Kyma APIKyma API

Changelog

What changed in Kyma API, newest first. Each change with its detail is in the full release notes.

September 7, 2026

  • Signup credit is now a free tier, 13 lower-cost chat models plus embeddings and reranking, instead of cash for the whole catalogue; one purchase of any size unlocks every model, permanently
  • The free tier now covers media too, on a price line instead of a blanket ban, cheap transcription and the cheapest image SKU stay free on signup credit, while image, video, music and premium voices need a top-up first
  • A request is now checked against what it could actually cost before it runs, and when your balance covers the prompt but not the full max_tokens, the reply is shortened to fit instead of refused
  • Every dashboard page loads faster, the API no longer re-reads your session from the database on each of the five to ten calls a page makes, and your balance is served from cache between the moments it actually changes
  • The keys, billing and referrals pages stop doing work they can avoid, per-key spend is kept as it happens instead of re-summed from your whole history, and the billing page no longer waits on a card lookup it did not need to make
  • Pages stop hiding what they already know while they wait for the network, /welcome shows its heading and your key card immediately instead of a full-page "Loading...", the Muse gallery shows placeholder tiles instead of telling you it is empty, /rate-limits draws the whole tier ladder before your account's tier arrives, and a number that has not arrived reads as "—" rather than 0
  • Each part of a dashboard page now appears as soon as its own data lands, instead of the whole page waiting for the slowest call, and a section still loading says so rather than showing a zero
  • Usage is always recorded and deducted, a request that costs more than your remaining balance is now charged in full and shows a negative balance, and the next request is refused until you top up

September 6, 2026

  • The dashboard shell loads a 190-byte identity instead of a 14 KB key dump on every page, per-key spend lives on the keys endpoint, and the Usage and Logs pages answer in well under a second
  • The MCP sign-in screen now has Continue with Google, so accounts created with Google can connect Claude, Cursor, Codex and ChatGPT without a password

September 5, 2026

  • qwen-3.6-plus gets cheaper, the published rate follows what it actually costs to serve
  • The Usage page loads in well under a second, and 7d / 30d / 90d show the range they say

September 4, 2026

  • A page that answers "what would moving part of my work to a cheaper model save?" from Kyma's own measured sessions, with every number traceable to one table
  • An agent can see what it spent, read back one request it made, and price a call before making it, and a chat call can carry its own cost ceiling

September 3, 2026

  • A request for a retired Imagen 4 model now names its replacement instead of failing upstream with nothing to act on
  • Gemini 3.8 Flash and Claude Fable 5.1 are available by name on the chat endpoints
  • Two open-weight multimodal models are available by name, Qwen 3.8 27B and DeepSeek V4 Flash Vision (experimental)
  • Promotional prices on five models now show as promotions with an end date, and GPT-5.6 Sol is listed at the price you were already being billed
  • qwen-3.7-max is listed at the price of the route that now serves it, so the page and the bill agree again
  • The 43 image, video, speech, music and transcription model pages now show the price in the unit the model bills in, and only the features it has

August 14, 2026

  • Gemini 3.1 Pro is live at $2.70/$16.20 per million tokens, the first Gemini Pro tier on Kyma, and Nano Banana 3 Flash is repaired after its upstream preview endpoint stopped answering
  • Gemini 3.7 Flash is live at $1.01/$5.06 per million tokens, and half that, $0.51/$2.53, while the launch promotion runs
  • 7 prices fall and 14 rise, every one computed from what the request actually costs to serve
  • v1/models now quotes the price you actually pay today, so a model on promotion no longer reads as twice its real cost

August 13, 2026

  • Claude Fable 5 is live at $13.50 in and $67.50 out per million tokens
  • Grok 4.6 is live at $2.70 in and $8.10 out per million tokens
  • Qwen 3.8 Max is live at $2.2275 in and $6.684 out per million tokens
  • Qwen 3.8 Max is listed once, at the $2.2275 / $6.684 rate

August 3, 2026

  • You are now billed at the exact rates published by the suppliers, eliminating incorrect pricing on several popular models.
  • The model uptime dashboard now accurately reflects supplier availability instead of showing false outages caused by our own probe limits.

