What we
ship.

Share your referral link from the Referrals page. When a friend signs up and makes their first purchase, they get 20% off — applied automatically at checkout, no code to enter. You earn 20% of what they paid as credit, used automatically toward your own next plan. Track your link and referrals right from the dashboard.

Koda's first launch now connects to your account through the browser:

• Run koda — your browser opens the dashboard with a one-time code.
• Sign in (or create an account), check the code matches your terminal, and click Approve.
• Koda receives its own named API key (e.g. Koda CLI — MacBook-Pro) and finishes setup automatically — revoke any device from the Keys page.

Prefer the old way? koda setup sk-cv-… and the OPENADAPTER_API_KEY env var still work everywhere, including CI.

Browser-based, OpenAI-compatible apps — like Janitor AI, SillyTavern, and other web chat front-ends — can now call the API directly.

• Set the endpoint to https://api.openadapter.in/v1/chat/completions and use your sk-cv-… key.
• Previously these apps hit a browser "network error" because the API only accepted requests from our own domains. The /v1/* endpoints now accept any origin.

Note: only paste your key into apps you trust — a key used in the browser is visible to that app.

The limited-time free promo for MiniMax-M3 has ended. It's now a standard premium model:

• It counts toward your request quota like other top-tier models.
• It's rate-limited per your plan tier (no more special promo allowance).

Thanks to everyone who tried it during the promo. It remains available on your plan — just under normal quota now.

GLM-5.1 now advertises and serves a 128K context window — up from the previous 32K cap.

• Large codebases, long documents, and extended chats no longer hit the old limit.
• Requests are automatically routed to a backend that can handle the full window; very large prompts simply skip any route that can't.

No action needed — your existing calls just get more headroom.

The GO plan now includes the latest 0G Network models — DeepSeek-V4 (Pro & Flash), Qwen3.7-max, 0GM-1.0, and MiniMax-M3 — alongside the existing 0G lineup.

These models also group correctly under 0G Network on the Models page instead of slipping into "Other."

For a limited time — through June 18 — MiniMax-M3 is free for everyone.

• It doesn't consume your request quota.
• It has no per-minute rate limit on our side.

Heavy concurrent use may still see brief upstream retries. After June 18 the model reverts to its normal limits automatically — no action needed.

Attach to your live Koda CLI session from the dashboard — watch it work in real time, send it prompts, and answer its permission gates, all end-to-end encrypted. Our relay only forwards ciphertext and cannot read your session.

How it works

• In the CLI, run /remote on (or koda --remote) — it shows a QR code and a short pairing code.
• Open the Koda page → Remote tab → pick your session (or Add by code), then confirm the 6-digit code matches what your terminal shows. That match is the security check that defeats a man-in-the-middle.
• /remote off to detach. Pairing codes expire after 5 minutes.

You're in control — pick your blast radius

Three presets decide what a remote viewer can do:

• Read-only — watch and read only.
• Read + Write, no exec (default) — read and edit files, but run no commands.
• Full autonomous — full control; dangerous commands like sudo and rm -rf still need an explicit Approve in the dashboard.

The policy is enforced locally by your CLI, and secret paths (~/.ssh, ~/.aws, /etc, **/.env) are hard-blocked under every preset. Keep the preset as low as the task needs, and detach when you're done.

The Koda page now feels like the rest of the dashboard instead of a separate site.

• Follows your theme — light or dark, with the standard page header, cards, and the official Koda wordmark.
• Spreads across the page — the early-access, setup, and connected views fill the width like every other section instead of sitting in a narrow column.
• Easier to scan — a tidier feature preview while you're on the waitlist, a side-by-side setup wizard once you're in, and clearer session and install stats when Koda's connected.

The Models page now shows everything at a glance and lets you filter to exactly what you want.

• Tier badges — Max / Pro / Lite on every model card.
• Quantization — see the serving precision (FP8, BF16, …) for each model.
• New filters — filter by tier, ≤1× quota cost, and tool-calling support, alongside the existing text/vision/embedding/audio filters.

