> ## Documentation Index
> Fetch the complete documentation index at: https://docs.requesty.ai/llms.txt
> Use this file to discover all available pages before exploring further.

# Changelog

> New features, integrations, and improvements shipped to the Requesty platform.

<Update label="July 10, 2026" description="Prompt Library response formats for reusable structured outputs" tags={["New"]}>
  Prompts can now carry their own response format. In the Prompt Library, use **Response Format** to set free-form JSON output or a named JSON Schema with optional description and strict mode. Requests that reference the prompt with `prompt_id` inherit the saved `response_format` automatically, and prompt-level response formats override caller-provided response formats. The editor's JSON view and version sidebar now surface response format settings alongside model parameters.

  [Prompt Library docs →](/features/prompt-library)
</Update>

<Update label="July 3, 2026" description="Prompt Library with model parameters, versioning, and diffs" tags={["New"]}>
  The Prompt Library now supports model parameters, version diffs, and a redesigned editor. Attach temperature, reasoning effort, max tokens, top\_p, and n directly to a prompt so every request inherits them automatically. Compare any two versions with a line-by-line diff viewer that highlights added, removed, and modified messages. The new prompts list includes search, sortable columns, tags, and copyable prompt IDs. Reference any prompt in your API requests with a single `prompt_id` and optional `prompt_variables` for runtime customization.

  [Prompt Library docs →](/features/prompt-library)
</Update>

<Update label="June 23, 2026" description="Access list and group member management endpoints in the Management API" tags={["API"]}>
  Full programmatic control over access lists and group member settings is now available in the Management API. Create, read, update, and delete access lists, set the organization's default group access list, update a member's role within a group, and set per-member budget overrides — all via API key with manage permissions.

  * [List Access Lists](/api-reference/endpoint/manage-access-list/manage-access-list-list)
  * [Create Access List](/api-reference/endpoint/manage-access-list/manage-access-list-create)
  * [Get Access List](/api-reference/endpoint/manage-access-list/manage-access-list-get)
  * [Update Access List](/api-reference/endpoint/manage-access-list/manage-access-list-update)
  * [Delete Access List](/api-reference/endpoint/manage-access-list/manage-access-list-delete)
  * [Set Default Group Access List](/api-reference/endpoint/manage-access-list/manage-access-list-set-group-default)
  * [Update Group Member Role](/api-reference/endpoint/manage-group-member/manage-group-member-update)
  * [Update Group Member Budget Override](/api-reference/endpoint/manage-group-member/manage-group-member-budget-override)
</Update>

<Update label="June 30, 2026" description="Hermes Agent integration with automatic prompt caching" tags={["Integrations"]}>
  Hermes Agent by Nous Research now integrates with Requesty out of the box. Configure Hermes to route through the gateway using the native Anthropic Messages format, which enables automatic prompt caching on multi-turn conversations. Hermes sends a large system prompt with tool definitions on every turn, and Requesty's auto-caching means subsequent turns reuse the cached prefix instead of reprocessing it from scratch. One config file gets you 300+ models, fallback routing, and cost tracking across all your Hermes sessions.

  [Set up Hermes →](/integrations/hermes)
</Update>

<Update label="June 12, 2026" description="Restricted access lists and a group default access list" tags={["New"]}>
  Two new ways to control which models your teams can reach. Mark an access list as **restricted** so only org admins can attach it to groups or API keys, while group admins stay free to attach the rest. Set a **group default access list** that applies to any group without its own explicit list, giving every team a baseline without per-group setup. The resolution order now runs through four layers: API key list, then group list, then the group default, then your organization's approved models.

  [Access Lists docs →](/features/access-lists)
</Update>

<Update label="June 12, 2026" description="Resource IDs in spending alert webhooks" tags={["New"]}>
  Spending alert webhooks now include the resource ID alongside the name in every payload. User, group, and API key alerts carry `user_id`, `group_id`, and `api_key_id` fields, and the Slack, Teams, and JSON formats all show the ID next to the resource name. No more guessing which "Production" key or "Engineering" group an alert refers to when names collide or change.

