Changelog
Improvements and fixes in each release, newest first. New features are announced on the roadmap.
1.3.46
Section titled “1.3.46”- Conversation items show their parent and response, so a client can rebuild the current thread. Each item of
GET /v1/conversations/{id}/itemscarrieszabio.parent_idandzabio.response_id, andGET /v1/conversations/{id}carrieszabio.leaf_id. Branching still happens only throughprevious_response_id. - Ask Zabio on every page. A button at the bottom right of every page of zabio.ai, the docs and the dashboard opens Ask Zabio: ask a question about Zabio and get an answer from the docs, with links to the pages it comes from. Under each answer you see the model that answered and what the answer cost, and what the same answer would have cost on a frontier model. It needs no account or key. Press
?to open or close it, or write to hello@zabio.ai to talk to us. - A chat in the dashboard. Chat in the menu (
app.zabio.ai/chat) talks to your models with your own key, at your usual prices, and keeps each chat as a stored conversation. Pickauto,auto/cheap,auto/bestor any model your organization allows. Under each answer you see the modelautopicked, what the answer cost, and what the same answer would have cost on the cheapest frontier model. Use this in your code shows the exact API call for the conversation. The first key made at signup now has the Conversations scope as well as Chat; a key without it gets a link to make one that has it. - The chat inside the dashboard. Signed in, Chat opens inside the dashboard: the menu becomes a strip of icons beside your chats, so the conversation keeps its width, and it opens out to the full menu and back. Your organization, its credit and the search stay at hand. On a phone, the menu and your chats each open as a panel of their own. Without an account, the chat stays full screen as before.
- Easy classification jobs on
autogo by our measurements of today’s models, and the price comparison counts what each side bills. Our second study of Jev measured it against the text modelsautopicks today on 180 easy classification jobs: Jev got every field right on 85 percent, level withgpt-6-luna(88 percent), andclaude-haiku-5-5on 81 percent. Zabio’s estimate of the routed model’s price now counts the tokens your JSON schema adds to the input and the thinking of a model whose setting reasons, and its estimate of Jev’s price follows TypeSafe’s current count, so of two models measured level the one Zabio estimates cheaper is now much closer to the one that bills less. On our test requests about 6 percent of easy jobs now go togpt-6-luna, each one billed at or below Jev’s price, and Jev answers the rest. The same estimates apply to every job Jev can answer onauto, toautolines inside a batch, and toPOST /v1/public/analyze. See Classification jobs on auto. - The AI Firewall’s model check reads more of an image and of a PDF. With the paid tier, and on the AI Firewall check with the model check: text drawn a few shades from a flat background (white on white, a banner’s own colour) is made readable before the image is read. On 44 such images with a published injection the check caught 43; it caught 15 before. Benign text hidden that way is flagged more often too. A JPEG that carries an EXIF orientation is turned the way models turn it. A scanned PDF is now read by its pages’ images when they are stored as JPEG, the first 8 of a document, each counted and billed as an image; before, a scan was not read. A document block’s
titleandcontexton/v1/messagesare read as text, each reported at its own path. An image checked before this release is checked once more. See the AI Firewall. - Medium classification jobs on
autogo by our measurements. Our second study of Jev measured it against the text modelsautopicks today, on 56 classification jobs rated medium: Jev got every field right on 82 percent, level withgpt-6-luna(80 percent) and ahead ofclaude-haiku-5-5(70 percent). A classification job rated medium is now answered by the line’s rule on those measurements, as easy ones already were. Jev was the cheaper one on every medium request we tested, so it answers these jobs as before. See Classification jobs on auto. - Two more hosts on Alibaba Cloud, and
qwen4-maxin full.deepseek-v4.1-flash-1017@alibaba-intlandkimi-k3.1-pro@alibaba-intlare new. Both are processed outside mainland China, and you call them by name.qwen4-maxnow takes images and tools, has its 1,000,000-token context and 131,072-token output, and bills cached input at Alibaba’s 0.075 USD per million tokens instead of the full input price. Prices and limits are on the models page. - A lower cache price for DeepSeek V4.1 Flash on Alibaba Cloud. Alibaba now prices cached input on
deepseek-v4.1-flashat a fixed 0.006 USD per million tokens in peak hours and 0.003 off-peak, a tenth of what Zabio billed. Zabio’s hourly price check reads the new price, and calls todeepseek-flash@alibaba-intlare billed at it from about a day after this release. - Edit an image from its link. The
urlof an image made withresponse_format: urlcan be sent back as animage_urlon a JSON edit, the way it came, for the 60 minutes its link lasts. Zabio does not fetch the address: it checks that the link is one Zabio signed and reads the image from your organization’s files, so your key must be able to read it. An expired link answers 400expired; any other web address is still refused. See Edit an image from its link.
1.3.45
Section titled “1.3.45”- Spoken answers from Qwen Omni. Alibaba’s
qwen3.5-omni-plus,qwen3.5-omni-plus-2026-03-15andqwen3.5-omni-flashanswer in audio on chat completions, processed outside mainland China. They answer in audio only when the request streams (an unstreamed request with the audio modality gets 400unsupported_valueonstream), inpcm16, with 56 voices. An answer that carries audio bills its audio alone: its text is free, as Alibaba bills it.qwen3.5-omni-flash-2026-03-15answers in text only, because it sends no audio. On any model, audio tokens a vendor reports for an answer that carried no audio are not billed. See Audio answers. - Rotate an API key. Rotate on the Keys page,
zabio keys rotateorPOST /admin/v1/orgs/{org}/keys/{key}/rotategives a key a new secret, shown once, and keeps everything else: its id, name, project, settings, limits, models and usage history. The old secret stops working at once. A connected app’s key gets a new one by reconnecting the app. - A failed background response returns its charge. A background response that runs outside a batch and ends
failedafter its answer was billed (a restart between the bill and storing the answer, or an answer that could not be stored) now has what the turn was billed returned to your balance. The response’s error says so, with the amount, and your ledger shows the returned charge as anadjustment. - The AI Firewall check on its own.
POST /v1/guard/checkchecks texts, images and PDFs for prompt injection without calling a model: the patterns for free, up to 60 checks a minute per key, and the model check at 0.50 USD per million tokens checked, with an optionaltaskit reads each item beside. The answer says what was found, where, and what could not be read.POST /v1/moderationsis the same check in OpenAI’s moderations shape, so an OpenAI SDK’smoderations.create()works unchanged; it judges prompt injection only. Zabio keeps none of the text. See AI Firewall check. - Check for prompt injection from an AI app. Zabio’s MCP server has a
check_injectiontool: an app connected tohttps://mcp.zabio.ai/mcpcan check a fetched page, a mail, a file or a tool’s output with the AI Firewall check before it acts on it, under the connection’s key and its daily limit. The patterns are free; the model check needs a connection allowed to ask. See the tools.
1.3.44
Section titled “1.3.44”- Existing keys follow the organization’s default action. An API key made before the organization’s default prompt-injection action existed now follows it too, as a new key does, unless an owner or admin had set the key’s own action, which it keeps. In an organization whose default is Tag, as it is until an owner or admin changes it, nothing changes for such a key; in one whose default is Block, the key now blocks. A key that follows shows
guard_action: null. See the guide.
1.3.43
Section titled “1.3.43”- A default action for the prompt-injection guard. An organization now sets the action its keys take on a pattern match, Tag or Block, in AI Firewall, Prompt Injection or with
actiononPATCH /admin/v1/orgs/{org}/guard. A key follows it unless it sets its own action; a new key follows it, and an existing key keepstagas its own action until you set it to follow (guard_action: null, or Organization in the key’s Action). A key that follows showsguard_action: null, and every key shows the action in force asguard_action_effective. See the guide. - Allow a text by typing it. Owners and admins can now add an allowed text before any call is flagged: Add text in AI Firewall, Prompt Injection, or
POST /admin/v1/orgs/{org}/guard/allowlist/text. The patterns read the text and Zabio keeps the rule and a hash of each match, never the text. An entry can carry a note. Only a web session can do it: no token, API key or MCP app. - Room for an answer on
auto. A request toautowith nomax_tokensnow goes only to models whose context window leaves at least 4,096 tokens for the answer beside the input, after the 5 percent Zabio keeps free. Before, a long prompt could go to a model whose window it nearly filled, with almost no room for the answer. When no modelautocan use leaves that room, the request gets400 context_length_exceeded, and the message says so. - DeepSeek models near their context window. DeepSeek now refuses a request whose input plus output limit passes the window. Close to the window Zabio now sends DeepSeek models the room the window leaves beside the input, as on Together AI models; with less than 4,096 tokens of room the request is too long for the model. Before, such a request was sent the model’s maximum output and DeepSeek refused it.
max_tokensnear the context window. On Anthropic models themax_tokensyou set is sent as you set it, within the model’s maximum output, and with none set the model’s maximum output is sent at every input size: Anthropic takes input plusmax_tokensover the window and stops at the window. On other models amax_tokenstoo large for the window is lowered to the room the window leaves, but no longer below 4,096 tokens (or your own value, when smaller); with less room than that the request is too long for the model. Before, it could be lowered to a few tokens.- An empty answer at the context window says so. When a model reasons until its context window ends and writes nothing,
zabio.no_answernow says the input left no room for an answer, instead of asking for a highermax_tokens. - Mark text you did not write. A text part of a user message can carry
"zabio": {"untrusted": true}on chat completions, the Responses API and/v1/messages, for a forum post, an email or a page you paste in. The prompt-injection guard then reads it as it reads a tool result: the patterns use the tool result rules, and the paid tier’s model check reads it beside your user’s own words. The model receives the text without the mark, and the price does not change. A mark anywhere else is refused with 400invalid_value. See Text you did not write. - What the guard did not read.
