Update docs following removal of providers (#2605)

* Update docs following removal of providers

* remove templates

* (unrelated) re-generate docs page for inference providers

Author: SBrandeis

docs/inference-providers/_redirects.yml

@@ -6,3 +6,5 @@ usage: index
 faq: index
 rate-limits: pricing
 guides/vscode: integrations/vscode
+providers/hyperbolic: index
+providers/sambanova: index

docs/inference-providers/_toctree.yml

@@ -120,8 +120,6 @@
     title: Fireworks
   - local: providers/groq
     title: Groq
-  - local: providers/hyperbolic
-    title: Hyperbolic
   - local: providers/hf-inference
     title: HF Inference
   - local: providers/novita
@@ -134,8 +132,6 @@
     title: Public AI
   - local: providers/replicate
     title: Replicate
-  - local: providers/sambanova
-    title: SambaNova
   - local: providers/scaleway
     title: Scaleway
   - local: providers/together

docs/inference-providers/guides/evaluation-inspect-ai.md

@@ -100,7 +100,7 @@ inspect view
 ## Example: Comparing several inference providers for a task
 In this section, we will evaluate the same model across different providers. Inference Providers gives us access to many providers for the same model. Performance might vary across providers, so this is a useful factor, in addition to speed and cost, to choose the most appropriate inference provider for your task.
 
-If we don't specify a provider, like we did in our previous examples, the system automatically selects the fastest available provider for the specified model (equivalent to the `:fastest` policy). But we can also select the provider by appending the provider name to the model id (e.g. `openai/gpt-oss-120b:sambanova`).
+If we don't specify a provider, like we did in our previous examples, the system automatically selects the fastest available provider for the specified model (equivalent to the `:fastest` policy). But we can also select the provider by appending the provider name to the model id (e.g. `openai/gpt-oss-120b:groq`).
 
 Let's run the evaluations for `gpt-oss-120b` across several providers. Please note that this time we are using the `eval_set` function directly in Python for extra flexibility (e.g., changing the list of providers):
 
@@ -109,12 +109,10 @@ from inspect_ai import eval_set
 
 target_providers = [
     "together",
-    "sambanova",
     "groq",
     "novita",
     "cerebras",
     "nscale",
-    "hyperbolic",
     "fireworks-ai",
     "scaleway"
 ]
@@ -139,15 +137,13 @@ Launching the viewer and sorting by score, we can compare the performance across
 
 | Model | Provider | Score |
 |-------|----------|-------|
-| openai/gpt-oss-120b | hyperbolic | 0.84 |
 | openai/gpt-oss-120b | fireworks-ai | 0.82 |
 | openai/gpt-oss-120b | nscale | 0.82 |
 | openai/gpt-oss-120b | scaleway | 0.81 |
 | openai/gpt-oss-120b | together | 0.81 |
 | openai/gpt-oss-120b | cerebras | 0.8 |
 | openai/gpt-oss-120b | novita | 0.8 |
 | openai/gpt-oss-120b | groq | 0.8 |
-| openai/gpt-oss-120b | sambanova | 0.8 |
 
 > [!TIP]
 > **Why performance varies across providers**: As seen above, the same model can produce different results when served by different inference providers due to several factors: variations in inference implementations, differences in hardware (GPU generations, optimizations), and non-determinism introduced by load balancing and batching strategies. Performance can vary across the matrix of provider-model combinations and may change with updates to inference stacks, GPU generations, and model versions. Evaluating across multiple providers helps identify the best-performing combinations for your specific use case.

docs/inference-providers/guides/function-calling.md

@@ -304,7 +304,6 @@ client = OpenAI(
 client.chat.completions.create(
 -     model="deepseek-ai/DeepSeek-R1-0528", # automatically selects the fastest available provider
 +     model="deepseek-ai/DeepSeek-R1-0528:novita", # manually select Novita
-+     model="deepseek-ai/DeepSeek-R1-0528:hyperbolic", # manually select Hyperbolic
       ...
 )
 ```

docs/inference-providers/hub-api.md

@@ -31,8 +31,8 @@ It can be combined with other filters to e.g. select only `text-to-image` models
 Pass a comma-separated list of providers to select multiple:
 