Context length, per-request quota cost, and vision/tools/JSON capabilities remain on every card.

Koda is OpenAdapter's own terminal coding agent: Claude-Code-class, on 70+ models with one key. There's a new Koda page in the sidebar.

Join the waitlist

Click Get early access. Invites roll out in waves, and Max plans skip the line, switched on within hours. Once you're in, the page walks you through install and setup, then becomes your personal Koda dashboard.

What makes Koda different

• Overseer reviews its own work and runs it to be sure, pulling in a stronger model when it's stuck. Cheap models that actually finish.
• Jobs schedule autonomous tasks that run while you sleep.
• Checkpoints & rewind, memory + vector recall, built-in tools + MCP, ask-before-dangerous permissions, and zenitsu speed that never idles on a rate limit.

Your Koda dashboard shows sessions, version, where it's installed, and a direct line to tell us what to improve. Anonymous to us, never your code.

Model listings now tell you the numeric precision a model is served at, so you can pick with eyes open.

• GET /v1/models (and the public models list) now include a quantization field — e.g. fp8, int8, bf16 — when we know it.
• Most large models run at fp8; smaller or budget routes may be int8. Models with unknown precision simply omit the field.

No action needed — it's purely additive on the responses you already get.

How it works

Share your personal referral link from the new Referrals page. When a friend signs up with it and makes their first paid purchase, you both get 20% off:

• Your friend gets the discount on their first plan, applied automatically at checkout.
• You get the discount on your next plan purchase — it's waiting for you the next time you upgrade or re-subscribe.

Track who you've referred and where each one stands right from the dashboard. The discount applies before checkout, so the price you see is the price you pay — no codes to enter.

Heads up: Teams is a request-specific feature. If you want it enabled on your account, click the support chat at the bottom-right — we'll switch it on for you.

What it does

• Create a team and invite peers via a shareable join link (optional expiry, max-uses, rotate, revoke) or by email.
• Owner sees aggregate + per-member usage — requests, tokens, est. provider cost, model breakdown, last-active, and which client (Claude Code, Cursor, Cline, etc.) each member uses.
• Per-member drill-down with daily activity chart and top models.
• Members can leave at any time; only the owner sees usage.

What it doesn't do

Owners do not see your prompts, request bodies, or API keys — ever. The privacy line is reinforced at every consent point. Each member still uses their own plan and quota; the team doesn't share capacity.

Redesigned dashboard

Real signal, not vanity numbers. An activity heatmap in the GitHub style, quota windows with countdown timers, top-model breakdown, upgrade hints sized to your actual usage. The whole app feels calmer.

Public status page

/status is now public — no auth, indexable, models grouped, gradient bars by error count. Link to it from anywhere.

Shareable activity widget

Generate a shareable SVG of your gateway activity at https://api.openadapter.in/embed/<token>.svg — drop it on a README, a blog post, or your portfolio. Three formats:

• ?format=svg — the badge image (default)
• ?format=iframe — a 320×120 iframe with hover detail
• ?format=json — raw numbers for your own UI

Toggle on/off from the Integration page.

Fixes & QOL

Accessibility across keyboard navigation and screen-reader labels, sidebar upgrade banner sized to your plan.

• Send a message, switch tabs, come back — your conversation is intact across both tabs.
• Messages typed while offline send automatically when the connection returns.
• Replying after a resolved conversation no longer creates ghost threads.
• The unread badge clears properly once you've read everything.

Fixes & QOL across the chat bubble, scroll behavior, and notification sounds.

Edge tools

Four new tools join the Tools page, powered by OpenAdapter Edge:

• OCR — extract text from images at scale
• DocParse — structured parsing of PDFs, DOCX, and similar
• Text2Doc — generate documents from prompts
• Hybrid embeddings — dense + sparse retrieval in one call

Support chat

A chat bubble at the bottom-right of the dashboard puts you in direct conversation with support. Your conversation persists across sessions.

Playground

The Playground gets a wider message column, a cleaner model picker, and a more readable prose render.

Full docs.openadapter.dev is live — versioned, full-text search, code-tabbed examples for Python, JS, and curl.