zabio.guard.not_readand the new headerx-zabio-guard-unreadcount the images, audio, video, files and system messages of a request, and with the paid tier the earlier messages, assistant turns and trusted tools’ results its model check does not read. The header ends with the number of strings the model check could not read, orpendingwhen the headers were sent before it finished. A long text the model check flagged while part of it could not be read is now also listed inzabio.guard.unchecked, withpartial: true. - The model check reads images and documents. With the paid tier, the AI firewall’s model check now looks at the PNG and JPEG images in tool results on
/v1/messagesand at images you mark with"zabio": {"untrusted": true}on any API, at most 8 per request, and reads the text of PDF and plain text documents on/v1/messages, hidden text included. Both are read as tool results and priced as tokens checked, as text is. An image given by URL, a GIF, a WebP and the pages of a scanned PDF are not read and are counted inzabio.guard.not_read; what could not be read is listed inzabio.guard.unchecked, with the new reasonsimage_limitandunsupported. See The paid tier. - Background responses keep their estimate set aside until they finish. A background response (
background: trueonPOST /v1/responses) that runs outside a batch now keeps its estimated cost set aside from the moment it is queued until it is billed or ends, as a synchronous call does while it runs. A turn whose estimate does not fit the balance left after the calls in flight, queued background turns included, is refused with 402insufficient_creditswhen it is queued. Cancelling a queued turn frees its estimate at once. - A background response whose call failed says
failed. A background response whose model call failed now ends withstatus: "failed"and the error of the call. Before, it endedcancelled, with a message saying it was cancelled before it ran. - Trial credit and background responses. For an organization on trial credit alone, a model of the
frontierclass named withbackground: trueis now refused with 402trial_model_restrictedwhen it is queued, as a synchronous call is. A background response that runs outside a batch is also held to the other trial terms when it runs:autodoes not pick afrontiermodel, and a turn whose estimate is above the trial balance endsfailedwithinsufficient_creditsbefore it reaches the model. Before, such a turn was queued and run on the model it named. - A background response interrupted after its answer was billed is not run twice. When a restart interrupted a background response that runs outside a batch after the call that wrote its answer was billed and before the answer was stored, the call was made and billed a second time. It is no longer made again: the response ends
failed. - A background response with a deadline of 24 hours or more needs its estimate once. When such a turn joined your organization’s batch, it was refused with 402
insufficient_creditsunless the available balance covered its estimate at the standard price and its estimate at the batch price together. Now the balance has to cover each of the two alone. max_output_tokenson a background response. The object of a background response now shows themax_output_tokensyou set, when it is queued and each time you read it. Before, it saidnull.- A time limit per request. A call to chat completions,
/v1/messagesor the Responses API now ends after 20 minutes without an answer, or, when streamed, after 10 minutes without the first piece of the answer. A stream that has started sending its answer is never cut. Compaction of a Responses conversation counts within the same limit; a compaction it cuts answersrequest_timeout, where it answered500 internal_error. Zabio starts no new attempt with under a minute left. You get the error of the last attempt that failed, orrequest_timeoutwhen none had failed, in the body or the stream when the200was already sent, and nothing is billed for the attempt that was cut. Before, a request that kept failing over could run for hours, and the keep-alive bytes kept your client’s own timeout from ending it. See Errors. - Trial credit and batches. For an organization on trial credit alone, a batch with a line that names a model of the
frontierclass now fails before it runs, withtrial_model_restrictedand the line’s number, andautoin a batch does not pick afrontiermodel, as on a synchronous call. The same holds for a background response with a deadline of 24 hours or more, which runs in your organization’s batch. Before, such a line ran on the model it named, or on afrontiermodelautopicked, and was billed to trial credit. - A background response interrupted between two models pays the first one once. When
automoved a background response to a stronger model and a restart interrupted it before that model answered, the first model’s call was made and billed a second time. The response now goes on at the stronger model, and the first call is billed once. - Free and background responses with a deadline of 24 hours or more. On the Free limits such a response on
auto, or on a model with a batch tier, was refused with 402insufficient_credits. It is now queued and served on the Free limits: in your organization’s batch when a free model has a batch tier, as its own job otherwise. - Free limits count background responses and batch requests. A background response and each request of a batch served on the Free limits now count toward the account’s requests a day and its fair-use limit, as a synchronous call does. Before, they were not counted there.
- A request refused for trial credit leaves no unfinished response. A Responses API call refused with
trial_model_restrictedused to leave its conversation and a response that stayedin_progressfor up to an hour and then readfailed. Nothing is stored for a refused call now. max_output_tokenswhen you read a response.GET /v1/responses/{id}now shows themax_output_tokensyou set on a completed response that did not run in the background too. Before, it saidnull.- The time limit covers background responses. A background response that runs outside a batch now ends
failedwithrequest_timeoutwhen its call gets no answer within 20 minutes, counted from when the call starts, not from when the response was queued.
1.3.42
Section titled “1.3.42”- Web search on your bill. The Dashboard and Usage pages now show what web search cost, on the cost card, the Spend chart, Top keys and each call in Logs, and a key’s settings can turn web search off.
1.3.41
Section titled “1.3.41”- Web search. Claude and OpenAI models can now search the web with their own search. Send the
web_searchtool on the Responses API,web_search_optionson chat completions, or Anthropic’sweb_search_20250305tool on/v1/messages, on a model whose price list shows a price per search. Each search is billed on its own line, and the results count as input tokens. Web search costs 0.0105 USD a search: the provider’s price of 10 USD per 1,000 searches plus Zabio’s 5 percent. See Web search. - Edit an image you generated in the background. A JSON edit (
POST /v1/images/edits) now takes theimg_id of a completed background generation as afile_id, and"zabio": {"index": n}in the same entry picks one of its images, so you no longer download an image and send it back to edit it. An image made withresponse_format: urlcan be named by its file id while its link works. The edit is billed as any edit; an expired generation or link answers 400expired. - A limit on an edit’s images in all. The images of one edit, including those read from files and generations, can be at most 100 MB together, the limit a multipart edit already had; above it the edit answers 413
media_too_large. - Responses usage counts the tokens written to the cache. On Claude models,
usage.input_tokensandusage.total_tokensofPOST /v1/responsesnow include the input written to the prompt cache, asprompt_tokenson chat completions always did;cached_tokensstays the tokens read from the cache. Bills do not change. A Responses turn with an image, audio or a video is no longer counted against your rate limit and balance hold as if its text were sent twice.
1.3.40
Section titled “1.3.40”- Videos over 20 MB by URL on Qwen models. An https video larger than 20 MB sent to one of Alibaba’s Qwen video models by name is no longer refused: Alibaba fetches it from your URL, up to the 2 GB Alibaba states as its limit, and Zabio reads only the first 1 MB of the file for its format and length. The call is billed on the tokens Alibaba reports, as every call is. Other models and
autokeep the 20 MB limit for a video by URL; send them a larger video as afile_id. - Audio in streamed Responses calls and batch lines is billed like audio everywhere else. A streamed
POST /v1/responsescall with aninput_audiopart now reports its audio tokens inusage.input_tokensandusage.input_tokens_details.audio_tokensand bills them at the model’s audio price, as the same call withoutstreamand chat completions already did. Batch lines with audio bill the same way. Earlier calls are not rebilled. - The credit estimate for audio. The credit estimate for a request with audio now prices the audio at the model’s audio price, and a clip whose length cannot be read is estimated from its size. Bills are unchanged.
- Long text to speech on Gemini. Gemini speech models now answer inputs up to 4,096 characters. A model that stops before the end of the input says so with
finish_reasonlength. - Stored videos are delivered. A video that was already made and billed is now delivered when Zabio hits an error while finishing it, instead of being refunded and deleted.
1.3.39
Section titled “1.3.39”- Requests close to the context window on Anthropic, DeepSeek and Together AI models. A request that names one of these models, sets no
max_tokensand has an input close to the model’s context window used to be moved to a model of the same provider with a larger window, or refused with400 context_length_exceeded, because the output limit Zabio sends by default was counted against the window. Anthropic and DeepSeek models accept such a request, so it is now served by the model you named; on Anthropic models an answer that reaches the window now ends withfinish_reasonlength. On Together AI models Zabio now sends the room the window leaves beside the input, so the request stays on the model you named with a shorter output limit; when less than 4,096 tokens of room remain it is moved or refused as before. A request that setsmax_tokensis unchanged. See Errors. - Call data export. Zabio can now send a record of each call your organization makes to your own observability tool over OpenTelemetry (OTLP): the model, tokens, cost, timing and outcome, and the request and answer when body logging is on for the key and you include bodies. Set it up in Settings, Call data export (owners and admins). It is off until you switch it on, and it never slows a call. See Call data export.
- Longer audio on Gemini models. The audio you send in
input_audioparts is now limited per model: Google’s Gemini models take up to 100 MB of decoded audio per request, and every other model 20 MB as before. A single request body carries about 25 MB of audio; more reaches a Gemini model on the Responses API, where a conversation’s stored clips count too. Zabio sends large requests’ clips to Google through Google’s file service and deletes them there as soon as the answer is in. A request above a model’s limit answers413 media_too_largeand now states the limit. - Speech as events. Text to speech now streams as events: send
stream_format: sseto/v1/audio/speechand get the audio in base64speech.audio.deltaevents, then aspeech.audio.doneevent with the usage and the call’s cost, on every speech model. - Cached audio on two Gemini models. Audio that
gemini-3-flash-previeworgemini-3.1-flash-litereads from its cache is now billed at Google’s cache price for audio: 0.10 and 0.05 USD per million tokens at list, before your plan’s fee. Until now it was billed at those models’ cache price for text, 0.05 and 0.025.GET /v1/modelsshows the price aszabio.pricing.cache_read_audio. Every other model has one cache price and does not change.
1.3.38
Section titled “1.3.38”- Transcription estimates on trial credit. While an organization runs on trial credit alone, the amount set aside for a transcription uses the longer of two lengths: the one the file’s header states, and the file’s size as speech at 16 kbit/s. A file encoded above 16 kbit/s is estimated above its bill until the call ends, and a call whose estimate does not fit the balance is refused with
402 insufficient_credits. The bill is the real length, as before, and nothing changes for an organization that has added credit. See Audio.
1.3.37
Section titled “1.3.37”- The IP lists in the organization’s data download. The organization’s data, downloaded from the web app by an owner or an admin, now holds the IP allow and deny lists themselves: the organization’s, and those of each project and each key that has its own, revoked keys included. Before, it only said whether a project or a key had a list.
1.3.36
Section titled “1.3.36”- Clearer words and phone widths in the web app. The pages of the new menu settle their wording in English and Spanish, name the pages by their new names, and work at phone widths: nothing scrolls sideways but wide tables, every control shows where the keyboard focus is, and text meets the contrast the accessibility guidelines ask for. The emails about two-step sign-in and the monthly usage summary now point to My Profile. A call refused by an IP address list now says the address it came from and where the lists are set, under AI Firewall, Network Access.
- A new tour of the web app. When you sign in, a window on the Dashboard offers a short tour in five steps: create an API key, make your first call, see it in Usage, protect it in AI Firewall and top up in Billing. Each step opens its page and points at the part it explains. Skip for now asks again the next time you sign in, and Don’t show this again does not ask again; your answer is kept with your account, on any browser. Take the tour, at the end of the menu, shows it again at any time. If you skipped or finished the earlier tour, the window does not open.
