=https://us-south.ml.cloud.ibm.com}
+base_url: ${env.WATSONX_BASE_URL:=https://us-south.ml.cloud.ibm.com}
 api_key: ${env.WATSONX_API_KEY:=}
 project_id: ${env.WATSONX_PROJECT_ID:=}
 ```

scripts/docker.sh

@@ -287,9 +287,9 @@ start_container() {
     # On macOS/Windows, use host.docker.internal to reach host from container
     # On Linux with --network host, use localhost
     if [[ "$(uname)" == "Darwin" ]] || [[ "$(uname)" == *"MINGW"* ]]; then
-        OLLAMA_URL="${OLLAMA_URL:-http://host.docker.internal:11434}"
+        OLLAMA_URL="${OLLAMA_URL:-http://host.docker.internal:11434/v1}"
     else
-        OLLAMA_URL="${OLLAMA_URL:-http://localhost:11434}"
+        OLLAMA_URL="${OLLAMA_URL:-http://localhost:11434/v1}"
     fi
     DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OLLAMA_URL=$OLLAMA_URL"
 

scripts/install.sh

@@ -640,7 +640,7 @@ cmd=( run -d "${PLATFORM_OPTS[@]}" --name llama-stack \
       --network llama-net \
       -p "${PORT}:${PORT}" \
       "${server_env_opts[@]}" \
-      -e OLLAMA_URL="http://ollama-server:${OLLAMA_PORT}" \
+      -e OLLAMA_URL="http://ollama-server:${OLLAMA_PORT}/v1" \
       "${SERVER_IMAGE}" --port "${PORT}")
 
 log "🦙 Starting Llama Stack..."

src/llama_stack/distributions/ci-tests/run-with-postgres-store.yaml

@@ -17,32 +17,32 @@ providers:
   - provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
     provider_type: remote::cerebras
     config:
-      base_url: https://api.cerebras.ai
+      base_url: https://api.cerebras.ai/v1
       api_key: ${env.CEREBRAS_API_KEY:=}
   - provider_id: ${env.OLLAMA_URL:+ollama}
     provider_type: remote::ollama
     config:
-      url: ${env.OLLAMA_URL:=http://localhost:11434}
+      base_url: ${env.OLLAMA_URL:=http://localhost:11434/v1}
   - provider_id: ${env.VLLM_URL:+vllm}
     provider_type: remote::vllm
     config:
-      url: ${env.VLLM_URL:=}
+      base_url: ${env.VLLM_URL:=}
       max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
       api_token: ${env.VLLM_API_TOKEN:=fake}
       tls_verify: ${env.VLLM_TLS_VERIFY:=true}
   - provider_id: ${env.TGI_URL:+tgi}
     provider_type: remote::tgi
     config:
-      url: ${env.TGI_URL:=}
+      base_url: ${env.TGI_URL:=}
   - provider_id: fireworks
     provider_type: remote::fireworks
     config:
-      url: https://api.fireworks.ai/inference/v1
+      base_url: https://api.fireworks.ai/inference/v1
       api_key: ${env.FIREWORKS_API_KEY:=}
   - provider_id: together
     provider_type: remote::together
     config:
-      url: https://api.together.xyz/v1
+      base_url: https://api.together.xyz/v1
       api_key: ${env.TOGETHER_API_KEY:=}
   - provider_id: bedrock
     provider_type: remote::bedrock
@@ -52,9 +52,8 @@ providers:
   - provider_id: ${env.NVIDIA_API_KEY:+nvidia}
     provider_type: remote::nvidia
     config:
-      url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
+      base_url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com/v1}
       api_key: ${env.NVIDIA_API_KEY:=}
-      append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
   - provider_id: openai
     provider_type: remote::openai
     config:
@@ -76,18 +75,18 @@ providers:
   - provider_id: groq
     provider_type: remote::groq
     config:
-      url: https://api.groq.com
