---
name: OpenRouter
slug: openrouter
domain: openrouter.ai
description: Unified API and marketplace that routes requests across hundreds of large language models from many providers, with automatic fallbacks, normalized billing, and usage-based pricing.
category: ai
sources: 2
total_releases: 136
releases_last_30d: 4
avg_releases_per_week: 1.1
last_updated: 2026-10-13
tracking_since: 2024-12-05
canonical: https://releases.sh/openrouter
overview_url: https://releases.sh/openrouter/overview.md
accounts:
  discord: "fVyRaUDgxW"
  github: "OpenRouterTeam"
  x: "openrouter"
---

## Overview

A $113M Series B anchored a busy stretch of shipping across the routing layer, developer tools, and enterprise controls.

**Multi-provider failure visibility improved** — When all provider fallbacks fail, error responses now carry a `previous_errors` array listing every attempted provider's error code, message, and name. Diagnosing cascading failures across providers no longer requires correlating separate logs.

**Enterprise IP filtering went live** — Organizations on enterprise plans can restrict API key usage to approved IP address ranges from Privacy settings, tightening the blast radius of any leaked key. IP allowlists also began actively blocking non-approved IPs with a `403` response, upgrading what had previously been a passive advisory.

**Presets expanded across three API surfaces** — Presets gained support for the Responses API via `POST /api/v1/presets/:slug/responses`, the Anthropic Messages API via `POST /api/v1/presets/:slug/messages`, and a direct creation path from inference request bodies. The TypeScript and Python SDKs ship the new routes.

**Workspace and observability management APIs arrived** — New REST endpoints landed for programmatically managing bring-your-own-key credentials and observability destinations (Datadog, Langfuse, LangSmith, and others) via management key authentication.

**Model comparison and rankings got richer** — A new comparison tool lets you benchmark up to five models side by side on pricing, context length, and benchmark scores. Rankings charts added a percentage-normalized toggle alongside raw token-volume views, and a `GET /api/v1/datasets/rankings-daily` endpoint exposes the underlying top-50 dataset.

**Activity and logging tools sharpened** — Negation filters arrived so any filter chip can be toggled to "is not," Activity deep links now point to individual messages via `?message=<n>`, and workspace sidebar navigation surfaces Activity and Logs pre-filtered per workspace. The `preset_id` field on generation responses ties each completion back to the preset that produced it.

<Source name="Blog Announcements" slug="openrouter-blog" type="feed" releases="68" latest-version="3.3" latest-date="2026-10-07T00:00:00.000Z" url="https://releases.sh/openrouter/openrouter-blog" />
<Source name="Changelog" slug="openrouter-changelog" type="feed" releases="64" latest-date="2026-06-04T00:00:00.000Z" primary="true" url="https://releases.sh/openrouter/openrouter-changelog" />

## Recent Releases

_Summaries below — fetch the release's `canonical` URL for full content, or `url` for the original source._

<Release source="openrouter-blog" date="October 7, 2026" published="2026-10-07T00:00:00.000Z" url="https://openrouter.ai/blog/announcements/elevenlabs-on-openrouter/" canonical="https://releases.sh/release/rel_B-I8UTfGV3PM11s3GOjkH" truncated="true">
### ElevenLabs is now on OpenRouter

Nine Text to Speech and two Speech to Text models from ElevenLabs are now available through OpenRouter's audio/speech and audio/transcriptions endpoints using an existing OpenRouter API key, including Eleven v4, v4 Turbo, and Scribe v2. All ElevenLabs models are 50% off OpenRouter list price through October 19.
</Release>

<Release source="openrouter-blog" date="October 2, 2026" published="2026-10-02T00:00:00.000Z" url="https://openrouter.ai/blog/announcements/model-router-benchmarks/" canonical="https://releases.sh/release/rel_6vF-h-RAE0LAj_rWyT_64" truncated="true">
### Model Router Benchmarks

OpenRouter introduced a Model Router Benchmarks page that scores routers across varied domains and synthesizes quality, speed, and cost into a 0 to 10 Router Index, with a slider to adjust the default 60/20/20 weighting. The page lists benchmarks for routers including Auto, Fugu Max, Fugu Ultra v2, Jev Router, Pareto, and NVIDIA Switchyard, alongside individual models as baselines, and excludes alias-style routers like Pareto Code, -latest slugs, and Fusion.
</Release>

<Release source="openrouter-blog" date="September 28, 2026" published="2026-09-28T00:00:00.000Z" url="https://openrouter.ai/blog/announcements/security-center/" canonical="https://releases.sh/release/rel_WEb_gEQjs44ZLo1tw5puy" truncated="true">
### Manage and de-risk your API keys with new Security Center

OpenRouter's new Security Center shows every key across workspaces in one place, scoring risk by spend limit and expiration, with bulk actions to disable, archive, or cap up to 500 keys at once and a CSV export of any recommendation's keys and owners. The IP allowlist, previously in privacy settings, gets its own tab and now applies to every key in an account or organization, rejecting off-list requests with a 403 Forbidden.
</Release>