1.3.35
Section titled “1.3.35”- Background image generations and videos set their estimate aside. When a background image generation or a video is queued, its estimated cost is now set aside on your balance until it ends, as a direct call’s already was, so requests queued at the same time can no longer take the balance below zero together. A request whose estimate does not fit the balance left after the calls still in flight is refused with
402 insufficient_creditsand nothing is queued; the message says the estimate, the balance and the least amount to add. The amount set aside is given back when the generation or the video fails or is cancelled, and replaced by the real charge when it is made. A video’s estimate no longer adds a quarter for safety: it is the length times the model’s highest price per second, fee included. See Images and Videos. - A new menu in the web app. The sidebar groups the pages under Overview, Build, Monitor, Security & Policies and Organization, and long pages are split into tabs, each with its own address. Your own settings (profile, password, two-step sign-in, sessions, access tokens and connected apps) moved from Settings to My Profile, in the menu under your initials. The AI firewall has its own page, Projects is a tab of API keys, Referrals a tab of Billing, and your account’s model access is under Models. The project switcher is now a filter: it shows all projects until you choose one, and the address keeps your choice. Old addresses and bookmarks still open the right page. What’s new, in the header, lists the latest changes and anything your account needs to act on.
- Search in the web app. Press Ctrl K (⌘ K on a Mac), or click the search box in the header, to find any page, tab or setting, and your organization’s API keys, models and projects, by name. Use the arrow keys and Enter to open a result, and Esc to close; the pages you opened last are listed first.
- IP allow and deny lists. An organization, a project and a key can each have a list of allowed addresses and a list of denied ones, IPv4 and IPv6, as single addresses or CIDR blocks. A deny list always wins, and a project or a key can only narrow what the level above allows. A call with a key from an address the lists refuse gets
403 ip_not_allowed: nothing reaches a model and nothing is billed. The lists are free on every plan, and with no list nothing changes. Owners and admins set them in the web app under AI Firewall, Network Access, which also shows your current address and asks before a change that would refuse it. See IP allow and deny lists. - A clearer Dashboard. The Dashboard opens with four figures: Spend, Saved by routing, Calls and Credits, which now says how many days your balance lasts at this month’s pace. Below them are the daily spend by model, the cost breakdown, your top models, the kind of work and your tokens; how each figure is computed is behind its info icon. A line above the figures shows one message at a time, the most important first: an action your account needs, trouble at a provider whose models you use, then what is new in the latest release. You can hide each message. Spend by key and by member moved to the Overview tab of Usage.
- The limits of every key in one list. Under API keys, the Limits tab lists each active key’s spend limit with how much of it is used this period, its requests and tokens per minute and when it expires; Edit opens the key. The Keys tab sums them up in one line at the top: active keys, keys with a spend limit, and any key near or at its limit or about to expire. Models, API keys, Conversations, Batches and the Playground take the new look. A batch’s page opened from a link no longer shows an error.
- Usage, Billing and Members in the new style. The Overview tab of Usage opens with four figures for the range and filters you chose: Spend with the cost per 1M tokens, Saved by routing, Calls with the share that succeeded and the latency, and Cache hits with what caching saved. The daily spend sits beside the cost breakdown. On Billing, your balance, what you added in total and your last top-up are one row of figures; while your launch match is open, Balance & Top up shows one line with where it stands, and the match itself is on Credits & Referrals. Members says how many members and pending invitations the organization has and your role, and shows each member’s spend this month against their monthly quota.
1.3.34
Section titled “1.3.34”- Image, speech, transcription and embeddings calls set their estimate aside. These calls now work like chat: before a call reaches the model, its estimated cost is set aside on your balance until the call ends, so calls sent at the same time can no longer take the balance below zero together. A call whose estimate does not fit the balance left after the calls still in flight is refused with
402 insufficient_credits; the message says the estimate, the balance and the least amount to add. Background image generations and videos are not changed yet. See Billing. - The AI firewall in Top keys. On the Usage page, Top keys now counts each key’s AI firewall charges in its spend and its share, as a key’s spend limit already did, so the table adds up to You paid. Top models stays the calls’ only, since the AI firewall is no model. Nothing is charged twice and no price changed.
- The AI firewall on the Dashboard. You paid, Spend and the daily spend chart now include the AI firewall’s charges, as the Usage page and your bill already did. The chart stacks them on top of the calls’ line, and You paid shows the same figure on the Dashboard, on the Usage page and on the bill for the same period. Nothing is charged twice and no price changed.
- The AI firewall in your usage. On the Usage page the Spend chart shows the AI firewall’s charges as a part of their own, so its total matches You paid. The monthly usage report names the AI firewall’s tokens checked and what it charged, and its bill includes them. The AI firewall’s charges count toward the 250 USD that unlocks the match. Nothing is charged twice and no price changed. See Credits, match and referrals.
- A request too long for the model now gets a clear 400. A request that does not fit the context window of the model you named, or of any model
autocan use, used to get503 no_provider_availablewithRetry-After, so clients retried a request that could never succeed. It now gets400 context_length_exceeded, with the request’s size, the output counted and the window in the message. A request whose input fits the model you named and that sets nomax_tokensis now sent to the model instead of refused near the window, and one that does not fit is no longer moved to another model; on Anthropic, DeepSeek and Together models the output Zabio sends by default still counts, and a model of the same provider with a larger window still takes the request when one can. See Errors. - Easy classification jobs on
autogo to the more accurate model. A request whoseresponse_formatis a JSON schema of fixed choices, booleans and bounded numbers was answered by Jev only when Jev was also the cheaper model, so most short requests went to the cheapest text model. In our tests Jev got every field right on 78 percent of such requests, against 51 percent for that model, so on an easy classification job Jev now answers at any input size. A short request can cost slightly more than before: at most Jev’s own price for the call, which stayed under 0.00004 USD on our test requests under 200 input tokens. The same rule applies to anautoline inside a batch, where Jev answers at its standard price at once, andPOST /v1/public/analyzeprices such a request the same way: itsjevswitch applies whenever Jev would answer, while itsjevtip still appears only when Jev is the cheaper one. Other jobs keep the price comparison, and a request that names a model is unchanged. See Classification jobs on auto. - Cached audio on the Gemini models is billed once. When a Gemini model reads part of an
input_audioclip from its cache, those tokens are billed at the cache price only:usage.prompt_tokens_details.cached_tokenscounts them andaudio_tokensis the audio that was not cached. No call on Zabio was billed the old way. - More Qwen models take video. Eleven Qwen 3.6 and 3.5 models on Alibaba Cloud (International) now take
video_urlparts when you call them by name. See Video.
1.3.33
Section titled “1.3.33”zabio.cache.appliedcounts a cache write. On a provider that caches on its own, a call that only wrote the cache, such as the first call of a long prompt on OpenAI GPT-5.6 and later or on Moonshot, now readsvendor_automaticinstead ofnone.read_tokensstill says whether the call hit the cache, andwrite_tokenswhat it wrote. Display only: the bill did not change. See the per-provider table.
1.3.32
Section titled “1.3.32”- Image requests on trial credit. An image generation or edit whose estimated cost is above what is left of your trial is now refused with
402 insufficient_creditsbefore it reaches the model, as a chat request already was; the message says the estimate and what is left. A background generation is checked when it is queued and again when it runs. Accounts that have added credits are not affected. See Images.
1.3.31
Section titled “1.3.31”- The prompt-injection guard reads more. It now also checks the override, extraction, persona and bypass phrases in Spanish, Portuguese, French, German, Italian, Russian and Chinese (detection is measured in English); key words broken by spaces (
ign ore prev ious); text in hex with separators, percent-encoding, HTML character references,\uescapes, decimal or binary character codes, ROT13 or written backwards, and one encoding inside another; tool results that close their own wrapper and go on with orders, fake user or assistant turns, fake agent steps and fake tool calls; instructions hidden in HTML comments or in invisible text; and HTML images whose link carries data out.detections[].encodingtakes the new encodings’ names. “Your new role is team lead” in a tool result is no longer reported. See Prompt-injection guard. - Each detection in
zabio.guardnow names itsdetector:patternfor the free patterns. See Prompt-injection guard. - Report what the prompt-injection guard flags. On the Usage page’s Logs tab a Guard filter shows the calls the guard flagged or could not fully read, and a flagged call’s detail has Not an injection (that exact text is no longer flagged in your organization) and Confirm attack, with the flagged text shared only if you choose. Settings gains a section for the guard: each key’s action, the texts your organization allowed and a weekly summary. A key can trust tools by name (
guard_trusted_tools): what the patterns find in their results is reported withtrusted: trueand never redacted or blocked. The MCPfeedbacktool takes aninjectionfield; such a report waits for an owner or admin in Settings. See Prompt-injection guard.
1.3.30
Section titled “1.3.30”- Webhooks when a batch ends. Add an
httpsaddress in Settings, Webhooks, and Zabio sends it a signedPOSTwhen one of your batches completes, fails, expires or is cancelled (batch.completed,batch.failed,batch.expired,batch.cancelled), with the batch id, its status, the line counts and links to its files, never a prompt or an answer. The request follows Standard Webhooks (webhook-id,webhook-timestamp,webhook-signature), so its libraries verify it; the signing secret is shown once and can be rotated with a 24-hour overlap. A delivery that fails is tried 8 times over about 31 and a half hours, and Deliveries shows each attempt. See Webhooks. - Claude Code through Zabio. Claude Code sessions no longer stop with a 400 on their second request (
messages.1.role) or when an advisor model is set. Messages with thesystemrole between the turns are accepted, as Anthropic accepts them. Server tools, Claude Code’s advisor among them, are removed from the request and listed inzabio.ignored_parametersinstead of refusing the call; the advisor is not available through Zabio. See Anthropic SDK and Claude Code. - Tools on Gemini models. Tools whose
parameterscarry JSON Schema keywords that Google’s Gemini models do not take ($schema,additionalProperties,$refand$defs,exclusiveMinimumand others, as Claude Code and the OpenAI and Anthropic SDKs send them) failed on every Gemini model, named or picked byauto. Zabio now converts each schema for Gemini, lists the keywords that carried a rule and were left out inzabio.ignored_parameters, and keepsautooff the Gemini models for a schema that refers to itself; a named Gemini model answers such a request with 400unsupported_parameternaming the tool. See Tools on Gemini models. - Calls that write OpenAI’s prompt cache are now billed at OpenAI’s cache write price, as the price list shows: 1.25 times the input price on
gpt-6.1-sol,gpt-6.1-terra,gpt-6-sol,gpt-6-luna,gpt-6-astra,gpt-5.6-sol,gpt-5.6-terraandgpt-5.6-luna, at the batch and flex rates on those tiers. Before, the written tokens were billed at the input price, below what OpenAI charges, andzabio.cache.write_tokensread 0; it now shows them, andprompt_tokensis unchanged. A call on those models that writes the cache costs slightly more from this release on; calls that only read it, and every other model, are unchanged. - A background response (
background: trueonPOST /v1/responses) that setszabio.cache.ttlorcache.breakpointstononeon a vendor that caches on its own now lists the field inzabio.ignored_parameters, as the same request sent withoutbackgrounddoes. The answer and the bill were already right; only the report was missing.
