What we
ship.

The gateway now speaks the OpenAI Responses API at POST /v1/responses, next to Chat Completions and Anthropic Messages. Newer OpenAI SDKs, Codex CLI and the OpenAI Agents SDK use this format by default, so they now work with your OpenAdapter key out of the box.

What works: text and streaming (response.output_text.delta and friends), function tools with streamed arguments, reasoning summaries, image input on vision models, instructions, max_output_tokens, reasoning.effort and text.format for JSON output. Every model and every auto-* tier is available, with the same quota, failover and X-Auto-Model header as the other endpoints.

Not supported: previous_response_id (send the full conversation in input each call) and hosted tools such as web search or file search. Those return a clear error instead of doing something else.

Python:

from openai import OpenAI
client = OpenAI(api_key="sk-cv-...", base_url="https://api.openadapter.in/v1")
r = client.responses.create(model="GPT-6-Luna", input="hello")
print(r.output_text)

See the Responses section in the Guide for JavaScript and curl.

GPT-6-Luna is live and GPT-5.6-Luna is retired. Luna is the fast tier of OpenAI's GPT-6 line, the one OpenAI calls its most efficient model for focused, high-volume work. It carries a 1M-token context window with up to 128K output, reads text, images and files, and has a knowledge cutoff of May 2026 against February for its predecessor. Call it as GPT-6-Luna.

It is a pro-tier model at 1 request of quota per call, so it is available on every paid plan and the free tier. GPT-5.6 Luna was max-tier; this is a step down in price for the same job.

OpenAI has not published a standard benchmark table for Luna. What they do state:

We will add more figures as OpenAI publishes them rather than borrow numbers from elsewhere.

Calls to GPT-5.6-Luna now return a message pointing to GPT-6-Luna.

Sources: OpenAI announcement, model page.

Four new model names pick a model for you: auto-max, auto-pro, auto-lite and auto-free.

Each tier keeps a pool of its three to five fastest models, measured from the last 24 hours of real traffic. On the first turn of a conversation a small decisions model reads the request once and picks the model in that pool best suited to it: coding, agent loops with tools, long documents, images, or plain chat. The pick stays with the conversation, so an agent session does not hop models mid-task and prompt caching keeps working.

You always know what answered. The response's model field and an X-Auto-Model header name the model that served the request, and quota is charged at that model's rate. If the picker is unavailable, the fastest model in the pool answers. Plan rules are unchanged: auto-max needs a plan that reaches max-tier models, and auto-free works on every plan.

Koda uses auto-pro by default from its next release.

MiMo-V2.6-Pro is live. The flagship of the V2.6 series: 1.02T parameters with 42B active, a 1M-token context window with up to 128K output, and unlike V2.5 Pro it now reads text, image, video and audio. MIT licensed. Xiaomi positions it for complex projects, long-horizon agent work, security research and high-stakes tasks. Call it as MiMo-V2.6-Pro.

Xiaomi's published scores against the V2.5 Pro it replaces:

It is a reasoning model: it thinks before it answers, so give it an output budget of a few thousand tokens or short replies come back cut off. It costs 2.5 requests of quota per call and is available on every paid plan and the free tier. MiMo-V2.5-Pro stays available.

Source: MiMo-V2.6-Pro model card.

MiMo-V2.6-Flash is live. Xiaomi's efficiency checkpoint of the new V2.6 series: a 309B mixture-of-experts model with 15B active, a 1M-token context window, and text, image, video and audio input. MIT licensed. Call it as MiMo-V2.6-Flash.

Xiaomi's published scores, with the previous V2.5 Pro flagship for scale:

It costs 1.5 requests of quota per call and is available on every paid plan and the free tier, the same terms as MiMo-V2.5. It also joins the auto-pro pool as soon as it has enough traffic to be ranked.

Source: MiMo-V2.6-Flash model card.

MiMo-V2.5-Pro is live. It is Xiaomi's flagship: a 1.02T-parameter mixture-of-experts model with 42B active per token, a 1M-token context window, MIT licensed, and text only. Xiaomi built it for demanding software engineering and long-horizon agent tasks that span thousands of tool calls. Call it as MiMo-V2.5-Pro.

Xiaomi's published scores:

It costs 2.5 requests of quota per call and is available on every paid plan and the free tier. Use it for the hard, multi-step coding jobs, and MiMo-V2.5 when you need images, video or audio.