 ```sh
-# List image-text-to-text models served by Novita or Sambanova
-~ curl -s https://huggingface.co/api/models?inference_provider=sambanova,novita&pipeline_tag=image-text-to-text | jq ".[].id"
+# List image-text-to-text models served by Novita or Nscale
+~ curl -s https://huggingface.co/api/models?inference_provider=nscale,novita&pipeline_tag=image-text-to-text | jq ".[].id"
 "meta-llama/Llama-3.2-11B-Vision-Instruct"
 "meta-llama/Llama-3.2-90B-Vision-Instruct"
 "Qwen/Qwen2-VL-72B-Instruct"

docs/inference-providers/index.md

@@ -48,13 +48,11 @@ Our platform integrates with leading AI infrastructure providers, giving you acc
 | [Fireworks](./providers/fireworks-ai)        |          ✅           |          ✅           |                    |               |               |                |
 | [Groq](./providers/groq)                     |          ✅           |          ✅           |                    |               |               |                |
 | [HF Inference](./providers/hf-inference)     |          ✅           |          ✅           |         ✅         |      ✅       |               |       ✅       |
-| [Hyperbolic](./providers/hyperbolic)         |          ✅           |          ✅           |                    |               |               |                |
 | [Novita](./providers/novita)                 |          ✅           |          ✅           |                    |               |      ✅       |                |
 | [Nscale](./providers/nscale)                 |          ✅           |          ✅           |                    |      ✅       |               |                |
 | [OVHcloud AI Endpoints](./providers/ovhcloud)|          ✅           |          ✅           |                    |               |               |                |
 | [Public AI](./providers/publicai)            |          ✅           |                       |                    |               |               |                |
 | [Replicate](./providers/replicate)           |                       |                       |                    |      ✅       |      ✅       |       ✅       |
-| [SambaNova](./providers/sambanova)           |          ✅           |                       |         ✅         |               |               |                |
 | [Scaleway](./providers/scaleway)             |          ✅           |                       |         ✅         |               |               |                |
 | [Together](./providers/together)             |          ✅           |          ✅           |                    |      ✅       |               |                |
 | [WaveSpeedAI](./providers/wavespeed)         |                       |                       |                    |      ✅       |      ✅       |                |
@@ -82,7 +80,7 @@ Here's what you can build:
 ## Key Features
 
 - **🎯 All-in-One API**: A single API for text generation, image generation, document embeddings, NER, summarization, image classification, and more.
-- **🔀 Multi-Provider Support**: Easily run models from top-tier providers like fal, Replicate, Sambanova, Together AI, and others.
+- **🔀 Multi-Provider Support**: Easily run models from top-tier providers like fal, Replicate, Together AI, and others.
 - **🚀 Scalable & Reliable**: Built for high availability and low-latency performance in production environments.
 - **🔧 Developer-Friendly**: Simple requests, fast responses, and a consistent developer experience across Python and JavaScript clients.
 - **👷 Easy to integrate**: Drop-in replacement for the OpenAI chat completions API.
@@ -135,7 +133,7 @@ By default, our system automatically selects the fastest available provider for
 
 You can change the provider selection policy by appending a policy suffix to the model id: `:cheapest` for the most cost-efficient provider (lowest price per output token), or `:preferred` to follow your preference order in [Inference Provider settings](https://hf.co/settings/inference-providers). For example, `openai/gpt-oss-120b:cheapest`.
 
-You can also select the provider of your choice by appending the provider name to the model id (e.g. `"openai/gpt-oss-120b:sambanova"`).
+You can also select the provider of your choice by appending the provider name to the model id (e.g. `"openai/gpt-oss-120b:groq"`).
 
 ```python
 import os
@@ -166,7 +164,7 @@ By default, our system automatically selects the fastest available provider for
 
 You can change the provider selection policy by appending a policy suffix to the model id: `:cheapest` for the most cost-efficient provider (lowest price per output token), or `:preferred` to follow your preference order in [Inference Provider settings](https://hf.co/settings/inference-providers). For example, `openai/gpt-oss-120b:cheapest`.
 
-You can also select the provider of your choice by appending the provider name to the model id (e.g. `"openai/gpt-oss-120b:sambanova"`).
+You can also select the provider of your choice by appending the provider name to the model id (e.g. `"openai/gpt-oss-120b:groq"`).
 
 ```python
 import os
@@ -198,7 +196,7 @@ By default, our system automatically selects the fastest available provider for
 
 You can change the provider selection policy by appending a policy suffix to the model id: `:cheapest` for the most cost-efficient provider (lowest price per output token), or `:preferred` to follow your preference order in [Inference Provider settings](https://hf.co/settings/inference-providers). For example, `openai/gpt-oss-120b:cheapest`.
 
-You can also select the provider of your choice by appending the provider name to the model id (e.g. `"openai/gpt-oss-120b:sambanova"`).
+You can also select the provider of your choice by appending the provider name to the model id (e.g. `"openai/gpt-oss-120b:groq"`).
 
 ```python
 import os
@@ -246,7 +244,7 @@ By default, our system automatically selects the fastest available provider for
 
 You can change the provider selection policy by appending a policy suffix to the model id: `:cheapest` for the most cost-efficient provider (lowest price per output token), or `:preferred` to follow your preference order in [Inference Provider settings](https://hf.co/settings/inference-providers). For example, `openai/gpt-oss-120b:cheapest`.
 
-You can also select the provider of your choice by appending the provider name to the model id (e.g. `"openai/gpt-oss-120b:sambanova"`).
+You can also select the provider of your choice by appending the provider name to the model id (e.g. `"openai/gpt-oss-120b:groq"`).
 