1.3.29
Section titled “1.3.29”- A free prompt-injection guard on every key. Chat completions, the Responses API and
/v1/messagesnow check the user’s messages, tool results and the assistant turns you send for text that tries to override the model’s instructions (“ignore all previous instructions”, a request for the system prompt, fake chat template markers, orders hidden in a fetched page), after undoing the usual disguises: invisible characters, lookalike letters, spaced-out or misspelled words, Base64 and hex. Each key has an action:tag(the default for every key: the call goes through and the answer’szabio.guardlists where each detection was, never the text),redact(the span is replaced with[PROMPT_INJECTION]before the model sees it),block(403prompt_injection_blocked, nothing billed) oroff. Set it withguard_actionon the key; a request can ask for a stronger action withzabio.guard.actionorx-zabio-guard, never a weaker one. A phrase your organization knows is harmless can be added to its allowlist. It is pattern based and not a guarantee. See Prompt-injection guard. - Anthropic’s Messages API and Claude Code. The Anthropic SDKs, Claude Code and any tool that takes an Anthropic base URL work with your Zabio key: set the base URL to the API host without
/v1and send your key asx-api-keyor a bearer token.POST /v1/messagestakes Anthropic’s request and answers with Anthropic’s message or stream;POST /v1/messages/count_tokenscounts tokens;GET /v1/modelswith ananthropic-versionheader lists the models in Anthropic’s shape; errors on these paths use Anthropic’s envelope. A Claude model named inmodelgets your body as you sent it (system blocks,cache_control, thinking with its signatures, documents), andautoand every other model get the request translated. Calls are billed as the same calls on chat completions. Server tools,container,mcp_servers, fast mode and data residency are refused. See Anthropic SDK and Claude Code. - Two-step sign-in. Turn it on in Settings: after your password, email link, Google or GitHub, Zabio also asks for a code from an authenticator app, with ten single-use recovery codes for a lost phone. While it is on, creating an API key or a personal token, approving the CLI, connecting an app, moving credit and deleting your account ask for a code if you have not entered one in the last 10 minutes;
zabio keys createasks for it in the terminal or takes--code. It is off unless you turn it on. See Settings. - Passkeys for two-step sign-in. In Settings, add a passkey (your fingerprint, face or screen lock, a password manager or a security key) as your second step, beside or instead of the authenticator app. Signing in and the actions that ask for a second step then offer Use a passkey. A passkey cannot be phished: it works only on app.zabio.ai. The first second step you add turns two-step on and gives you the ten recovery codes;
zabio keys createkeeps asking for a code. See Settings.
1.3.28
Section titled “1.3.28”- The web app stays reachable while a new release starts: a page or a form sent at that moment waits a second and is answered, instead of failing.
- An opaque id for your end users at the vendors. On Zabio’s vendor keys, every chat completion, Responses and image call now carries an opaque identifier in the field the vendor documents for one (OpenAI’s
safety_identifier, Anthropic’smetadata.user_id, Google’slabels.safety_identifier, DeepSeek’suser_id, DeepInfra’suser, Moonshot’ssafety_identifier), derived from your organization and from your own end user’s id when you sendsafety_identifieroruser; never your organization’s id or your value. A vendor can then act on one end user rather than on the account all customers share. Chat completions and the Responses API now readsafety_identifier, and the Responses API readsuserinstead of listing it inzabio.ignored_parameters. On your own vendor key, the value you sent goes to the vendor as it is. See What the vendor receives. - A batch line that sets
zabio.cache.ttlorcache.breakpointstononeon a provider that caches on its own (OpenAI, Google and the others) lists the field in its output line’szabio.ignored_parameters, as the same request sent synchronously does. See Batches. - Grok 4.7 and Grok 4.6 in batches. xAI now prices both models for its Batch API at 20 percent off every token type, so a batch line can name
grok-4.7orgrok-4.6and is billed at the batch price (1.76 USD per million input tokens, 0.44 cached and 5.28 output on Zabio’s US endpoint), andautoinside a batch can pick them. Before, such a line failed the batch withmodel_not_batchable. See Batches.
1.3.27
Section titled “1.3.27”- API keys show when they were last used. The Last used column of the API keys page shows the time of the key’s latest request, to the minute. Before, every key read Never, however many calls it made.
- Usage: the cost breakdown for any range. The Stats tab of Usage shows how the spend adds up (provider price, Zabio fee, automatic model choice, sharing discount, classifier and what you paid) for the range and filters in the filter bar, a past month included, so a link with
range=custom&from=...&to=...opens it. - A retired model answers 410. A request that names a model past its retirement date gets 410
model_retiredinstead of 404model_not_found, with the same message naming the date, on every endpoint that takes a model and in the lines of a batch (a line whose model retires after the batch was created ends in the error file withmodel_retiredand status code 410). Nothing reaches the vendor and nothing is billed. See Errors. - A retired model names its successor. When the vendor names a model that replaces one,
GET /v1/modelsshows it aszabio.successorand the 410model_retiredmessage names it, so you know which model to call instead, before the date or after it. See Models. - Logs: filter by provider, model and key, and see each call’s key. The Logs tab narrows the calls by provider, by model (the model you asked for or the one that answered) and by key, and keeps the filters in the page address so a filtered view can be shared. Every row shows the name of its key and its project.
GET /admin/v1/orgs/{org}/callsreturnskey_nameandproject_nameon each call, and itsmodelfilter matchesrequested_modelorserved_model. - Responses lines in batches.
POST /v1/batchestakesendpoint: "/v1/responses", as OpenAI’s Batch API does: every line of the file is aPOST /v1/responsesrequest, routed, priced at the batch rates and billed exactly as a chat completion line with the same tokens, and each output line carries a Response object. A batch line has no stored conversation, soprevious_response_id,conversation,store: trueandbackground: truefail the batch withunsupported_parameter, and the Response object is not stored and does not repeat the request. A batch is all chat completion lines or all Responses lines.gpt-6-astranow takes tools in a batch and in a background response, on either endpoint: Zabio sends those lines to OpenAI’s batch for the Responses API. See Batches. - Batch chat lines list their ignored parameters. A chat completion line of a batch that sends
seed,logit_bias,presence_penaltyorfrequency_penaltylists them in its output line’szabio.ignored_parameters, as the same request sent synchronously does. Before, only Responses lines listed them. See Batches. - Batches in the web app. A Batches page lists your batches with their status, lines, cost and the vendors’ discount (what the batch prices took off the standard prices), filtered by status and by date. A batch’s page shows its lines one by one with their errors, the cost charged, the saving against your baselines, Cancel batch while it runs, and the output and errors files for owners and admins. The admin API gains
GET /admin/v1/orgs/{org}/batches,GET .../batches/{id},POST .../batches/{id}/cancelandGET .../batches/{id}/files/{output|errors}. See Batches.
1.3.26
Section titled “1.3.26”- Audio answers from chat models.
POST /v1/chat/completionsanswers in audio when the request sendsmodalities: ["text", "audio"]andaudio: {"voice", "format"}, in OpenAI’s own shape: the answer’smessage.audiocarries the audio as base64, its transcript, anidandexpires_at, and a stream carriesdelta.audiochunks. The models are OpenAI’sgpt-audio-1.5,gpt-audioandgpt-audio-mini, called by name, inwav,mp3,flac,opus,pcm16oraac(a stream inpcm16) and thirteen voices;zabio.capabilities.audio_outputmarks them inGET /v1/models. The audio is billed at the model’s audio output price (64.00 USD per million audio tokens ongpt-audio-1.5), the text at its output price. Zabio never stores the audio. A later turn can send the assistant’saudio: {"id"}back to the same model.autoand the Responses API answer in text; see Chat completions.
1.3.25
Section titled “1.3.25”- Every ElevenLabs and Deepgram voice and transcription model. Seven speech models join
POST /v1/audio/speech: from ElevenLabseleven-v3(80.00 USD per million characters, 5,000 characters a request),eleven-v3-conversational(40.00),eleven-multilingual-v2(80.00, 29 languages),eleven-flash-v2.5(40.00, 32 languages) andeleven-flash-v2(40.00, English only), all with the same 19 voices aseleven-v4; from Deepgramaura-1(15.00, English only, 12 voices) andflux-tts(45.00, 266 voices in English and 41 more languages,speedfrom 0.5 to 1.5). Two transcription models joinPOST /v1/audio/transcriptions:scribe-v2-medical(ElevenLabs, for clinical audio, 0.22 USD per hour asscribe-v2) andwhisper-large(Deepgram, 0.0048 USD per minute).autoon speech never picks a model that speaks English only, since a speech request does not say its language; name one to use it. The models ElevenLabs and Deepgram have deprecated, serve only in real time or do not price are not added; see Audio.
1.3.24
Section titled “1.3.24”- Gemini Omni Flash videos.
gemini-omni-1.1-flash(Google) joinsPOST /v1/videos: 3 to 10 seconds from a prompt, an image, or a first and a last frame, at 360p, 720p, 1080p or 4k, always with sound, billed on the tokens Google reports (17.50 USD per million video tokens, about 0.10 USD a second at 720p).secondssets the length as on the other models. It does not make videos of certain recognizable people: such a request fails withmoderation_blockedand says so. See Videos.
1.3.23
Section titled “1.3.23”- Video generation.
POST /v1/videosmakes a video in the shape OpenAI’s SDKs knew for Sora (client.videos.create, as JSON or the multipart form the SDKs send): a prompt, a length inseconds, asizeorresolution, and optionally an image to start from (input_reference). The answer comes at once with avideo_id;GET /v1/videos/{id}says when the video is ready and then carries a link that works without your key for 60 minutes,GET /v1/videos/{id}/contentdownloads the MP4,DELETEcancels a queued video or deletes an ended one, andGET /v1/videoslists yours. The first models: xAI’sgrok-imagine-video-1.5(0.08 USD a second, 1 to 15 seconds, up to 1080p, a first and a last frame, sound that can be turned off) andgrok-imagine-video-1.5-lite(0.02 USD a second), both 0.01 USD per image sent,, made on xAI’s global endpoint, and Alibaba’swan2.6-t2vandwan2.6-i2v(from a prompt or from an image, 2 to 15 seconds, 0.10 USD a second at 720p and 0.15 at 1080p, with sound), made in the United States.model: autopicks the cheapest model that makes the length and resolution you ask for. A video is billed per second of the video made, at the price of the resolution made, plus the plan fee; credit is checked against the video’s estimate when it is queued and again when it starts. The prompt and the images go to the vendor that makes the video; the video is stored encrypted under your organization’s retention (or sooner withzabio.expires_after) until you delete it. See Videos.
