diff --git a/content/guides/12.ai/1.assistant/0.index.md b/content/guides/12.ai/1.assistant/0.index.md index 2621b4e4..c548bff3 100644 --- a/content/guides/12.ai/1.assistant/0.index.md +++ b/content/guides/12.ai/1.assistant/0.index.md @@ -26,42 +26,64 @@ Directus AI Assistant is an embedded conversational assistant that helps you int ### :icon{name="i-simple-icons-openai" class="align-middle mr-1 size-5"} OpenAI -| Model | Model ID | Context Window Size | -| ------------ | --------------------- | ------------------- | -| GPT-4o Mini | `gpt-4o-mini` | 128k tokens | -| GPT-4.1 Nano | `gpt-4.1-nano` | 1M tokens | -| GPT-4.1 Mini | `gpt-4.1-mini` | 1M tokens | -| GPT-4.1 | `gpt-4.1` | 1M tokens | -| GPT-5 Nano | `gpt-5-nano` | 400k tokens | -| GPT-5 Mini | `gpt-5-mini` | 400k tokens | -| GPT-5 | `gpt-5` | 400k tokens | -| GPT-5.2 | `gpt-5.2` | 400k tokens | -| GPT-5.2 Chat | `gpt-5.2-chat-latest` | 128k tokens | -| GPT-5.2 Pro | `gpt-5.2-pro` | 400k tokens | -| GPT-5.4 | `gpt-5.4` | 1M tokens | -| GPT-5.4 Pro | `gpt-5.4-pro` | 1M tokens | +| Model | Model ID | Context Window Size | +| ------------- | --------------- | ------------------- | +| GPT-4o Mini | `gpt-4o-mini` | 128k tokens | +| GPT-4.1 Mini | `gpt-4.1-mini` | 1M tokens | +| GPT-4.1 | `gpt-4.1` | 1M tokens | +| GPT-5 Nano | `gpt-5-nano` | 400k tokens | +| GPT-5 Mini | `gpt-5-mini` | 400k tokens | +| GPT-5 | `gpt-5` | 400k tokens | +| GPT-5.1 | `gpt-5.1` | 400k tokens | +| GPT-5.2 | `gpt-5.2` | 400k tokens | +| GPT-5.2 Pro | `gpt-5.2-pro` | 400k tokens | +| GPT-5.4 Nano | `gpt-5.4-nano` | 400k tokens | +| GPT-5.4 Mini | `gpt-5.4-mini` | 400k tokens | +| GPT-5.4 | `gpt-5.4` | 1M tokens | +| GPT-5.4 Pro | `gpt-5.4-pro` | 1M tokens | +| GPT-5.5 | `gpt-5.5` | 1M tokens | +| GPT-5.5 Pro | `gpt-5.5-pro` | 1M tokens | +| GPT-5.6 Luna | `gpt-5.6-luna` | 1M tokens | +| GPT-5.6 Terra | `gpt-5.6-terra` | 1M tokens | +| GPT-5.6 Sol | `gpt-5.6-sol` | 1M tokens | +| GPT-5.6 | `gpt-5.6` | 1M tokens | +| GPT-6 Luna | `gpt-6-luna` | 1M tokens | +| GPT-6 Sol | `gpt-6-sol` | 1M tokens | +| GPT-6 Astra | `gpt-6-astra` | 1M tokens | +| GPT-6.1 Sol | `gpt-6.1-sol` | 1M tokens | ### :icon{name="i-simple-icons-anthropic" class="align-middle mr-1 size-5"} Anthropic | Model | Model ID | Context Window Size | | ----------------- | ------------------- | ------------------- | +| Claude Haiku 5.5 | `claude-haiku-5-5` | 1M tokens | +| Claude Sonnet 5.5 | `claude-sonnet-5-5` | 1M tokens | +| Claude Opus 5.5 | `claude-opus-5-5` | 1M tokens | +| Claude Fable 5.1 | `claude-fable-5-1` | 1M tokens | +| Claude Sonnet 5 | `claude-sonnet-5` | 1M tokens | +| Claude Opus 5 | `claude-opus-5` | 1M tokens | +| Claude Fable 5 | `claude-fable-5` | 1M tokens | +| Claude Opus 4.8 | `claude-opus-4-8` | 1M tokens | | Claude Haiku 4.5 | `claude-haiku-4-5` | 200k tokens | -| Claude Sonnet 4.5 | `claude-sonnet-4-5` | 200k tokens | -| Claude Opus 4.5 | `claude-opus-4-5` | 200k tokens | -| Claude Sonnet 4.6 | `claude-sonnet-4-6` | 200k tokens | -| Claude Opus 4.6 | `claude-opus-4-6` | 200k tokens | +| Claude Sonnet 4.6 | `claude-sonnet-4-6` | 1M tokens | +| Claude Opus 4.7 | `claude-opus-4-7` | 1M tokens | +| Claude Opus 4.6 | `claude-opus-4-6` | 1M tokens | ### :icon{name="i-simple-icons-googlegemini" class="align-middle mr-1 size-5"} Google -| Model | Model ID | Context Window Size | -| ----------------------------- | ------------------------------- | ------------------- | -| Gemini 2.5 Flash | `gemini-2.5-flash` | 1M tokens | -| Gemini 2.5 Pro | `gemini-2.5-pro` | 1M tokens | -| Gemini 3 Flash Preview | `gemini-3-flash-preview` | 1M tokens | -| Gemini 3 Pro Preview | `gemini-3-pro-preview` | 1M tokens | -| Gemini 3.1 Flash Lite Preview | `gemini-3.1-flash-lite-preview` | 1M tokens | -| Gemini 3.1 Pro Preview | `gemini-3.1-pro-preview` | 1M tokens | -| Gemini 2.5 Flash Lite | `gemini-2.5-flash-lite` | 1M tokens | +| Model | Model ID | Context Window Size | +| ---------------------- | ------------------------ | ------------------- | +| Gemini 3.8 Flash | `gemini-3.8-flash` | 1M tokens | +| Gemini 3.7 Flash | `gemini-3.7-flash` | 1M tokens | +| Gemini 3.6 Flash | `gemini-3.6-flash` | 1M tokens | +| Gemini 3.5 Flash | `gemini-3.5-flash` | 1M tokens | +| Gemini 3.5 Flash Lite | `gemini-3.5-flash-lite` | 1M tokens | +| Gemini 3.1 Flash Lite | `gemini-3.1-flash-lite` | 1M tokens | +| Gemini 3.1 Pro Preview | `gemini-3.1-pro-preview` | 1M tokens | +| Gemini 3 Flash Preview | `gemini-3-flash-preview` | 1M tokens | +| Gemini 2.5 Pro | `gemini-2.5-pro` | 1M tokens | +| Gemini 2.5 Flash | `gemini-2.5-flash` | 1M tokens | +| Gemini 2.5 Flash Lite | `gemini-2.5-flash-lite` | 1M tokens | ### :icon{name="material-symbols:cloud-outline" class="align-middle mr-1 size-5"} OpenAI-Compatible diff --git a/content/guides/12.ai/1.assistant/1.setup.md b/content/guides/12.ai/1.assistant/1.setup.md index 6ccca1b3..cb9eb8e7 100644 --- a/content/guides/12.ai/1.assistant/1.setup.md +++ b/content/guides/12.ai/1.assistant/1.setup.md @@ -28,7 +28,7 @@ You'll need an API key from at least one provider. Choose based on which models :::accordion-item{label="OpenAI" icon="i-simple-icons-openai"} -OpenAI provides GPT-5 models (Nano, Mini, Standard). +OpenAI provides GPT models (GPT-6, GPT-5.6, and earlier). See [Supported Models](/guides/ai/assistant#supported-models) for the full list. 1. Go to [platform.openai.com](https://platform.openai.com/) and sign in or create an account 2. Navigate to **API Keys** in the left sidebar (or go directly to [platform.openai.com/api-keys](https://platform.openai.com/api-keys)) @@ -44,7 +44,7 @@ OpenAI requires a payment method and has usage-based pricing. Set spending limit :::accordion-item{label="Anthropic" icon="i-simple-icons-anthropic"} -Anthropic provides Claude models (Haiku 4.5, Sonnet 4.5, Opus 4.5). +Anthropic provides Claude models (Haiku, Sonnet, Opus, and Fable). See [Supported Models](/guides/ai/assistant#supported-models) for the full list. 1. Go to [console.anthropic.com](https://console.anthropic.com/) and sign in or create an account 2. Navigate to **API Keys** in the settings @@ -60,7 +60,7 @@ Anthropic requires a payment method and has usage-based pricing. Monitor usage i :::accordion-item{label="Google AI" icon="i-simple-icons-googlegemini"} -Google provides Gemini models (2.5 Flash, 2.5 Pro, 3 Flash Preview, 3 Pro Preview). +Google provides Gemini models (Flash, Flash Lite, and Pro). See [Supported Models](/guides/ai/assistant#supported-models) for the full list. 1. Go to [aistudio.google.com](https://aistudio.google.com/) and sign in with your Google account 2. Click **Get API Key** in the left sidebar @@ -90,7 +90,7 @@ Go to **Settings → AI** in the Directus