The old MiMo-V2-Flash name is retired. Requests for it now return a message pointing to MiMo-V2.5.

Source: MiMo-V2.5-Pro model card.

MiMo-V2.5 from Xiaomi is live. It is natively omnimodal: it takes text, images, video and audio in a single model, with a 1M-token context window. It is a 310B mixture-of-experts model with 15B active per token, released under the MIT license. Call it as MiMo-V2.5.

Xiaomi's published scores:

It costs 1.5 requests of quota per call and is available on every paid plan and the free tier, the same terms as the other flash vision models. Reach for it when the input is a document, chart, screen recording or audio clip rather than plain text.

Source: MiMo-V2.5 model card.

DeepSeek-V4.1-Flash is live. It reads text and images, carries a 1M-token context window, and is built for input-heavy agentic and coding work. Reasoning effort is adjustable, so it can answer quickly or think hard on request. Call it as DeepSeek-V4.1-Flash.

DeepSeek publishes these scores against the earlier V4 Flash, all at maximum reasoning effort:

It costs 2 requests of quota per call and is available on every paid plan and the free tier. DeepSeek-V4-Flash stays exactly as it is at 1 request per call, so nothing changes for existing setups. Pick V4.1 when the task is a long agent run or terminal work, and V4 when you want the cheapest fast model.

Source: DeepSeek-V4.1-Flash model card.

When you create a key you now choose what it can do: Inference (chat, audio, embeddings, images) and/or Manage account (keys, billing, usage). New keys are inference-only by default — the right shape for a key you paste into an editor, because it can never rotate your keys or touch billing if it leaks.\n\nNothing changes for keys you already have: they keep exactly the access they had. Scopes show as small tags on the Keys page.

Opening a live Koda session from the dashboard used to take two confirmations: matching a six-digit code in the browser, then running /remote approve in the terminal. Both are gone.

Reaching your session already required your OpenAdapter credentials — the same ones that authorize every model call Koda makes. A second and third confirmation guarded a door you had already unlocked, and the terminal step in particular defeated the point of remote: it asked you to walk back to the machine you had walked away from. Pick your session, and you are watching it.

Sessions stay end-to-end encrypted between your terminal and your browser; the relay still forwards frames it cannot read. Permission gates are untouched — a dangerous command still stops and waits for you to approve it.

Two fixes ship alongside. Refreshing the page no longer loses the conversation or the model and thinking controls: a long transcript exceeded the relay's frame limit, which quietly killed the connection every time you reattached. And a permission prompt raised while your browser was closed now waits for you instead of expiring unseen — the relay tells Koda when someone is actually watching.

Qwen3.8-Flash is live. It reads text, images and video, carries a 1M-token context window, and is the least expensive of the three vision models we added this week.

Alibaba positions it for coding assistance, agentic workflows, document and codebase analysis, chart reading and long-video analysis. Call it as Qwen3.8-Flash.

It costs 1.5 requests of quota per call and is available on every paid plan and the free tier — the same terms as GLM-5.3-Flash and DeepSeek-V4-Flash-Vision.

Alibaba has not published benchmark scores for this model yet. We will add them to the model page once they exist rather than borrowing figures from its siblings.

GLM-5.3-Flash and DeepSeek-V4-Flash-Vision are live. Both take images as well as text, and both carry a 1M-token context window.

GLM-5.3-Flash is built for coding and long-running agent work — it scores 84.3 on Terminal-Bench 2.1, within a point of the frontier models, and also accepts video input. DeepSeek-V4-Flash-Vision adds image understanding to the V4 Flash line, which posts 79% on SWE-bench Verified and 88.4% on LiveCodeBench, and is aimed at documents, charts and multimodal agent workflows.

Both are available on every paid plan and on the free tier, and cost 1.5 requests of quota per call. Call them as GLM-5.3-Flash and DeepSeek-V4-Flash-Vision.

Benchmark figures are as published by the model authors; DeepSeek's vision variant is marked experimental upstream.

Speech-to-text now works as audio arrives instead of only after a recording ends. Each sentence comes back the moment the speaker finishes it, so a voice agent can start responding before the person has stopped talking.

Open a WebSocket to wss://api.openadapter.in/v1/realtime/transcribe, send microphone audio, and read transcripts as they land. Your normal API key works — nothing to enable.

Available on parakeet, whisper-1, whisper-large-v3 and whisper-large-v3-turbo.