1.3.22
Section titled “1.3.22”- Video in chat.
usermessages onPOST /v1/chat/completionstakevideo_urlparts andPOST /v1/responsestakesinput_videoparts: a video as a data URL, an https URL, a public YouTube URL, or thefile_idof a file you uploaded with purposeuser_data; MP4, MOV or WebM, up to 10 videos and 100 MB per request. A request with video is routed only to models that take it (zabio.capabilities.video_inputinGET /v1/models): Google’sgemini-3.8-flash,gemini-3.6-flash,gemini-3.5-flash-lite,gemini-3-flash-previewandgemini-3.1-flash-lite, and Alibaba’sqwen3.8-omni-flash,qwen3.8-flashandqwen3.7-plusby name. YouTube URLs and WebM go to the Gemini models only.autopicks among the Gemini models; a named model that takes no video answers 400 before anything is sent. A video is billed as input tokens at the model’s input price, its sound at the model’s audio price where the vendor counts it apart. Zabio never keeps a video: a stored Responses turn keeps its format, size and length only, so a later turn does not see it again, and a video cannot go in a batch or a background Response. See Chat completions.
1.3.21
Section titled “1.3.21”- Images as URLs.
"response_format": "url"onPOST /v1/images/generations(direct or in the background) andPOST /v1/images/editsreturns each image as a link indata[].urlinstead of base64, the way OpenAI’s DALL-E models answered. The link works for 60 minutes without your API key, so it can go straight into an<img>tag; anyone holding it can open the image until then, so share it as you would the image. The images are stored for those 60 minutes, encrypted with your organization’s key, and deleted after.b64_jsonstays the default. See Images. - xAI’s Grok Imagine models.
grok-imagine-image(0.02 USD per image, 0.002 per input image on an edit) andgrok-imagine-image-2.0(0.04 USD per image at qualitylow, 0.06 atmedium, 0.01 per input image on an edit) generate and edit images: one input image on 1.0 and up to five on 2.0, no mask, sizes 1024x1024, 1248x832 and 832x1248 (the pixels xAI makes; 1536x1024 and 1024x1536 are not xAI sizes). xAI serves images only on its global endpoint, so these two models show their processing location as not guaranteed; xAI’s chat models stay in the United States.autonow picksgrok-imagine-imageat 1248x832 and 832x1248 and for a one-image edit without a mask. xAI charges for an image its moderation refuses, so a refused request on these models is billed what xAI charged plus the plan fee (400moderation_blocked, the message says how much).GET /v1/modelsgives the input-image price aszabio.pricing.per_input_image. See Images.
1.3.20
Section titled “1.3.20”- Image edits, a FLUX model and background generation.
POST /v1/images/editstakes OpenAI’s multipart form: one or moreimage[]files (png, jpeg or webp, 50 MB each at most) and an optionalmask. The OpenAI image models take up to 16 images and a mask,gemini-nano-banana-2.1andgemini-3-pro-imageup to 14 images,gemini-3.1-flash-lite-imageone;autopicks the cheapest model that takes what you send. The input images are never stored.flux-2-dev@deepinfra, FLUX.2 [dev] by Black Forest Labs served by DeepInfra, generates images billed per image (0.017858 USD at 1024x1024)."zabio": {"background": true}on a generation answers 202 with animg_id; fetch the images withGET /v1/images/generations/{id}and delete them withDELETE. A background generation stores the prompt until it ends and the images under your organization’s retention, encrypted. See Images. - Image follow-ups.
GET /v1/images/generationslists your background generations, newest first, withlimit,afterandstatus."zabio": {"expires_after": {"anchor": "created_at", "seconds": N}}on a background generation deletes its images sooner than your organization’s retention. Credit is checked again when a background generation runs: one whose balance reached zero while it waited endsfailedwithinsufficient_creditsand bills nothing.POST /v1/images/editsalso takes OpenAI’s JSON shape, the images as base64 data URLs or file ids; web addresses are not fetched. The CLI gainszabio image edit,zabio image --background,zabio image statusandzabio image get. See Images.
1.3.19
Section titled “1.3.19”- Image generation.
POST /v1/images/generationstakes a prompt in OpenAI’s shape and returns the images as base64: OpenAI’sgpt-image-2.5-flare,gpt-image-2.5-sunburstandgpt-image-2(any size within OpenAI’s limits, qualitylowtomax, png, jpeg or webp, transparent backgrounds, partial images withstream),gpt-image-1-miniby name until its shutdown on 2026-12-01, and Google’sgemini-nano-banana-2.1,gemini-3.1-flash-lite-imageandgemini-3-pro-image(jpeg, up to 4K, 14 aspect ratios).model: autopicks the cheapest model that produces the asked size, quality and format. Every call is billed on the tokens the vendor reports; the images are never stored. A long generation is kept alive on the connection (the 200 is committed after 90 seconds and a space written every 15 until the body arrives). The CLI gainszabio image PROMPT -o FILE. Edits and background generation are not available yet. See Images.
1.3.18
Section titled “1.3.18”- Audio in chat.
usermessages onPOST /v1/chat/completionsandPOST /v1/responsestakeinput_audioparts in OpenAI’s shape: the clip as base64,wavormp3, up to 20 MB per request. A request with audio is routed only to models that take it (zabio.capabilities.audio_inputinGET /v1/models): Google’sgemini-3.8-flash,gemini-3.6-flash,gemini-3.5-flash-lite,gemini-3-flash-previewandgemini-3.1-flash-lite, and OpenAI’sgpt-audio-1.5,gpt-audioandgpt-audio-miniby name (the last two until their shutdown on 2027-01-20).autopicks among the Gemini models; a named model that takes no audio answers 400 before anything is sent. The clip’s audio tokens are billed at the model’s audio price and reported inusage.prompt_tokens_details.audio_tokens. On chat completions the clip is never stored; a stored Responses turn keeps it under the conversation’s retention. See Chat completions.
1.3.17
Section titled “1.3.17”- Text to speech.
POST /v1/audio/speechtakes text in OpenAI’s shape and returns the audio, streamed as the model produces it, asmp3,opus,aac,flac,wavorpcm.model: autopicks the cheapest speech model that produces the format you ask for and has the voice you name; the models are Hexgrad’s Kokoro (served by Together AI), Deepgram’s Aura-2, ElevenLabs’ v4 and v4 Turbo, Google’s Gemini 3.8 Flash TTS and Flash-Lite TTS, and OpenAI’sgpt-4o-mini-tts,tts-1andtts-1-hdby name until their shutdown on 2027-01-06. Nothing is transcoded: each model returns the formats its vendor produces, listed with its voices inGET /v1/models. Billed per character of input text, or in text and audio tokens where the vendor bills tokens; the call id, the model, the vendor, the cost and the units travel asx-zabio-*response headers, since the body is audio. The audio is never stored. The CLI gainszabio speak -o FILE TEXT. See Audio.
1.3.16
Section titled “1.3.16”- Audio transcription.
POST /v1/audio/transcriptionstakes an audio file in OpenAI’s shape and returns its text, asjson,text,verbose_json,srtorvtt, streamed or whole.model: autopicks the cheapest transcription model able to do what the request asks; the models are OpenAI’sgpt-transcribe(and its retiringwhisper-1andgpt-4o-transcribefamily until 2027-02-26), Google’sgemini-3.5-transcribe, ElevenLabs’ Scribe v2, Deepgram’s Nova-3, Whisper Large v3 on Together AI and Mistral’s Voxtral Mini and Small on DeepInfra, billed per minute of audio (or in audio tokens where the vendor bills tokens) at the provider’s list price plus the plan fee. ElevenLabs and Deepgram are new vendors; see the privacy page. The audio is never stored. Usage, the CSV export and the model list show minutes of audio and each model’s unit. See Audio.
1.3.15
Section titled “1.3.15”- A model a vendor stops serving is retired on its own. When a vendor’s model list has not shown a model for a day and a test call to it is refused, Zabio sets its
retires_atseven days ahead:autostops choosing it at once, requests that name it keep working until the date and carry the newx-zabio-retires-atheader, and after the date they get a 404model_not_foundthat says when the model was retired. If the vendor lists the model again before the date, the date is removed. Models retired earlier by hand follow the same rule from their date. See Models and the API reference. - More from
askon the MCP server, two new tools and three prompts.asktakesinstructions(a system message),schema(a JSON answer in that shape),images(up to 4 https URLs),deadline(from 15 minutes the call may use the vendor’s flex tier, in apps that show progress) andthread(a stored conversation, started withnewand continued with itsconv_id). Its closing line names the model, the vendor and the cost.estimateprices a task without running it, asPOST /v1/public/analyzedoes, andbudgetshows what remains of the connection’s daily limit and the organization’s balance. The promptsask,estimateandexplainappear as slash commands in the apps that show them. See Connect an AI app
1.3.14
Section titled “1.3.14”- Parasail is a host. Sixteen open-weight models Zabio already serves have a copy on Parasail with an id ending in
@parasail(DeepSeek V4 and V4.1, Qwen 3, 3.5, 3.6 and 3.8, Llama 3.3 70B, GLM 5.3 and MiniMax M3), each at the precision Parasail states (fp8, or the maker’s full precision forqwen3.5-9b@parasail) and billed at Parasail’s list price plus 5 percent, with cache hits at Parasail’s cached rate where it has one. The copies of modelsautoalready uses (qwen3.5-9b,llama-3.3-70b-instruct-turbo,deepseek-flash,deepseek-v4-pro) joinautowith their originals, so a call goes to Parasail when it is the cheapest host or when another host is down. The vendor is on by default and can be turned off like any other; you can bring your own Parasail key. See Models and the privacy page. - DeepInfra is a host. Sixteen open-weight models Zabio already serves have a copy on DeepInfra with an id ending in
@deepinfra(DeepSeek V4 and V4.1, Qwen 3, 3.5 and 3.6, Llama 3.3 70B, gpt-oss-120b and MiniMax M3), each at the precision DeepInfra states (fp8, or the maker’s full precision forqwen3.5-9b@deepinfraandgpt-oss-120b@deepinfra) and billed at DeepInfra’s list price plus 5 percent, with cache hits at DeepInfra’s cached rate where it has one. The copies of modelsautoalready uses (llama-3.3-70b-instruct-turbo,qwen3.5-9b,deepseek-flash,gpt-oss-120b,deepseek-v4-pro) joinautowith their originals, so a call goes to DeepInfra when it is the cheapest host; the rest are called by name. The vendor is on by default and can be turned off on the Models page, and you can bring your own DeepInfra token. See Models and Privacy. - Moonshot AI is a vendor. Kimi K3.1 Pro (
kimi-k3.1-pro), its high-speed variant (kimi-k3.1-pro-highspeed) and a second host of Kimi K3 (kimi-k3@moonshot) are served through Moonshot AI’s international API at Moonshot’s list price plus 5 percent, with cache hits billed at Moonshot’s cached rate. The two K3.1 Pro models are inauto/best. The vendor is on by default and can be turned off like any other; you can bring your own Moonshot key. See Models and the privacy page. - Model labels name the maker and the processing region. The eleven models whose label named the host, for example “DeepSeek (North America, via Together AI)” and “Qwen3.7 Max (US, via Alibaba Cloud)”, now show the maker’s model name and where the call is processed: “DeepSeek V4.1 Flash, processed in North America”, “Qwen3.7 Max, processed in the US”. The label is
zabio.labelinGET /v1/modelsand the line under the id in the model tables. Model ids, prices,zabio.vendorand thex-zabio-vendorheader do not change; the privacy policy and the data processing addendum quote the new labels. - Models show their maker.
