> ## Documentation Index
> Fetch the complete documentation index at: https://edenai-integrations-any-llm.mintlify.site/llms.txt
> Use this file to discover all available pages before exploring further.

# any-llm

> Use any-llm (Mozilla AI) with Eden AI to call 500+ AI models through one unified Python interface.

export const TechArticleSchema = ({title, description, path, articleSection, about, proficiencyLevel = "Beginner", dependencies, keywords = [], datePublished, dateModified, image, inLanguage = "en"}) => {
  const baseUrl = "https://www.edenai.co/docs";
  const canonicalUrl = `${baseUrl}/${path}`.replace(/\/+$/, "");
  const ogParams = new URLSearchParams({
    division: articleSection || "",
    title: title || "",
    description: description || ""
  });
  const resolvedImage = image || `https://edenai.mintlify.app/_mintlify/api/og?${ogParams.toString()}`;
  const data = {
    "@context": "https://schema.org",
    "@type": "TechArticle",
    "@id": `${canonicalUrl}#techarticle`,
    mainEntityOfPage: {
      "@type": "WebPage",
      "@id": canonicalUrl
    },
    headline: title,
    name: title,
    description: description,
    url: canonicalUrl,
    inLanguage: inLanguage,
    isPartOf: {
      "@type": "WebSite",
      name: "Eden AI Documentation",
      url: baseUrl
    },
    author: [{
      "@type": "Organization",
      name: "Eden AI",
      url: "https://www.edenai.co/"
    }],
    publisher: {
      "@type": "Organization",
      name: "Eden AI",
      url: "https://www.edenai.co/",
      logo: {
        "@type": "ImageObject",
        url: "https://www.edenai.co/assets/logo.png"
      }
    }
  };
  if (articleSection) data.articleSection = articleSection;
  if (about) data.about = {
    "@type": "Thing",
    name: about
  };
  if (proficiencyLevel) data.proficiencyLevel = proficiencyLevel;
  if (dependencies) data.dependencies = dependencies;
  if (keywords && keywords.length) data.keywords = keywords;
  if (datePublished) data.datePublished = datePublished;
  if (dateModified) data.dateModified = dateModified;
  data.image = Array.isArray(resolvedImage) ? resolvedImage : [resolvedImage];
  const json = JSON.stringify(data);
  const schemaId = `techarticle-${canonicalUrl}`;
  React.useEffect(() => {
    if (typeof document === "undefined") return;
    document.querySelectorAll(`script[data-schema-id="${schemaId}"]`).forEach(n => n.remove());
    const script = document.createElement("script");
    script.type = "application/ld+json";
    script.dataset.schemaId = schemaId;
    script.textContent = json;
    document.head.appendChild(script);
    return () => script.remove();
  }, [json, schemaId]);
  return null;
};

<TechArticleSchema title={"any-llm"} description={"Use any-llm (Mozilla AI) with Eden AI to call 500+ AI models through one unified Python interface."} path="v3/integrations/any-llm" articleSection="AI Frameworks" about={"LLM Framework Integration"} proficiencyLevel="Intermediate" keywords={["Eden AI", "AI API", "any-llm", "Mozilla AI", "Python"]} datePublished="2026-07-20T00:00:00Z" dateModified="2026-07-20T00:00:00Z" />

Use any-llm (Mozilla AI) with Eden AI to call 500+ AI models through one unified Python interface.

## Overview

[any-llm](https://github.com/mozilla-ai/any-llm) is a lightweight Python library from **Mozilla AI** that lets you talk to any LLM provider through a single `completion()` interface — swap providers by changing one string. **Eden AI is a built-in any-llm provider**, so you reach models from OpenAI, Anthropic, Google, Mistral and 500+ more behind one key, with EU-based, GDPR-aligned inference.

You select a model with the `provider:model_id` syntax. For Eden AI, the provider is `edenai` and the model id follows Eden AI's `provider/model` scheme — for example `edenai:anthropic/claude-sonnet-5`.

## Installation

Install any-llm with the Eden AI provider extra:

<CodeGroup>
  ```bash pip theme={null}
  pip install 'any-llm-sdk[edenai]'
  ```

  ```bash uv theme={null}
  uv add 'any-llm-sdk[edenai]'
  ```
</CodeGroup>

## Quick Start

Set your key, then point any-llm at Eden AI by prefixing any model with `edenai:`:

<CodeGroup>
  ```bash .env theme={null}
  EDENAI_API_KEY=your_api_key_here
  ```

  ```python Python theme={null}
  from any_llm import completion

  response = completion(
      model="edenai:anthropic/claude-sonnet-5",  # edenai:<provider>/<model>
      messages=[{"role": "user", "content": "Hello! How are you?"}],
  )

  print(response.choices[0].message.content)
  ```
</CodeGroup>

The `edenai` provider automatically uses the Eden AI base URL (`https://api.edenai.run/v3`) and reads your key from the `EDENAI_API_KEY` environment variable.

## Switching models

any-llm's core benefit: change providers by changing one string. Every Eden AI model is reachable the same way:

<CodeGroup>
  ```python Python theme={null}
  from any_llm import completion

  messages = [{"role": "user", "content": "Write a haiku about the sea."}]

  for model in [
      "edenai:openai/gpt-5.5",
      "edenai:anthropic/claude-sonnet-5",
      "edenai:mistral/mistral-large-2512",
  ]:
      response = completion(model=model, messages=messages)
      print(model, "->", response.choices[0].message.content)
  ```
</CodeGroup>

## Streaming

Eden AI supports streaming through any-llm — pass `stream=True`:

<CodeGroup>
  ```python Python theme={null}
  from any_llm import completion

  stream = completion(
      model="edenai:mistral/mistral-small-2603",
      messages=[{"role": "user", "content": "Count from one to five."}],
      stream=True,
  )

  for chunk in stream:
      delta = chunk.choices[0].delta.content
      if delta:
          print(delta, end="", flush=True)
  ```
</CodeGroup>

## Available Models

Use the `edenai:<provider>/<model>` format for any Eden AI model:

**OpenAI**

* `edenai:openai/gpt-5.5`
* `edenai:openai/gpt-5-mini`

**Anthropic**

* `edenai:anthropic/claude-sonnet-5`
* `edenai:anthropic/claude-opus-4-8`
* `edenai:anthropic/claude-haiku-4-5`

**Google**

* `edenai:google/gemini-2.5-pro`
* `edenai:google/gemini-3.5-flash`

**Mistral**

* `edenai:mistral/mistral-large-2512`
* `edenai:mistral/mistral-small-2603`

## Embeddings

The Eden AI provider also supports embeddings:

<CodeGroup>
  ```python Python theme={null}
  from any_llm import embedding

  response = embedding(
      model="edenai:openai/text-embedding-3-small",
      inputs="The quick brown fox jumps over the lazy dog.",
  )

  print(response.data[0].embedding[:5])
  ```
</CodeGroup>

## Environment Variables

<CodeGroup>
  ```bash .env theme={null}
  EDENAI_API_KEY=your_api_key_here
  # Optional — override the endpoint:
  EDENAI_API_BASE=https://api.edenai.run/v3
  ```
</CodeGroup>

## Next Steps

* [Chat Completions](/v3/llms/chat-completions) - Core LLM endpoint
* [List LLM Models](/v3/llms/listing-models) - Browse available providers and models
* [aisuite](/v3/integrations/aisuite) - Another unified LLM interface
* [OpenAI SDK (Python)](/v3/integrations/openai-sdk-python) - Direct SDK usage