You're charged per transcribed sentence, not per connection or per second of audio — an open socket with nobody talking costs nothing.

Read the guide →

Qwen3.8-27B is live on Pro plans at 0.25× quota — four requests for the price of one.

It handles a 250K-token context, supports tool calling, and thinks step by step before answering (reasoning is returned separately, so you can show or hide it). Released by Alibaba on 14 August 2026.

Call it as Qwen3.8-27B from any client.

One note if you use it programmatically: thinking is on by default and consumes part of your max_tokens budget. Give it room — a few thousand tokens — or turn thinking off if you only want the answer.

Four models land on OpenAdapter today, and one is on its way out.

Hy3 and GPT-5.6 Luna — 1x quota

Both come in at 1x quota, the same cost as a standard model, which makes them the cheapest MAX-tier models on the platform. If you want frontier-class output for everyday agent loops without burning through your plan, start with these two.

Hy3 is Tencent's Hunyuan 3. Luna is the newest GPT-5.6 variant.

DeepSeek V4 Pro 0813 — 2x quota

DeepSeek re-post-trained V4 Pro. It serves under the same name you already use — DeepSeek-V4-Pro — so nothing in your config changes.

Qwen 3.8 Max — 4x quota

Alibaba's newest flagship and the largest Qwen we carry. It is the most expensive model on the platform at 4x quota, so reach for it when the task actually warrants it.

All four are MAX tier, so they need a paid plan.

GLM-4.7 is retiring

GLM-4.7 is being retired. You do not need to change anything — requests for GLM-4.7 now serve GLM-5 automatically, so existing configs, scripts and agents keep working. GLM-5 is the stronger model on every axis, and it costs the same 1x quota.

If you would rather be explicit, switch your config to GLM-5 at your convenience.

If web_search has been returning "No results found", this fixes it — but you need to re-run one command.

What was wrong

Two separate faults, which together meant search was broken for essentially everyone:

1. The search tool never reached our servers. The MCP we installed talked to a search instance on localhost:8888 — a local container almost nobody runs. So it had nothing to query.
2. Our own search fleet was being blocked. The engines behind it refuse traffic from datacenter addresses, so even a correctly-pointed request came back empty roughly eight times in ten.

What changed

Search now runs through the gateway. Your machine asks us, we handle the fleet and which engines to use. That means the next time an engine starts blocking, it is a fix on our side — not a reinstall on yours.

You need to re-run setup

The fix ships in the installer, so machines that already have the old search tool keep the old behaviour until you re-run it. From your terminal:

curl -sL "https://api.openadapter.in/api/setup/mcp-search?key=YOUR_API_KEY&tool=claude-code" | bash

Windows (PowerShell):

irm "https://api.openadapter.in/api/setup/mcp-search-ps?key=YOUR_API_KEY&tool=claude-code" | iex

Swap tool=claude-code for opencode if that is what you use. Your key is on the API Keys page. Restart your editor afterwards.

Windows users: the PowerShell installer itself was also broken and never completed. That is fixed in the same release.

Checking it worked

Ask your agent to search for something current. You should get real results rather than "No results found".

Koda is out of beta. Until today npm i -g @openadapter/koda gave you 1.0.0-beta.13 — latest had been frozen there for months while the real work happened on @beta. This release moves latest onto current code:

npm i -g @openadapter/koda

Debugging — new

Koda speaks the Debug Adapter Protocol. It can set a breakpoint, launch or attach, then read the real stack and actual variable values at the moment things broke — step through, and evaluate expressions in the paused frame.

It discovers 14 adapters on your PATH, with an xcrun fallback for the lldb-dap Xcode hides. It registers the tool only when an adapter genuinely exists on your machine, and never loads the engine until you actually debug.

This is the difference between reading a stack trace and watching the value change.

Delegation — new

A task tool with context-isolated subagents — general, explore, or your own in .koda/agents/*.md. They run in parallel and only their results come back, so the main context stays clean. A live line under the input shows how many are working and for how long.

Skills — new

koda skill search / add / remove / list / update, against the open skills.sh registry.

Editing — new

hashline_edit (vendored from oh-my-pi, MIT). Reads carry a content tag and line numbers; edits are line-anchored operations that never echo old text back. A stale tag fails closed with a re-read instruction rather than quietly corrupting the file.

Choose it in /settings → Edit tool, which enforces one or the other — running both just hands the model a coin to flip.