owned_byinGET /v1/models, the newmakerfield ofGET /v1/public/pricesand the Maker column of the model tables name the company that made each model, for examplemoonshot(Moonshot AI) forkimi-k3andzai(Z.ai) for the GLM models. Model ids and prices do not change. - Off-peak prices on calls that cross the boundary. A call on a model with an off-peak price takes it only when both its arrival and its completion fall inside the off-peak hours; a call that crosses the boundary in either direction is billed at the list price. Where a vendor states which instant it charges by, Zabio follows it, and
GET /v1/public/pricessays so inoff_peak.charged_by. See Billing.
1.3.13
Section titled “1.3.13”- Current prices as data.
GET /v1/public/priceslists the provider list price of every model, withas_of, when the prices last changed, and where each price was read. It needs no API key and answers304when the list has not changed since your copy. See Billing.
1.3.12
Section titled “1.3.12”- Workload report. Each month your organization shares calls, an independent model judges a sample of the answers blind (it sees the de-identified request and the answer, never which model produced it) and, for one in ten, asks a cheaper and a stronger model for their own answer to the same request. On the 2nd the owners receive a report by email, also under Usage, Workload report: the share of correct answers by type of work, what the cheaper replays said and the month’s sharing discount. A report needs at least 50 judged answers in the month. Nothing on your account changes from it.
- Which vendors see a shared call. The privacy page now names them: a shared call is sent only to vendors whose published terms say they do not train on API inputs and outputs. DeepSeek receives none.
POST /v1/feedbackis rate limited by the key’s own request limit, like every other call.
1.3.11
Section titled “1.3.11”- Tell Zabio when an answer was wrong.
POST /v1/feedbacktakes{call_id, verdict, reason}under your API key, and the same object travels aszabio.feedbackinside your next chat completions or Responses request. The Logs tab has thumbs up and down on every row. A bad verdict makes Zabio choose the model again on the next turn of that call’s session, as the MCP server’sfeedbacktool already did. - Lost calls are named. A call the server did not finish recording (it stopped between accepting the call and writing its row) now appears in Logs and the CSV as Lost, not billed, instead of disappearing.
1.3.10
Section titled “1.3.10”- Parallel tool calls on every model. An assistant message carrying several
tool_calls, followed by onetoolmessage per call (what an agent loop with parallel tool calls sends on its second turn), now reaches every provider as one assistant turn. Before, the OpenAI-compatible providers (DeepSeek, Together AI among them) rejected the second turn with “an assistant message with tool_calls must be followed by tool messages”. Stored conversations on the Responses API read back the same way. - Images on the Responses API. An
input_imagewith a URL is fetched and inlined before anything is stored, as on chat completions, so every provider gets the same bytes under the same size limit, and a data URI is decoded rather than passed to the provider as a URL; later turns of the conversation never fetch the image again. - Running out of credit. When your balance reaches zero, requests now stop by default: a request is refused with
402 insufficient_creditsuntil credit is added, and so is a request whose estimated cost does not fit the balance left after the calls in flight; the message names the estimate, the balance and the least amount to add. A balance below zero refuses every request until a top-up brings it above zero. Continuing on the free tier at zero is now a setting an owner turns on under Organization settings; organizations that were on the previous default have been moved and their owners emailed, and an organization whose owner had chosen to continue keeps the choice. - Provider errors in streams. A provider failure in the middle of a stream now ends it with the same error envelope a failed call gets (
type, acodesuch asupstream_error, Zabio’s message), never the provider’s own text or Zabio’s internal error class. A provider’s refusal of the request itself (a 400) keeps its reason, with URLs, identifiers and addresses removed, and names the provider and the model inzabio. - Forced tool choice on Alibaba Cloud’s models. A request with
tool_choice: requiredor a named function on a Qwen or GLM model with a reasoning level runs with thinking off,zabio.reasoning.appliedsaysoffand the level is listed inzabio.ignored_parameterswith the reasontool_choice; Alibaba Cloud does not take a forced tool choice in thinking mode, and the call used to fail with a 400. - A disconnect is billed only for work the provider did. Leaving before the provider accepted the request (during Zabio’s own steps, or while a provider’s refusal was being retried) bills nothing; leaving while an answer was being written still bills the work done, as before.
- Automatic model choice after a provider failure. When the provider chosen for an
autorequest fails, the next choice is the next candidate of the same selection; only when none is left does the earlier rule choose, andzabio.routing.fallbacksays so.
- A reservation per call. Each paid call now sets aside its estimated cost (input, expected output and the fee, on the dearest model
automay pick) against your available balance when it is admitted, and settles to what it actually cost when it ends. A call that does not fit the balance left after the calls in flight is treated as a call at zero balance: served on the Free limits when your organization continues at zero, refused with402 insufficient_creditswhen it is set to stop, the message naming the estimate and the balance in USD. Before, every concurrent call was admitted while the balance read above zero and the overshoot could exceed it. The response headerx-zabio-balance-microskeeps reading the balance net of the calls in flight. - The Free plan follows the person. The Free allowance and its daily limits now count the organizations and the calls of the person who owns them (plus-tag and Gmail-dot aliases included), and an organization closed in the last 30 days still counts, so closing and recreating an organization does not start a new allowance.
- Logs show the parameters a call ignored. A call’s detail on the Usage page’s Logs tab lists each parameter the request sent that Zabio accepted and could not apply, with the reason (not supported, the provider caches on its own, reasoning off with tools on this path, the model cannot reason).
- The output estimate prices what is sent. On the Responses API, where OpenAI’s gpt-6-luna and gpt-6-sol keep their reasoning with tools, the cost estimate that routes and reserves now prices that reasoning instead of the chat completions rule’s off.
- Shared calls. Your organization now shares a percentage of its calls with Zabio, de-identified, to improve how Zabio routes requests: 100 percent by default during the beta, set by the owner from 0 to 100 in Organization settings, with a share of its own per project and per API key. A call sent with
store: false, the headerX-Zabio-Share: noorzabio.share: falseis never shared. The owner can delete what the organization shared from Settings. What is kept, for how long and who reads it is on the privacy page. - Sharing discount. Sharing earns up to 5 percent off Zabio’s fee: 0.05 percent of the fee per 1 percent shared, on the service fee and on the per call fee. The response’s
zabio.costgainsshare_discount_micros, usage totals and the CSV a Sharing discount line, and a call’s detail in Logs says whether it counted as shared. See Billing.
- Reasoning with tools on OpenAI’s gpt-6-luna and gpt-6-sol. On the Responses API, where Zabio sends OpenAI calls, these two models now keep their reasoning when the request carries tools; before, Zabio turned it off on every call with tools, a rule OpenAI states for chat completions only. On the calls that stay on chat completions (a
stop, your own OpenAI key,max_tokensunder 16) reasoning is still off with tools,zabio.reasoning.appliedsaysoffand a level you sent is listed inzabio.ignored_parameters. - Thinking with tools on Together AI and Alibaba Cloud. A
reasoning_effortyou send to Together AI’s thinking models (qwen3.5-9b,kimi-k3,glm-5.2, the DeepSeek copies) and to Alibaba Cloud’s Qwen and GLM models is now kept when the request carries tools; Zabio used to turn thinking off there on every call with tools. Measured on each model with a live tool round trip. DeepSeek’s own API still runs with thinking off on tool requests.
- The response says who cached.
zabio.cache.appliedon every chat completion and Responses answer, streamed or not:none(nothing was cached),zabio(Zabio’s cache markers on Anthropic wrote or read the cache) orvendor_automatic(the provider cached a repeated prefix on its own). OpenAI, Google and the other providers that cache automatically offer no way to decline it, so a request that setszabio.cache.ttlorcache.breakpointstononeon them is accepted and the field is listed inzabio.ignored_parameters; on Anthropicnonesends no marker, as before. The docs carry one table per provider saying who decides and whatnonedoes.
- OpenAI’s models answer through OpenAI’s newer API. A long think on an OpenAI model is now watched like any other provider’s, and a call that is not streamed gets its
200as soon as OpenAI accepts it. A call that setsstop, or runs on your own OpenAI key, is sent as before. Calls are billed at what OpenAI meters on that API, which differs slightly from before: about one more output token per call, and fewer input tokens on a call with tools or a JSON schema. - A call that fails is never billed. A streamed call that failed after it started was billed for its input; now no failed call is billed, also when the model provider had already started on it. Zabio pays the provider for that work. A call you cancel by closing the connection is billed for the work done, without the per-call fee. See Billing.
- Long answers no longer time out. Zabio now receives every answer from the model provider as it is written and keeps your connection open until it is done, so a long answer is no longer cut at a fixed time: an attempt ends only when the provider stops sending data for 2 minutes, or after 30 minutes in all. A call that is not streamed gets its
200status as soon as a provider accepts it (after 90 seconds at the latest, and at 90 seconds on OpenAI’s models that reason), then a space every 15 seconds until the answer; if it fails after that, the body is only anerrorobject with the request id, so check forerrorbefore you readchoices. A stream sends: ZABIO PROCESSINGcomments while nothing else is sent, and a stream that fails ends with the error event and a last chunk whosefinish_reasonis"error". Until any part of the answer has reached you, a failed attempt is tried again on another model. If you disconnect, the call is cancelled and you pay for the work done: the input and the output generated before you disconnected, streamed or not. See Errors. - Streamed calls bill exactly what unstreamed calls bill. On some models a streamed call counted cached tokens differently from the same call unstreamed; both now count the same tokens and bill the same amount.