  [Spending Alerts docs →](/features/alerts)
</Update>

<Update label="June 12, 2026" description="Strict EU enforcement for organizations" tags={["New"]}>
  Organizations that need a hard data residency guarantee can now enforce EU routing server-side. With strict EU enforcement enabled, every request from your organization must go through `https://router.eu.requesty.ai`, and requests to non-EU endpoints are rejected. Contact [support@requesty.ai](mailto:support@requesty.ai) to activate it for your organization.

  [EU Routing docs →](/features/eu-routing)
</Update>

<Update label="June 10, 2026" description="Image generation in the n8n community node" tags={["Integrations"]}>
  The Requesty n8n package (`@requesty/n8n-nodes-requesty` v1.1.0) now includes a **Requesty Image Generation** node. Generate images from text prompts with models like `azure/openai/gpt-image-1`, with control over size, quality, background (including transparent), and output format. Get binary image data with a preview in the n8n output panel, or URLs for downstream use. The node also works as an AI Agent tool, so an agent can generate images on its own when a user asks.

  [Set up n8n →](/integrations/n8n)
</Update>

<Update label="June 10, 2026" description="Free models on the gateway" tags={["New"]}>
  Four models are now free to use through the gateway: `nvidia/nemotron-3-ultra-550b-a55b`, `nvidia/nemotron-3-super-120b-a12b`, `poolside/laguna-xs.2`, and `poolside/laguna-m.1`. New organizations get 50 free requests per day and paying organizations get 200, shared across all free models. Free for now, any pricing change will be announced here first.

  [Free Models docs →](/features/free-models)
</Update>

<Update label="June 10, 2026" description="Member offboarding via the Management API" tags={["New", "API"]}>
  Automate member offboarding alongside your existing API-based onboarding. Call `DELETE /v1/manage/org/member/{user_id}` with a write-manage API key to remove a member from your organization: they lose access to the organization, all API keys they created in it are invalidated, and they are removed from all of its groups. Look up user IDs with the [List Organization Members](/api-reference/endpoint/manage-org-member-list) endpoint.

  [Delete Organization Member reference →](/api-reference/endpoint/manage-org-member-delete)
</Update>

<Update label="June 9, 2026" description="Model retirement dates in the API" tags={["API"]}>
  Models now carry a `retires_at` date so you can plan migrations before a model goes away. The [List Models](/api-reference/endpoint/models-list) response includes the field for any model with a scheduled retirement, and the date is shown on each model card in the Model Library. Once a model's `retires_at` date passes, requests to it fail, so switch to a successor or add a fallback policy ahead of time.

  [List Models reference →](/api-reference/endpoint/models-list)
</Update>

<Update label="June 8, 2026" description="Unified web search across all inference endpoints" tags={["New"]}>
  Enable real-time web search with a single tool definition that works across the Messages, Chat Completions, and Responses APIs. Pass `{ "type": "web_search" }` and Requesty translates it to each provider's native web search format automatically, normalizing citations and results behind one interface. Look for `supports_web_search: true` in the List Models response to find compatible models.

  [Web Search docs →](/features/web-search)
</Update>

<Update label="June 6, 2026" description="Strict JSON Schema structured outputs" tags={["New"]}>
  Get guaranteed, schema-valid JSON from supported models. Set `response_format` to `{ "type": "json_schema" }` with your schema and the model output conforms to it exactly. The List Models response now includes a `supports_json_schema` flag so you can find compatible models programmatically.

  [Structured Outputs docs →](/features/structured-outputs)
</Update>

<Update label="June 4, 2026" description="Requesty community node for n8n" tags={["Integrations"]}>
  Build AI workflows in n8n with 300+ models through Requesty. Install the **Requesty Chat Model** community node (`@requesty/n8n-nodes-requesty`) and drop it into any AI Agent or Basic LLM Chain. Get strict JSON Schema structured output, native web search, reasoning effort control, and routing policies, all behind one API key.

  [Set up n8n →](/integrations/n8n)
</Update>

<Update label="May 31, 2026" description="Connect GitHub Copilot to Requesty" tags={["Integrations"]}>
  Use GitHub Copilot Chat in VS Code with 300+ models through Requesty. Add Requesty as a Bring Your Own Key (BYOK) Custom Endpoint provider to get model routing, cost tracking, and fallback policies for Copilot Chat, tools, and MCP servers. Requires VS Code 1.122+.