<Release source="openrouter-blog" date="September 22, 2026" published="2026-09-22T00:00:00.000Z" url="https://openrouter.ai/blog/announcements/batch-api/" canonical="https://releases.sh/release/rel_kMKoYoKRazUm4DHuk4XSy" truncated="true">
### Batch API: half-price inference by bundling requests

OpenRouter launched an asynchronous batch API at api/v1/batches supporting chat completions, responses, messages, and embeddings, with providers generally charging 50% or less of normal per-token pricing in exchange for completing requests within a 24-hour window. Across 230k+ beta batches, the median finished in 7 minutes and 90% within an hour.
</Release>

<Release source="openrouter-blog" date="September 9, 2026" published="2026-09-09T00:00:00.000Z" url="https://openrouter.ai/blog/announcements/us-in-region-routing/" canonical="https://releases.sh/release/rel_gOT3qDFiXWWdXzH-x2x3o" truncated="true">
### In-Region Routing: Keep your data in the US or EU

Requests to us.openrouter.ai and eu.openrouter.ai are decrypted inside the region and routed only to providers operating there, and a request fails with a 404 rather than falling back outside the region when no in-region provider serves the model. In-Region Routing is available on the Business and Enterprise plans, and can be enforced per workspace, team, or API key with Guardrails.
</Release>

<Release source="openrouter-blog" date="September 8, 2026" published="2026-09-08T00:00:00.000Z" url="https://openrouter.ai/blog/announcements/shell-tool/" canonical="https://releases.sh/release/rel_hmjPfHdaR496gR1fOHsJX" truncated="true">
### Give any model a terminal and files

OpenRouter launches the openrouter:shell server tool and a Files API, letting any model that supports tool calling run commands in a hosted Linux container, upload files to work with, and download outputs. Both are in beta, with sandbox time billed at $0.0001 per second as part of the request.
</Release>

<Release source="openrouter-blog" date="August 21, 2026" published="2026-08-21T00:00:00.000Z" url="https://openrouter.ai/blog/announcements/image-benchmarks/" canonical="https://releases.sh/release/rel_rE-VqVjaFgPR0Zg_XXqp4" truncated="true">
### Image Benchmarks: See the Capabilities of Every Model

OpenRouter launched Visual Image Benchmarks showing every result from challenging prompts across 39 image models in a sortable grid by price and generation time, with the same side-by-side format extended to video and speech models. Prompts are grouped into seven families covering improbable scenes, counting, text rendering, spatial relations, negation, editing, and consistency.
</Release>

<Release source="openrouter-blog" date="August 17, 2026" published="2026-08-17T00:00:00.000Z" url="https://openrouter.ai/blog/announcements/activity-dashboard/" canonical="https://releases.sh/release/rel_x7xqGC1jk2oJQWn539AT6" truncated="true">
### Understand your AI usage: every agent, model, and request

OpenRouter's new Activity dashboard breaks down spend, requests, tokens, cache hit rate, and blended cost per million tokens across agents, models, API keys, and team members, with Overview, Trends, Explore, and Guardrails views that link through to filtered logs and a Generation detail view covering cost, latency, routing, and attribution. All data is available through the Analytics API and an openrouter-analytics skill for querying usage from an agent or terminal.
</Release>

<Release source="openrouter-blog" date="August 12, 2026" published="2026-08-12T00:00:00.000Z" url="https://openrouter.ai/blog/announcements/web-search-benchmark/" canonical="https://releases.sh/release/rel_Y8Praw8jhxHQHiOEcxzHQ" truncated="true">
### Live Web Search Benchmarks: Pick the Right Engine, Depth, and Model for Your Agent

OpenRouter published live leaderboards across BrowseComp, DeepSearchQA, WideSearch, and HLE that rank model, engine, and search-budget combinations by quality, value, and speed. Findings show raising the search budget from 1 to 25 turns roughly doubles scores at 2.5-7x the cost, and that model choice moves results more than engine choice.
</Release>

<Release source="openrouter-blog" date="August 10, 2026" published="2026-08-10T00:00:00.000Z" url="https://openrouter.ai/blog/announcements/introducing-the-new-auto-router/" canonical="https://releases.sh/release/rel_vM_Ln0iAVxIUteMdxDXv8" truncated="true">
### Model Routing Powered by Wisdom of the Market

The Auto router for openrouter/auto now selects models using the past 7 days of aggregate spend on OpenRouter, classifying each prompt into one of roughly 30 task types and routing to the models the community spends on for that task. A cost_tier parameter (low, medium, high, xhigh, max) sets the spend band, and sticky routing keeps multi-turn conversations on one model while it remains a leading choice.
</Release>

## Fetching more

Append `.md` (markdown), `.json` (raw data), or `.atom` (feed) to any URL on this page.

- Per-source history: `https://releases.sh/openrouter/{source-slug}`
- Atom feed: `https://releases.sh/openrouter.atom`
- Individual release: `https://releases.sh/release/{release-id}`