The Docs link in your sidebar opens it directly. Any /docs or /guide URL in the dashboard now redirects there too, so old bookmarks still work.

0G Network

0G Network is now a dedicated provider on the Models page — TEE-attested, zero-data-retention models with privacy markers on hover.

OpenAdapter Edge

A dedicated bare-metal compute brand on the Models page. TEE-attested variants of popular open models, plus dedicated embedding endpoints.

GO plan

A new OpenAdapter GO plan — exclusively on 0G, no RPM caps. For workloads where data residency is non-negotiable.

Announcements

In-dashboard announcement banners — when something new ships, you'll see it on next dashboard load.

Fixes & QOL

A maintenance banner so you'll know when something's actively being worked on, plus per-model privacy documentation across 75+ models.

• Collection cards now show real counts and metadata instead of stalling on empty placeholders.
• Embedding upload auto-retries when the upstream embedder is busy, with better duplicate-collection handling.
• Chunked text uploader no longer loops on certain file sizes.
• "View Collection" button now actually navigates to the Collections tab.
• RAG chat gets a phased loader and proper markdown rendering — streamed answers look right while they arrive.
• Code SDK pulls model and collection names from the live API instead of a stale snapshot.

Fixes & QOL across collection naming, search bar alignment, and default model selection.

• Anthropic-format 429s on /v1/messages — Claude Code now retries cleanly instead of erroring out.
• Multipart /v1/audio/transcriptions so tools that default to form-data upload without manual reshaping.
• Better error messages — useful 400s reach you intact instead of generic upstream noise.
• Large audio uploads return a proper 413 instead of timing out.

Fixes & QOL across the model picker, integration page, and stream-finalization edge cases.

Tools

A new Tools page with cards for web search, scrape, crawl, plus TTS and STT. Each tool ships with a copyable code sample and a live preview.

Vector DB

Full Vector DB — manage collections from the dashboard, upload documents, search semantically, and chat with your data through the built-in RAG playground. The Code SDK panel emits ready-to-paste snippets for Python and JavaScript.

Your Vector DB plan stays in sync with your OpenAdapter plan, so quota matches everywhere.

Docs

A proper /docs section with editable pages — replaces the static in-app guide.

Burst mode

Allow 2× burst above your RPM limit before throttling kicks in. Useful when an agent fires parallel tool calls — the natural bunching no longer trips the rate limiter.

New endpoints

• /v1/completions for legacy text completions
• /v1/embeddings for vector embeddings
• /v1/audio/transcriptions and /v1/audio/speech for STT + TTS

Misc

• KiloCode added to the integration page.
• A comprehensive Developer Guide covering burst, retry, tools, JSON mode, streaming, and chaining — copyable for agents.

Onboarding

A new onboarding flow walks first-time users through their first request without leaving the dashboard.

Per-key lifetime limits

Cap any API key's total requests or tokens — set it from the Keys page, choose hard cutoff or warn-mode.

Capability badges

Model cards now show at a glance which models support tool calling, JSON mode, and vision — no more guessing whether to bring out the parser.

More providers and models added across the catalog.

Fixes & QOL

Usage reset timer now reflects the real window even when it's already expired. Dashboard logs only show the requests you actually made — no internal noise.

• One-liner setup scripts for Claude Code, OpenClaw, Cursor, Cline, Continue, Windsurf, and Aider — paste, run, done.
• MCP Store with Search, Vision, and Image MCPs ready to install.
• Paid plans live — Lite, Pro, and Max with one-tap checkout.
• Cleaner billing and login screens.

Fixes & QOL

Audio transcription quota counting, Anthropic-format error shapes on /v1/messages.

OpenAdapter gives you one API key that works in every AI tool you already use — Claude Code, Cursor, Cline, Continue, Aider, and more. One subscription, one quota, no juggling provider keys.

• OpenAI SDK and Anthropic SDK formats both work — same key, both shapes.
• Live usage dashboard with countdowns to your quota reset.
• A starter Developer Guide to get you running in a couple of minutes.