  [Set up GitHub Copilot →](/integrations/github-copilot)
</Update>

<Update label="May 28, 2026" description="Error codes reference page" tags={["New", "Analytics"]}>
  A comprehensive reference for every router error code — what it means, where it originates, and how to fix it. Plus, you can now group by `status_code` in [Advanced Analytics](https://app.requesty.ai/analytics/advanced?groupBy=status_code\&metric=cost\&aggMethod=sum\&timeRange=7d\&timeGroup=day) to track error trends and costs in your dashboards.

  [Error Codes docs →](/features/error-codes)
</Update>

<Update label="May 27, 2026" description="Custom time ranges in analytics" tags={["Analytics"]}>
  Pick an exact start and end date for any analytics view. Use relative presets or switch to Date Range mode for full control over the time window.

  [Usage Analytics docs →](/features/usage-analytics)
</Update>

<Update label="May 26, 2026" description="Logs & Traces view for full request visibility" tags={["New"]}>
  Inspect every LLM request in a searchable table with click-to-filter, configurable columns, and pagination. Switch to Traces mode to see multi-step agent runs grouped by `trace_id`. Click any row to open a detail panel with the full message timeline, tool call arguments, metadata, guardrail violations, and a model arena for side-by-side comparison.

  [Logs & Traces docs →](/features/logs)
</Update>

<Update label="May 22, 2026" description="Export analytics as PDF or CSV" tags={["Analytics"]}>
  Download your advanced analytics data as a professional PDF report or CSV spreadsheet. The PDF includes your Requesty logo, date range, and a formatted data table, perfect for sharing cost reports with your team or keeping monthly records.

  [Analytics Exports docs →](/features/analytics-exports)
</Update>

<Update label="May 21, 2026" description="Connect OpenAI Codex to Requesty" tags={["Integrations"]}>
  Use OpenAI Codex with 300+ models through Requesty. Get model routing, cost tracking, and fallback policies for your Codex coding agent.

  [Set up Codex →](/integrations/openai-codex)
</Update>

<Update label="May 20, 2026" description="API keys now return group information" tags={["API"]}>
  The Get API Key and List API Keys endpoints now include a `group` field showing which group each key belongs to, making it easier to manage keys programmatically.

  [API Keys reference →](/api-reference/endpoint/manage-api-key-get)
</Update>

<Update label="May 19, 2026" description="EU routing with Gemini models" tags={["New"]}>
  Route requests through the EU endpoint with the newest Gemini models: `vertex/gemini-3.5-flash@eu` and `vertex/gemini-3.1-flash-lite@eu`. Full data residency when combined with the EU endpoint.

  [EU routing docs →](/features/eu-routing)
</Update>

<Update label="May 16, 2026" description="Enforce SSO for your organization" tags={["Security"]}>
  Lock down access with Entra ID (Azure AD), Okta, or any OIDC/SAML provider. Members authenticate through your identity provider and land directly in Requesty.

  [Set up SSO →](/features/sso)
</Update>

<Update label="May 14, 2026" description="Restrict models per API key with Access Lists" tags={["Security"]}>
  Create named model allow-lists and attach them to individual API keys or groups. Control exactly which models each key can call without touching your org-wide settings.

  [Create an access list →](/features/access-lists)
</Update>

<Update label="May 12, 2026" description="Use the Responses API through Requesty" tags={["API"]}>
  Route OpenAI `/v1/responses` calls through the gateway with full analytics, fallback, and cost tracking. Custom tool types are supported.

  [Responses API reference →](/api-reference/endpoint/responses-create)
</Update>

<Update label="May 9, 2026" description="See the cost of every request inline" tags={["API"]}>
  API responses now include a `usage.cost` field with the exact dollar amount. For streaming, set `stream_options.include_usage` to get cost on the final chunk.

  [Cost tracking docs →](/features/cost-tracking)
</Update>

<Update label="May 7, 2026" description="Query organization-level usage" tags={["API"]}>
  A new Management API endpoint returns aggregated spend and token counts across your entire org, with the same time filters available on key-level usage.