+      base_url: https://api.groq.com/openai/v1
       api_key: ${env.GROQ_API_KEY:=}
   - provider_id: sambanova
     provider_type: remote::sambanova
     config:
-      url: https://api.sambanova.ai/v1
+      base_url: https://api.sambanova.ai/v1
       api_key: ${env.SAMBANOVA_API_KEY:=}
   - provider_id: ${env.AZURE_API_KEY:+azure}
     provider_type: remote::azure
     config:
       api_key: ${env.AZURE_API_KEY:=}
-      api_base: ${env.AZURE_API_BASE:=}
+      base_url: ${env.AZURE_API_BASE:=}
       api_version: ${env.AZURE_API_VERSION:=}
       api_type: ${env.AZURE_API_TYPE:=}
   - provider_id: sentence-transformers

src/llama_stack/distributions/ci-tests/run.yaml

@@ -17,32 +17,32 @@ providers:
   - provider_id: ${env.CEREBRAS_API_KEY:+cerebras}
     provider_type: remote::cerebras
     config:
-      base_url: https://api.cerebras.ai
+      base_url: https://api.cerebras.ai/v1
       api_key: ${env.CEREBRAS_API_KEY:=}
   - provider_id: ${env.OLLAMA_URL:+ollama}
     provider_type: remote::ollama
     config:
-      url: ${env.OLLAMA_URL:=http://localhost:11434}
+      base_url: ${env.OLLAMA_URL:=http://localhost:11434/v1}
   - provider_id: ${env.VLLM_URL:+vllm}
     provider_type: remote::vllm
     config:
-      url: ${env.VLLM_URL:=}
+      base_url: ${env.VLLM_URL:=}
       max_tokens: ${env.VLLM_MAX_TOKENS:=4096}
       api_token: ${env.VLLM_API_TOKEN:=fake}
       tls_verify: ${env.VLLM_TLS_VERIFY:=true}
   - provider_id: ${env.TGI_URL:+tgi}
     provider_type: remote::tgi
     config:
-      url: ${env.TGI_URL:=}
+      base_url: ${env.TGI_URL:=}
   - provider_id: fireworks
     provider_type: remote::fireworks
     config:
-      url: https://api.fireworks.ai/inference/v1
+      base_url: https://api.fireworks.ai/inference/v1
       api_key: ${env.FIREWORKS_API_KEY:=}
   - provider_id: together
     provider_type: remote::together
     config:
-      url: https://api.together.xyz/v1
+      base_url: https://api.together.xyz/v1
       api_key: ${env.TOGETHER_API_KEY:=}
   - provider_id: bedrock
     provider_type: remote::bedrock
@@ -52,9 +52,8 @@ providers:
   - provider_id: ${env.NVIDIA_API_KEY:+nvidia}
     provider_type: remote::nvidia
     config:
-      url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com}
+      base_url: ${env.NVIDIA_BASE_URL:=https://integrate.api.nvidia.com/v1}
       api_key: ${env.NVIDIA_API_KEY:=}
-      append_api_version: ${env.NVIDIA_APPEND_API_VERSION:=True}
   - provider_id: openai
     provider_type: remote::openai
     config:
@@ -76,18 +75,18 @@ providers:
   - provider_id: groq
     provider_type: remote::groq
     config:
-      url: https://api.groq.com
+      base_url: https://api.groq.com/openai/v1
       api_key: ${env.GROQ_API_KEY:=}
   - provider_id: sambanova
     provider_type: remote::sambanova
     config:
-      url: https://api.sambanova.ai/v1
+      base_url: https://api.sambanova.ai/v1
       api_key: ${env.SAMBANOVA_API_KEY:=}
   - provider_id: ${env.AZURE_API_KEY:+azure}
     provider_type: remote::azure
     config:
       api_key: ${env.AZURE_API_KEY:=}
-      api_base: ${env.AZURE_API_BASE:=}
+      base_url: ${env.AZURE_API_BASE:=}
       api_version: ${env.AZURE_API_VERSION:=}
       api_type: ${env.AZURE_API_TYPE:=}
   - provider_id: sentence-transformers