 ```js
 import { InferenceClient } from "@huggingface/inference";
@@ -276,7 +274,7 @@ By default, our system automatically selects the fastest available provider for
 
 You can change the provider selection policy by appending a policy suffix to the model id: `:cheapest` for the most cost-efficient provider (lowest price per output token), or `:preferred` to follow your preference order in [Inference Provider settings](https://hf.co/settings/inference-providers). For example, `openai/gpt-oss-120b:cheapest`.
 
-You can also select the provider of your choice by appending the provider name to the model id (e.g. `"openai/gpt-oss-120b:sambanova"`).
+You can also select the provider of your choice by appending the provider name to the model id (e.g. `"openai/gpt-oss-120b:groq"`).
 
 ```javascript
 import OpenAI from "openai";
@@ -309,7 +307,7 @@ By default, our system automatically selects the fastest available provider for
 
 You can change the provider selection policy by appending a policy suffix to the model id: `:cheapest` for the most cost-efficient provider (lowest price per output token), or `:preferred` to follow your preference order in [Inference Provider settings](https://hf.co/settings/inference-providers). For example, `openai/gpt-oss-120b:cheapest`.
 
-You can also select the provider of your choice by appending the provider name to the model id (e.g. `"openai/gpt-oss-120b:sambanova"`).
+You can also select the provider of your choice by appending the provider name to the model id (e.g. `"openai/gpt-oss-120b:groq"`).
 
 ```js
 import fetch from "node-fetch";
@@ -348,7 +346,7 @@ By default, our system automatically selects the fastest available provider for
 
 You can change the provider selection policy by appending a policy suffix to the model id: `:cheapest` for the most cost-efficient provider (lowest price per output token), or `:preferred` to follow your preference order in [Inference Provider settings](https://hf.co/settings/inference-providers). For example, `openai/gpt-oss-120b:cheapest`.
 
-You can also select the provider of your choice by appending the provider name to the model id (e.g. `"openai/gpt-oss-120b:sambanova"`).
+You can also select the provider of your choice by appending the provider name to the model id (e.g. `"openai/gpt-oss-120b:groq"`).
 
 ```bash
 curl https://router.huggingface.co/v1/chat/completions \
@@ -440,7 +438,7 @@ const client = new InferenceClient(process.env.HF_TOKEN);
 // Explicit provider selection
 await client.chatCompletion({
   model: "deepseek-ai/DeepSeek-R1",
-  provider: "sambanova", // Specific provider
+  provider: "novita", // Specific provider
   messages: [{ role: "user", content: "Hello!" }],
 });
 
@@ -466,7 +464,7 @@ client = InferenceClient(token=os.environ["HF_TOKEN"])
 # Explicit provider selection
 result = client.chat_completion(
     model="deepseek-ai/DeepSeek-R1",
-    provider="sambanova",  # Specific provider
+    provider="novita",  # Specific provider
     messages=[{"role": "user", "content": "Hello!"}],
 )
 

docs/inference-providers/integrations/vscode.md

@@ -19,7 +19,7 @@ Use frontier open LLMs like Kimi K2, DeepSeek V3.1, GLM 4.5 and more in VS Code
 ## ✨ Why use the Hugging Face provider in Copilot
 
 - Access [SoTA open‑source LLMs](https://huggingface.co/models?pipeline_tag=text-generation&inference_provider=all&sort=trending) with tool calling capabilities.
-- Single API to switch between multiple providers like Groq, Cerebras, Together AI, SambaNova, and more.
+- Single API to switch between multiple providers like Groq, Cerebras, Together AI, and more.
 - Built for high availability (across providers) and low latency.
 - Transparent pricing: what the provider charges is what you pay.
 

docs/inference-providers/providers/fal-ai.md

@@ -87,6 +87,6 @@ Find out more about Text To Video [here](../tasks/text-to-video).
 
 <InferenceSnippet
     pipeline=text-to-video
-    providersMapping={ {"fal-ai":{"modelId":"meituan-longcat/LongCat-Video","providerModelId":"fal-ai/longcat-video/text-to-video/480p"} } }
+    providersMapping={ {"fal-ai":{"modelId":"Wan-AI/Wan2.2-TI2V-5B","providerModelId":"fal-ai/wan/v2.2-5b/text-to-video"} } }
 />