- No default output limit. A request that sets no
max_tokens(or nomax_output_tokenson the Responses API) now gets no output limit from Zabio, as on OpenAI. Before, chat completions and batch lines were limited to 16,000 tokens and Responses turns to 4,096. Providers that need a value (Anthropic, DeepSeek, Together AI) are sent the model’s maximum output. Setmax_tokenswhenever you want a limit. A Responses object now showsmax_output_tokensasnullwhen the turn set none. The balance checks before a call, the hold of a batch and the per-minute token limit count the output expected for the job, so no call that worked before is refused. When your balance cannot pay for the model’s full output, the call is sent the limit your balance can still pay for instead of being refused. The Free plan keeps its 2,000-token output limit, now also on Free batch lines. See Billing. - Plain
automeans Zabio picks for you. The pages now describe plainauto(or a request with no model) as what it is: Zabio picks the cheapest model able to do the job, moving up a line when the job needs it. Routing is unchanged. On a plainautocall, Logs, the calls API (line, also in the CSV export), the MCP toolsrecent_callsandget_call, andescalated_fromnow show the line Zabio actually applied (cheap,balancedorbest) instead of alwaysbalanced, past calls included;zabio.routing.linestill showsauto. InGET /v1/models, plainautolists withtierautoinstead ofbalanced. - The analyzer states costs only. In
POST /v1/public/analyze, each line (lines[]) and each combination of the switches (scenarios) gives its cost only, besidetoday; neither carriessaving_usdany more. The playground on zabio.ai shows each model’s cost and, at the top, the request as sent and onautoside by side. - The analyzer’s tips show two costs, not a saving. In
POST /v1/public/analyze, a tip no longer carriessaving_usd: itsparamsgive the call as it is and with the tip (the line tip addsreference_modelandreference_usd, the cache tipcall_usdandcached_call_usd), so the difference shows without a saving claim. The playground’s tips say the same. - Savings are now computed when you look at them. What routing saved is worked out when you open the Dashboard or Usage, run
zabio usageor use the MCPusagetool, and is never stored per call. For each key, Zabio takes its baseline model by the 95% rule over the key’s last 30 days at that moment, prices eachautoanswer of the period on that model at the price it had when the call ran, and subtracts what you paid, fees included. A key never shows less than zero, and a period with no saving shows zero. The new routeGET /admin/v1/orgs/{org}/usage/savingsreturns the saving of a period, key by key. See Billing. - Calls show their cost only.
zabio.costno longer carriesdirect_micros,saved_micros,baselineorsaving_noteon chat completions, responses and batch lines, and the batch object no longer carriesdirect_microsorsaved_micros. Logs, the call detail, the CSV export and the MCP toolsrecent_calls,get_callandaskshow what each call cost, without a saving. The usage totals and the CSV export dropdirect_cost_micros,direct_cost_usd,saved_microsandsaved_usd, the CSV also dropsbaseline_pending, and a key no longer hasbaseline_model. Per call, the prompt cache shows as cached tokens and a split as the size of its excerpt:zabio.splitno longer carriessaved_microsorestimate, and the MCP tools no longer carrysaved_usdordifference_usd. What caching saved over a period stays in Usage. See API reference. - High-stakes requests on plain
autoget the strongest third. When a plainautorequest is high stakes, Zabio now picks among the models in the top third of skill for the work, asauto/bestdoes, instead of the top two thirds. - Hard and high-stakes requests keep reasoning after an empty answer. When an
autoanswer comes back empty because the model spent its whole output budget reasoning, a hard, frontier or high-stakes request no longer tries again with reasoning off. It tries again with a thinking budget that leaves room for the answer, on a stronger model if the first cannot take one, or at the lowest setting that still reasons. Easy and medium requests work as before, and the empty answer is still not billed. See Models. - Changes to the terms take effect when published. The terms no longer promise 30 days’ notice before a change: Zabio depends on providers, models and routing that change at any time. Zabio still tells organization owners about changes that matter, by email or in the web app.
- Notice of new sub-processors is now by subscription. Under the data processing agreement, an organization owner who writes to privacy@zabio.ai gets 30 days’ notice by email before a new sub-processor handles your content. Model vendors are listed when added, without that notice; to keep a new vendor from receiving your content, allow only the providers you accept in Model access, and a vendor added later stays off until you allow it.
- Prices and fees can change at any time. Zabio’s prices follow the providers’, and providers change theirs without notice, so a change to Zabio’s fees no longer waits 30 days. The pricing page always shows the current fees, and a change applies only to calls and top-ups made after it. See Billing.
- Small auto requests pay less for automatic model choice. The price of automatic model choice now follows the request: an
autorequest pays the same as the model’s own cost for it, at least 0.00015 USD and at most 0.00025 USD, once per request. Before, everyautorequest paid 0.00025 USD. A request whose model costs 0.00004 USD now pays 0.00015 USD instead of 0.00025 USD; a request whose model costs more than 0.00025 USD pays the same as before. The same range applies toautorequests on your own provider keys.zabio.cost.call_fee_microsshows what each request paid. See Billing. - When to name a model. The playground’s tips now say when a small request pays as much for automatic model choice as for the model itself, and what naming the model
autopicks would cost instead: the service fee only. The public analyzer returns it as thename_modeltip. See Billing. - Empty answers: the limits and the marks. An empty answer on a named model is free only when
max_tokenswas at least 1,000 tokens (or the model’s smallest thinking budget, when higher), and each organization’s free empty answers are capped per UTC day at the larger of 0.50 USD and 2% of what it was billed that day; past either limit the empty answer is billed andzabio.no_answersays so. Logs, the CSV export and the MCP toolsrecent_callsandget_callnow show each call’s role (an empty answer, a failed check) and reasoning setting, and mark the attempts Zabio did not bill; Errors only keeps the empty and failed-check attempts too.asksays when it answered on a second attempt. See Checked answers. - An empty answer is never billed. When a model spends its whole output budget reasoning and writes nothing, that call is not billed, whoever set the reasoning. On
autoZabio tries once more with less reasoning: the same model at its lowest setting, or a model whose reasoning can be held within the budget; areasoning_effortoflowon a model that can only reason fully or not at all no longer runs at full reasoning on that retry. With nothing to change, the empty answer arrives withzabio.no_answersaying why, and the MCP toolasksays “No answer” in words. With amax_tokensof 4,000 or less,autoprefers models whose reasoning can be limited. See Checked answers. - No negative savings. A call that cost more than its baseline now shows a saving of 0 and “no saving on this call” (
saving_note), and every total counts it as 0.direct_microsagainstcost_microsstill shows the difference, and the MCP toolget_callshows it asdifference_usd. - Connected apps can be allowed to ask later. Zabio’s sign-in now names read and ask, so Claude, OpenCode, VS Code and Cursor offer both on Zabio’s page (you can still untick ask). A connection whose app was never offered
asklists it, and using it makes the app ask you to allow it. Approving Claude.ai, VS Code or Cursor again for the same project replaces the earlier connection. See Allowing ask later. - Connect Codex, Cursor, VS Code and OpenCode. Connect an AI app now has steps for each, next to Claude and Claude Code, and Zabio is listed in the official MCP Registry as
ai.zabio/zabio. - Totals count no saving for calls made while a baseline was pending. A call on a key that had not reached its 20 calls is compared with itself, so it shows no saving. The dashboard, Usage, the CSV export, the CLI, the MCP
usagetool and batch totals now count none for it either, even after the key’s baseline is set, so every total adds up the calls as each one showed. Before, those calls’ fees counted as a negative saving. The CSV export gainssaved_micros,saved_usdandbaseline_pendingcolumns at the end. See API reference. - What a split saved, shown on its own. On a big request Zabio answered from an excerpt,
zabio.split.saved_micros(andget_call’ssplit.saved_usd) states what the split saved against the request sent whole, at list price. It is separate fromcost.saved_microsand shows while your key’s baseline is pending too. See Split and route. get_callstates the same saving asrecent_calls. On a key that has its baseline,get_callshowed a saving of 0 for a callrecent_callsshowed with its real saving. Both tools now read the saving andbaseline_pendingthe same way.
- No saving shown while a key’s baseline is pending. An
autocall on a key that has not reached the 20 calls its baseline needs no longer carriessaved_microsinzabio.cost;cost.baselinestill showspendingand the progress. Before, the field showed the fees as a negative saving. Code that readssaved_microsshould treat a missing value as no saving. See API reference. - An empty answer is retried one step up, never straight to the strongest model. When a model on
autospends its whole output budget thinking and answers nothing, Zabio now sends the request to the next cheapest model at the same skill level first, and on any line but best never to the strongest model for that kind of work. See Checked answers. - More from connected apps.
get_callandaskshow how Zabio split a big request, and reconnecting an app to the same project keeps its key’s savings baseline. See Connect an AI app. - Connected apps keep working across Zabio updates. A field Zabio adds to an MCP tool’s answer no longer makes an app that connected earlier refuse the answer.
asknow also returnscached_tokens, and itsinput_tokenscounts only the input not read from the cache, asget_calland Logs do. Connected apps shows when an app was last used within a minute. If Claude Code refusedaskanswers with “does not match the tool’s output schema” on 2026-10-14, reconnect it once with/mcp. See Connect an AI app. - Connect Claude and other AI apps to Zabio. Zabio now runs an MCP server. Add
https://mcp.zabio.ai/mcpto Claude.ai, Claude Code or another MCP app and it can read Zabio’s docs, models and prices, your project’s usage and recent calls, explain why a call went to its model, and ask Zabio’s models questions within a daily limit you set. Each connection has its own API key, and Settings, Connected apps disconnects it.https://mcp.zabio.ai/publicoffers the docs, models and status with no sign-in. See Connect an AI app. - One id for every call. Every response’s
zabioobject now carriescall_id, the id Logs shows for the call (call_and the same hex as a chat response’schatcmpl-id), on chat completions streamed or not, the Responses API, embeddings and batch results. See API reference. - A clear answer when a model cannot take tools. A call that names
gpt-6-astraand sendstoolsnow getsunsupported_parameterwith a sentence naming the limit, instead of the provider’s refusal. The same call without tools works as before, andautonever sends a call with tools there. See Errors.
- Price cuts reach you within a day. Zabio now reads every provider’s prices every day and applies a lower price as soon as it reads it. When a provider raises a price, Zabio keeps billing the old one until it confirms the change from what the provider charges.
- Prices checked against real charges. Every day Zabio now compares the provider cost it records for each model with what OpenAI and Anthropic actually charged it, so a price that drifts from the provider’s is found within a day.