  [Org Usage API →](/api-reference/endpoint/manage-org-get-usage)
</Update>

<Update label="May 5, 2026" description="Filter models by deployment region" tags={["API"]}>
  The `/v1/models` endpoint now returns geolocation data for each model. The Model Library shows EU/US region chips so you can pick the right model before routing.

  [EU routing docs →](/features/eu-routing)
</Update>

<Update label="May 2, 2026" description="Route Pi through Requesty" tags={["Integrations"]}>
  Connect the Pi coding agent for model routing, cost tracking, and fallback policies across your coding workflows.

  [Set up Pi →](/integrations/pi)
</Update>

<Update label="May 1, 2026" description="Clearer error messages from every provider" tags={["Improved"]}>
  Context length overflows, unsupported image formats, and other provider errors are now translated into plain, actionable messages instead of generic errors.
</Update>

<Update label="Apr 28, 2026" description="Generate speech and transcribe audio" tags={["API"]}>
  Two new endpoints: `/v1/audio/speech` for text-to-speech and `/v1/audio/transcriptions` for speech-to-text. Multiple providers including OpenAI and Mistral with automatic fallback.

  [Speech API →](/api-reference/endpoint/audio-speech-create) · [Transcription API →](/api-reference/endpoint/audio-transcriptions-create)
</Update>

<Update label="Apr 25, 2026" description="Edit images through the gateway" tags={["API"]}>
  Send image edit requests through `/v1/images/edits` with the same multi-provider routing and fallback as generation.

  [Image Edits API →](/api-reference/endpoint/images-edits-create)
</Update>

<Update label="Apr 23, 2026" description="Tag traffic by app with analytics headers" tags={["Analytics"]}>
  Pass `HTTP-Referer` and `X-Title` headers to label requests by app or site. Filter your analytics dashboard by these values to see cost and latency per integration.

  [Analytics headers docs →](/features/analytics-headers)
</Update>

<Update label="Apr 21, 2026" description="Get alerted before budgets run out" tags={["New"]}>
  Set dollar thresholds on API keys and receive Slack or Microsoft Teams webhooks when spend crosses them. Configurable trigger percentages give you time to act.

  [Configure alerts →](/features/alerts)
</Update>

<Update label="Apr 18, 2026" description="Route Claude Cowork through your org" tags={["Integrations"]}>
  Use Requesty as the backend for the Claude Cowork desktop assistant. All traffic gets unified analytics, cost controls, and model policies.

  [Set up Claude Cowork →](/integrations/claude-cowork)
</Update>

<Update label="Apr 16, 2026" description="Connect OpenCode with one-liner analytics" tags={["Integrations"]}>
  Route OpenCode terminal agent traffic through Requesty. A one-line installer adds analytics tracking to your setup.

  [Set up OpenCode →](/integrations/opencode)
</Update>

<Update label="Apr 14, 2026" description="Control guardrail actions per policy" tags={["Security"]}>
  The admin panel now lets you set each guardrail policy to Disabled, Report, or Mask individually. A new violations column and detail tab in logs shows exactly what fired.

  [Guardrails docs →](/features/guardrails)
</Update>

<Update label="Apr 10, 2026" description="Structured outputs work with the Responses API" tags={["API"]}>
  JSON Schema and json\_object modes are now available on `/v1/responses`, matching the Chat Completions feature set.

  [Structured outputs docs →](/features/structured-outputs)
</Update>

<Update label="Apr 7, 2026" description="Azure EU regions auto-detected" tags={["New"]}>
  Azure deployments across European regions are now automatically recognized under the EU filter in the Model Library and routing engine.

  [EU routing docs →](/features/eu-routing)
</Update>

<Update label="Mar 27, 2026" description="Redesigned model management" tags={["Improved"]}>
  Provider grouping with expand/collapse, region and capability filters, bulk approve/remove, preset quick-filters, and a "New" tab that surfaces recently released models per provider.

  [Manage approved models →](/features/approved-models)
</Update>

<Update label="Mar 24, 2026" description="Compare models side by side in the playground" tags={["New"]}>
  Pick two models, send the same prompt, and see which responds better. The redesigned chat playground also supports image attachments and markdown rendering.
</Update>

<Update label="Mar 20, 2026" description="See service account details at a glance" tags={["Improved"]}>
  Expandable table rows now show each service account's API keys, monthly spend, and creator at a glance.