Type errors in the loop

After an edit, the errors your change introduced — including the call sites you broke somewhere else — come back in the tool result, so the model fixes them in the same turn. TypeScript needs no install; Python, Go, Rust, Java and C/C++ work through their standard language servers.

Koda finishes what it starts

The big one if you have ever watched an agent stop halfway.

There is now a completion gate on every model tier, not just the ones running the overseer. The old check only fired when the model had made a todo list — which happened in 13.6% of multi-step tasks, so on a cheap model nothing was checking at all. The new gate costs zero extra model calls.

Todos can also carry a verify command, and marking one done is only a claim until Koda runs that command itself and sees it exit 0.

Fullscreen mode

KODA_FULLSCREEN=1 gives a live sidebar: session, context, model, LSP status, and the todo plan marked [ ] / [x] / [✓] — that third mark meaning Koda verified it, not that the model said so.

Plus 15 themes on a four-role colour system. The old palette used accent 102 times against text's 16, so everything read as important and therefore nothing did.

Fixed

• Theme changes apply instantly instead of needing a restart
• The sidebar scrolls
• A language server's stderr can no longer shred the fullscreen frame
• A deleted working directory explains itself instead of throwing uv_cwd
• Stray ... on fullscreen rows
• Plan mode records a plan the gates can actually check
• The overseer toggle stops claiming to be on when it is suppressed
• Retried timeouts stay quiet
• A self-update rule that could have pulled beta users backwards onto latest

DeepSeek V4 Flash 0731 is a re-post-trained revision of V4 Flash, and it is now a primary backend behind DeepSeek-V4-Flash on OpenAdapter. Same model name, same quota cost. What changed is what it can do as an agent.

What it is

A sparse mixture-of-experts model: 284B total parameters, 13B active per token, tuned for coding, reasoning and agent workflows. Only a fraction of the network fires per token, so it answers at small-model speed while reasoning like a much larger one.

Independent evaluation

Measured by Artificial Analysis, who run models themselves rather than republishing vendor claims:

90.8% on GPQA Diamond is the number to look at — that is graduate-level science reasoning, from a model with 13B active parameters. The low CritPt and non-hallucination figures are equally worth knowing: it is strong at structured reasoning, weaker at research-frontier physics, and like most models it will still assert things confidently when it does not know. Do not use it as an oracle.

What the retrain changed

The weights are the same size. The post-training is not. DeepSeek's own agent-benchmark figures for this revision:

Note the shape: single-shot coding barely moved (SWE-bench flat at 79.0) while multi-step agent ability transformed. This model got better at operating, not at writing a function. Driven in a loop with tools you will feel it; on one-off questions you may not. DeepSeek claim 0731 now beats V4 Pro Preview on every agent benchmark they published — Terminal Bench 82.7 against Pro's 72.1.

Treat that second table with care: those are DeepSeek testing DeepSeek, on a harness that is not public yet, and two of the nine are internal sets the company built. The Artificial Analysis figures above and our own measurements below are the parts with independent backing.

How fast it is here

Measured through our gateway, median of three runs each:

Thirty-four thousand tokens of code answered in under five seconds is what makes it usable as an agent backend rather than just a chat model.

Capability check

We run every new model through the same suite before promoting it. This one passed all six:

Using it

Nothing to change. Point at DeepSeek-V4-Flash and you get it:

curl https://api.openadapter.in/v1/chat/completions \
  -H "Authorization: Bearer $OPENADAPTER_API_KEY" \
  -d '{"model":"DeepSeek-V4-Flash","messages":[{"role":"user","content":"Refactor this module"}]}'

The other backends stay in place as automatic failover, so if this one is ever busy your request still completes — you just will not notice.

OA-Robin-Mini-Preview is the first model we built and host ourselves, and it is live now.

Because it runs entirely on our own hardware, your prompts never leave our infrastructure and nothing is retained — the same privacy guarantee as our other Edge models.

• Private by default — great for confidential chat, brainstorming and creative work you would rather not send to a third party.
• 256K context with vision, tool calling and JSON mode, so it slots straight into agents and long-running workflows.
• 0.5x multiplier — every request costs half a normal one, so you get roughly double the usage from the same plan.

It is a preview, so expect it to keep improving. A much larger model in the same family is coming soon — we will announce it here when it lands.

Try it from the Models page, or just point your client at OA-Robin-Mini-Preview.

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.