admin panel. Add your API key for one or more providers: -- **OpenAI API Key** - Enables GPT-4 and GPT-5 models +- **OpenAI API Key** - Enables GPT models - **Anthropic API Key** - Enables Claude models - **Google API Key** - Enables Gemini models @@ -328,7 +328,7 @@ For details on creating prompts with variables, see [MCP Prompts](/guides/ai/mcp :: **Tips for controlling costs:** -- Use faster, cheaper models (GPT-5 Nano, Claude Haiku 4.5, Gemini 2.5 Flash) for simple tasks +- Use faster, cheaper models (GPT-6 Luna, Claude Haiku 5.5, Gemini 3.5 Flash Lite) for simple tasks - Use [Allowed Models](#configure-allowed-models) to restrict access to expensive models - Start a new conversation when switching tasks to avoid sending unrelated conversation history - Set spending limits in your provider dashboard: diff --git a/content/guides/12.ai/1.assistant/2.usage.md b/content/guides/12.ai/1.assistant/2.usage.md index 4101a8b3..3f18aa05 100644 --- a/content/guides/12.ai/1.assistant/2.usage.md +++ b/content/guides/12.ai/1.assistant/2.usage.md @@ -21,9 +21,9 @@ Click the model dropdown in the chat header to choose which AI model to use: | Model | Best For | |-------|----------| -| :icon{name="logos:openai-icon"} GPT-5 Nano / :icon{name="logos:claude-icon"} Claude Haiku 4.5 / :icon{name="i-simple-icons-googlegemini"} Gemini 3 Flash Preview | Quick tasks, simple queries | -| :icon{name="logos:openai-icon"} GPT-5 Mini | Balanced speed and capability | -| :icon{name="logos:openai-icon"} GPT-5 / :icon{name="logos:claude-icon"} Claude Sonnet 4.5 / :icon{name="i-simple-icons-googlegemini"} Gemini 3 Pro Preview | Complex operations, detailed analysis | +| :icon{name="logos:openai-icon"} GPT-6 Luna / :icon{name="logos:claude-icon"} Claude Haiku 5.5 / :icon{name="i-simple-icons-googlegemini"} Gemini 3.5 Flash Lite | Quick tasks, simple queries | +| :icon{name="logos:openai-icon"} GPT-5.6 Terra / :icon{name="logos:claude-icon"} Claude Sonnet 5.5 / :icon{name="i-simple-icons-googlegemini"} Gemini 3.8 Flash | Balanced speed and capability | +| :icon{name="logos:openai-icon"} GPT-6.1 Sol / :icon{name="logos:claude-icon"} Claude Opus 5.5 / :icon{name="i-simple-icons-googlegemini"} Gemini 3.1 Pro Preview | Complex operations, detailed analysis | Only models for [configured providers](/guides/ai/assistant/setup) appear in the dropdown. diff --git a/content/guides/12.ai/3.translations.md b/content/guides/12.ai/3.translations.md index 37cb9d57..b6ca4068 100644 --- a/content/guides/12.ai/3.translations.md +++ b/content/guides/12.ai/3.translations.md @@ -108,6 +108,6 @@ Non-translatable interfaces — booleans, dates, files, colors, select dropdowns - Use the **glossary** for brand names, product names, and technical terms that shouldn't be translated or need specific handling across languages. - Use the **style guide** for consistent tone and voice across all translations. -- Cheaper, faster models (GPT-5 Nano, Claude Haiku 4.5, Gemini 2.5 Flash) work well for straightforward content translation. +- Cheaper, faster models (GPT-6 Luna, Claude Haiku 5.5, Gemini 3.5 Flash Lite) work well for straightforward content translation. - You can retry individual failed languages without re-translating the ones that succeeded. - Translations are applied to the item but not saved automatically — review the results and save when ready.