  [Service accounts docs →](/features/service-accounts)
</Update>

<Update label="Mar 17, 2026" description="Send PDFs in your requests" tags={["New"]}>
  The gateway extracts and formats PDF content across providers that support document input. Just include the file in your chat completions request.

  [PDF support docs →](/features/pdf-support)
</Update>

<Update label="Mar 12, 2026" description="Pick a use case, skip the model selection" tags={["New"]}>
  Dedicated model aliases like `coding/` select the right model, provider, and parameters for your workload automatically.

  [Dedicated models docs →](/features/dedicated-models)
</Update>

<Update label="Mar 6, 2026" description="Google Gemini Embedding 2.0 support" tags={["New"]}>
  Generate embeddings with Google's latest Gemini Embedding 2.0 model through Requesty, with automatic provider selection.
</Update>

<Update label="Feb 26, 2026" description="Deeper analytics with percentiles and pivot tables" tags={["Analytics"]}>
  The analytics dashboard now supports P95 and P99 latency percentiles, pivot tables for multi-dimensional breakdowns, and flexible time ranges including This Week, Month, Quarter, and Year.

  [Usage analytics →](/features/usage-analytics) · [Performance monitoring →](/features/performance-monitoring)
</Update>

<Update label="Feb 24, 2026" description="See which models support tool calling" tags={["New"]}>
  The models list now shows which models support tool calling. Use this to filter models by capability before routing or to build smarter model selection.
</Update>

<Update label="Feb 20, 2026" description="Connect OpenClaw agents" tags={["Integrations"]}>
  Route OpenClaw autonomous agent workloads through Requesty for unified analytics and cost controls.

  [Set up OpenClaw →](/integrations/openclaw)
</Update>

<Update label="Feb 17, 2026" description="Restrict models per group" tags={["Improved"]}>
  Groups can now have their own approved model list, independent of the org-wide setting. Regional model approval handles providers with location-specific deployments correctly.

  [Groups docs →](/features/groups)
</Update>

<Update label="Feb 12, 2026" description="Spending alerts with Slack webhooks" tags={["New"]}>
  Set dollar thresholds on your organization and receive Slack notifications when spend crosses them.

  [Alerts docs →](/features/alerts)
</Update>

<Update label="Feb 6, 2026" description="Polished API keys table" tags={["Improved"]}>
  The API keys table is easier to scan with cleaner columns, hover tooltips for long values, and one-click copy. The same improved layout appears in both admin and user views.
</Update>

<Update label="Jan 29, 2026" description="Compare two requests side by side" tags={["New"]}>
  Select any two requests in the logs table and open a JSON diff viewer. Added, modified, and removed fields are highlighted with one-click filtering.
</Update>

<Update label="Jan 24, 2026" description="Filter traces by key, user, or ID" tags={["Analytics"]}>
  Filter the traces page by trace ID, API key name, or user email. Cached percentage is now visible per trace.

  [Session reconstruction docs →](/features/session-reconstruction)
</Update>

<Update label="Jan 21, 2026" description="Manage group budgets inline" tags={["Improved"]}>
  Groups now show spend percentage and budget overrides directly in the table. Admins can adjust limits without navigating away.

  [Groups docs →](/features/groups)
</Update>

<Update label="Jan 16, 2026" description="Update member roles from the dashboard" tags={["Improved"]}>
  Org admins can change member roles at both the organization and group level. Safety checks prevent admins from accidentally demoting themselves.

  [Users and roles docs →](/features/users)
</Update>

<Update label="Jan 12, 2026" description="Reasoning tokens visible in logs" tags={["Analytics"]}>
  A new column shows how many reasoning tokens each request consumed, giving visibility into model "thinking" costs.
</Update>

<Update label="Jan 6, 2026" description="Filter analytics by API key label" tags={["Analytics"]}>
  Scope cost, latency, and usage breakdowns to specific API key labels for more targeted reporting.

  [Usage analytics →](/features/usage-analytics)
</Update>