- A clear answer when a provider is out of service. A call that names a model on a provider Zabio cannot use right now gets the new error
vendor_unavailable, naming the provider, instead of a provider error.autonever sends a call there, and when another provider serves the same model,automoves to it first. See Errors.
- Usage replaces Logs. A new Usage page has a Stats tab and a Logs tab under one filter bar (range, project, key, provider, model), in your time zone and kept in the page address. Stats charts spend, what Zabio saved, requests, tokens and caching, hourly or daily, stacked by model or by provider, with Top keys and Top models; Logs lists the calls with an errors-only filter, and a call opens with its details. The dashboard’s tiles link into it. See The web app.
- Calls keep their project. A call and its spend stay in the project they happened in, even when the key moves to another project later. Usage, the call list and the CSV export follow that.
- What caching saved, on every call. Usage shows how much of your input came from the prompt cache and what that saved at the providers’ prices.
- The web app on phones. The menu folds behind a Menu button on small screens, so every page uses the whole width.
- On the API: the usage routes take
providerandmodelfilters, the call list takesfrom,toanderrors, a new series route draws the charts, and calls carry theirproject_id. The usage summary no longer returnsopenrouter_equiv_microsandopenrouter_equiv_usd. - One match per account, from your signup. The launch match is now your account’s, once, in your first organization, and its 30 days start when you sign up instead of at your first top-up. The dashboard counts the days down. Other organizations you create, and people you invite, have no match of their own. See Credits and promotions.
- Keys that expire. A key can now expire: never, in 7, 30 or 90 days, or on a date you choose. An expired key is refused with the new error
key_expired, shows as Expired, and whoever created it gets an email 7 days before. A new expiration brings it back. See Errors. - Spend limits that reset. A key’s spend limit now resets every day, week or month at 00:00 UTC (weeks from Monday), or covers the key’s whole life. When it is reached, the error says when it resets, and the key list shows each key’s spend against its limit. Existing monthly caps became monthly limits. On the API, the key’s
spend_cap_micros_monthis nowspend_limit_microswithspend_reset. - A simpler way to create keys. Creating a key asks for its name, expiration and spend limit; everything else starts at its default. The Edit panel holds every setting, the key’s models included, and a key’s scopes can now be changed after it is created.
- Prompt caching on every call. Zabio now caches every call automatically, whether it names
autoor a model, and a call turns it off withcache.ttlnone. The key’s default prompt cache setting is gone: on the API,cache_ttl_defaultwas removed. Seecache.ttl. - Notice before your own plan costs more. When Zabio moves an organization that has its own pricing plan to a plan that raises any of its fees, the change takes effect at least 30 days later and the organization’s owner gets an email listing each fee that changes; a change that only lowers fees applies at once, and a cancelled change is announced too.
- A clearer error when no model is left. When the model access of your account, organization, project or key leaves
autono model to pick, the call now answers400 no_model_allowedand names the level to check, and the model picker warns before a change that would leave a project or key without a model forauto, naming them. - Model access at four levels. Your account, each organization, each project and each key now choose which models they allow, and a call may use only what every level allows;
autopicks only among those. One picker at every level: grouped by provider, with filters, a switch per provider that includes its future models, a checkbox per model and theautolines at the top, which you can now turn off one by one. On the API, the key’sallowed_modelsis nowmodel_access, and the organization’s vendor switch is a provider entry. See Model access. - One account above your organizations. Signing up now creates your account and its first organization, Default Organization, which you can rename in Settings. Only the account’s owner creates organizations and projects. People you invite belong only to the organizations you invite them to; someone you invited who wants their own account signs up with another email, and someone you invited who later belongs to no organization gets their own account at their next sign-in.
- Members limited to projects. When you invite a member you can choose the projects they work in, and change them later from Members. They then see only those projects’ keys, calls, usage and conversations; owners and admins see everything. A project menu next to the organization menu shows one project or all of them, and a new key is created in the project you are in.
- Keys in a project see their own project. On the API, a key that belongs to a project reads and changes only the conversations, responses, files and batches made with that project’s keys; a key at the organization’s level sees the whole organization. See Organizations, members and keys.
- Updates no longer interrupt your calls. When Zabio releases an update, calls already running, streams included, finish on the version that started them, and new calls go to the new version without a pause.
- Automatic recharge on the call that crosses your threshold. A recharge could wait for your next call or for the next check a few minutes later; it now starts on the call that takes your balance below the threshold.
- Ten models retired on Alibaba Cloud. Alibaba Cloud no longer serves
qwen3.6-max-preview,deepseek-v4-flash,qwen3-next-80b-a3b-thinking,qwen3-next-80b-a3b-instruct,qwen3-30b-a3b-thinking-2507,qwen3-30b-a3b-instruct-2507,qwen3-235b-a22b-thinking-2507,qwen3-235b-a22b-instruct-2507,qwen3-vl-235b-a22b-thinkingandqwen3-vl-235b-a22b-instructon its international service. The Models page marks them retired; choose another model there. - Prices now match each provider’s own price list. Six OpenAI models (
gpt-6.1-sol,gpt-6-sol,gpt-6-luna,gpt-5.6-sol,gpt-5.6-terra,gpt-5.6-luna) bill a cache write at 1.25 times the input price, as OpenAI does; cached input in an OpenAI batch is billed at the batch input price ongpt-4.1,gpt-4.1-mini,gpt-4.1-nano,gpt-4o,gpt-4o-mini,o1,o3,o3-miniando4-mini; cached input ongemini-3.1-pro-previewcosts the standard cache price in a batch and at flex;qwen3.5-plus-2026-04-20,qwen3.6-plusandqwen3.6-flash@alibaba-us, which Alibaba Cloud gives no cache discount, bill cached input at the input price; andgemini-3.5-flash, which Google now answers with Gemini 3.6 Flash, costs Gemini 3.6 Flash’s lower price. The Models page shows every price in force. - New models arrive on their own. When a provider adds a model, Zabio reads its price from the provider’s own price list, checks that the model answers, and makes it callable by name within the hour. Where the provider’s own sources show two prices, you pay the lower one. The Models page lists every model you can call.
- Lower cache prices on Claude Sonnet 5.5. Cached input on
claude-sonnet-5-5is now billed at Anthropic’s own price, 0.10 USD per million tokens (0.05 in a batch), half of what it was. - Provider sales reach your price. When a provider sells a model below its list price to everyone, Zabio charges the sale price.
- Three more models you can name, each at its provider’s own list price. The Models page lists them.
autopicks by skill for each kind of work. Everyautorequest now goes to the cheapest model skilled enough for its kind of work;auto/balancedandauto/bestask for more skill, and a hard or high-stakes request moves one step up. An answer that fails Zabio’s check is sent once more to a stronger model at Zabio’s cost. The dashboard, the Logs page andzabio.routing.task_typeshow the kind of work. See Models and routing.- Routing details show the tier you asked for and the skill floor used.
zabio.routing.linenow readsauto,cheap,balancedorbestas you sent it, and the newzabio.routing.floorsays which skill floor was applied.zabio.auto_eligible, the Models page and the newGET /v1/public/auto-modelsshow the modelsautocan pick today, and the request analyzer showsauto’s own picks. - Requests no longer fail on a parameter the model does not take. When the model that answers does not take
temperatureortop_p, Zabio leaves it out and names it inzabio.dropped_parametersand thex-zabio-dropped-paramsheader instead of returning an error.stopis always honored: where a model does not take it, Zabio cuts the answer itself. The Models page lists each model. - The whole saving is yours, with simpler fees. Zabio no longer takes a share of what routing saves you. Every call pays the service fee on the provider price, and every
autorequest pays a small fixed fee for automatic model choice, once, shown as its own line (call_fee_micros). This replaces 1.2.6’s “never for choosing the model”: choosing the model now has its own small price. The fees in force are on the pricing page. - Calculations always use reasoning. On math,
autoturns a model’s reasoning on and picks a model that can reason, so sums, averages and other calculations are worked through before the answer. - Reasoning levels follow each model’s own levels. Where a model names its thinking levels,
low,mediumandhighnow ask for those levels instead of a fixed number of thinking tokens, andzabio.reasoning.appliedreads the level. Two models that cannot stop thinking are now treated that way: with no level they think at their own default, andnonegives their lowest level. The Models page says which, so you can leave room inmax_tokens. - Thinking shows in your usage on more models.
usage.completion_tokens_details.reasoning_tokensand the dashboard now count the thinking of models that report it in their own format, so you can see which part of your output was thinking. - Calculations reason on more models. Some models reason only when asked, and Zabio now records which ones:
autoturns their reasoning on for calculations too. When you name one of them without a level,zabio.reasoning.appliednow readsoff, which is how they already answered. - You’re never charged for an empty answer caused by a setting Zabio chose. When
autoturns reasoning on, it makes sure yourmax_tokensleaves room for the answer. If the model still spends the whole budget thinking and writes nothing, that call is free, and a model that reasons by default answers instead, or the same model again without reasoning when there is none. With a reasoning level you set yourself, calls are billed as before. - Simpler routing details.
zabio.routingno longer includessubjectandlanguage, and thejobthatPOST /v1/public/analyzereturns no longer includeslanguage. Routing never used them.
- You pay for the answer, never for choosing the model. The small routing step that reads each
autorequest is now part of Zabio’s fee, soclassifier_microsreads 0 and the saving on everyautocall is larger. - Lower prompt cache costs on long prompts you send once. A long prompt is now written to the provider’s cache when it comes back, not the first time, so a document you send once no longer pays the cache write. Conversations and sessions are cached from the first turn, as before.
- Two new providers, Alibaba Cloud (US) and Alibaba Cloud (International). 34 more models you can name, the Qwen family among them, with the processing location of each shown on the Models page. Automatic routing keeps choosing from the same models as before.
- More models to choose from. The catalog carries 43 more models you can name, from every provider Zabio serves, each at the provider’s own list price. Automatic routing keeps choosing from the same models as before.
- A fresh look for every email. Sign-in links, receipts, balance notices and invitations now share one clear layout, addressed to you by name, with the Zabio logo, in English or Spanish, and replies reach our support team.
- Sign in with GitHub, next to Google, a password and the email link.
- Automatic top-ups. Credit is added automatically when your balance runs low, up to a monthly cap you choose.
- The Free plan. Start without a card: 100 requests a day on a set of fast models.
- Move credit between your organizations. Owners can transfer paid credit from one organization to another from the Billing page.
- Better observability. The dashboard shows your cache hit rate, your cost per million tokens and your spend by kind of work, and a new Logs page shows how long each call took.
- Security improvements across sign-in, accounts and payments, including better fraud protection for sign-ups and payments.