August 2, 2026

  • 1 model got cheaper to call, effective immediately

August 1, 2026

  • You can list everything one lab makes in a single request
  • One click unsubscribes you from Kyma email, and it sticks
  • You can add live web results to 25 models by appending one suffix to the model id
  • Grok, Meta's newest line and Claude are all callable with the same key as everything else
  • Published prices follow the cheapest route that can serve you, not whichever one happened to carry the last request
  • What a model says it can do now matches what its provider says it can do
  • Searching the models page no longer throws you somewhere else on the page

July 31, 2026

  • You can compare models on measured speed and uptime instead of taking a claim on trust
  • When a supplier cuts its price, yours falls too, automatically, and within a day
  • Your account is harder to attack, and a database read no longer yields anything replayable
  • The cost in your streaming response is what you were charged, not what your request cost Kyma

July 30, 2026

  • Older clients that speak the legacy completions shape work without changing your code
  • You can build retrieval on Kyma without a second vendor for the embedding half
  • Every model has its own page, with the whole price and a plain-markdown mirror an agent can read
  • You are billed for the route that actually served you, and never above the published price
  • Pages load faster, and the site stops rendering dark on a light theme

July 29, 2026

  • You have until 20 October to move off nano-banana, and Kyma stopped recommending it today
  • Six models joined the catalogue, including the cheapest one Kyma sells
  • Five models were repriced against what they actually cost to serve, two of them had been sold below that
  • Multi-turn reasoning with Gemini 3 keeps its train of thought across turns

July 28, 2026

  • A long conversation is never rescued by a model too small to hold it

July 27, 2026

  • You can ask the catalogue for exactly the models you need instead of reading all of them
  • An error now tells you whose problem it is, so you know whether retrying will help

June 2026

  • Every model got a page with live numbers instead of a specification copied from a launch post
  • Six models joined, including two flagship coding models and the strongest open-weight tier Kyma had carried
  • Speech and transcription stopped failing outright when one supplier did

June 19, 2026

  • 2 new flagship models: GLM 5.2 and Kimi K2.7 Code

June 10, 2026

  • 4 new models: Qwen 3.7 Plus, MiniMax M3, Nemotron 3 Ultra, Step 3.7 Flash

June 4, 2026

  • ElevenLabs v3, most expressive TTS + low-latency streaming

May 2026

  • Speech, music and sound effects arrived, so an audio app no longer needs a second vendor and a second bill
  • Image and video generation grew a real catalogue, and pricing that matches how each one actually charges
  • Web-grounded answers became callable models rather than a separate search product to integrate
  • Signing up got harder to abuse and easier for real users on shared connections

May 17, 2026 (later)

  • Google media models, 7 new SKUs + public pricing catalog

May 17, 2026

  • Audio infrastructure refresh

May 1, 2026

  • Several updates, listed in the full release notes

April 30, 2026

  • MiniMax bundle, 9 new SKUs across audio, image, video
  • Sharing a cloned voice_id with another account is rejected
  • Image catalog refresh, 5 new SKUs

April 29, 2026

  • Audio - 2 new endpoints + 2 SKUs

April 26, 2026

  • Video Generation - 5 new models

April 25, 2026

  • DeepSeek V4, Pro and Flash
  • Image Generation, Week 1

April 23, 2026

  • API Reliability and Platform Changes

April 21, 2026

  • Product and Dashboard Updates

April 19, 2026

  • Product and Dashboard Updates

April 17, 2026

  • Agent, Install, and Runtime Improvements

April 16, 2026

  • Kyma Agent v0.1.12, KYMA.md context + MCP servers
  • GLM family from Z.AI

April 15, 2026

  • Kyma Agent v0.1.8

April 11, 2026

  • Kyma CLI v0.3

April 10, 2026

  • Higher Limits, Better Emails

April 8, 2026

  • Models & Pricing

April 7, 2026

  • Reliability & Performance

April 4, 2026

  • Launch