Skip to main content
Follow along as Kyara Intelligence evolves. This is where we track what ships. Kyara has been in active development for a while, and while earlier work is not captured here, this is the first release we are tracking publicly.
​
Billing
August 23, 2026
Top-up credits now work without an active subscription.
  • Your credits keep working if your subscription lapses. If your plan ends or a payment fails, requests continue to run on any top-up credits you already bought. 403 no_active_plan is only returned when you have no active plan and no top-up credits. You still need an active subscription to buy credit packs. See Plans and credits.
​
APIBilling fairness
August 20, 2026
New request parameters, cleaner responses, and a few billing fixes.
  • More sampling controls. repetition_penalty and min_p are now accepted and forwarded to the model.
  • Sessions for prompt caching. Pass a session_id to keep a conversation on the same prompt cache across turns. See Sessions and prompt caching.
  • New models. deepseek/deepseek-v4-flash-0731 and deepseek/deepseek-v4-pro-0813 are in the catalog.
  • Cleaner responses and consistent errors. Responses carry only public fields, model always matches the catalog ID, and errors now use a fixed set of codes documented in the API reference.
  • Failed generations are free. Any request that fails, including a stream that fails partway through, is not billed.
  • Slow generations are no longer cut off. Long-running requests that went quiet for more than a few seconds could previously be dropped mid-generation.
​
Billing
August 2, 2026
One weekly allowance now replaces the separate base and weekly buckets.
  • One weekly allowance per plan. Spark includes $4.00 per week and Ember includes $8.00 per week. The base bucket and its eight-hour refresh are gone.
  • Everyone resets Friday at 06:00 UTC. The single global reset replaces per-user rolling windows. Unused allowance does not roll over.
  • Going over carries into the next reset. Postpay usage beyond your balance is deducted from Friday’s allowance. Renewing or changing plans restores the full allowance. Top-up credits are untouched and never go negative.
  • GET /v1/balance has a new shape. balances.weekly, caps.weekly, and a static refresh object replace the base and overage balances, caps, and two window objects. balances.total no longer reports a percentage. Reading your balance no longer triggers refills.
  • The dashboard has one weekly meter and a complete ledger. The meter shows when you are over the allowance.
​
Billing fairnessReasoning
July 31, 2026
A billing fairness release: you no longer pay for empty generations, and a credit refill race that could overfill buckets is fixed.
  • Empty generations are free. A generation that produces zero visible output costs nothing.
  • Every request has a sane output cap. Requests without an output limit now default to 8,192 output tokens, and explicit limits are clamped to the model’s maximum, so the pre-flight cost estimate and the actual generation always agree on the same bound.
  • Finer reasoning control. The reasoning object now accepts enabled and exclude booleans alongside effort and max_tokens, so you can toggle reasoning on or off and keep reasoning tokens out of the response.
  • Credit refills no longer overfill. Concurrent requests arriving right as a credit window elapsed could each apply a full refill, pushing a bucket above its plan cap. The refill decision now happens under a lock, and balances that were over-granted by this bug have been corrected.
​
StabilityBilling accuracy
July 24, 2026
A large rewrite of the API plus a wave of gateway improvements. The whole stack is more stable, usage tracking is more precise, and caching hits far more often.
  • Reasoning controls actually work now, with more levels. reasoning / reasoning_effort is now forwarded in the form the model expects, so the setting genuinely reaches the model instead of being silently dropped. The effort enum also grew from high / medium / low / minimal / none to add max and xhigh.
  • Legacy max_tokens is honored. Requests fold max_tokens into max_completion_tokens before forwarding, so older OpenAI-style clients get their output limits respected, including in the pre-flight cost estimate.
  • No more concurrency cap. The 3-concurrent-generations-per-user limit and its Too many concurrent generations (429) error are gone. Parallel requests just work.
  • Far fewer false “insufficient balance” rejections. The pre-flight affordability check used to assume 4,096 output tokens when the client did not set a limit. That default is now 800, so users with a small remaining balance can make normal-sized requests without being blocked by a wildly pessimistic estimate.
  • Cleaner, more standard API responses. Internal fields are now stripped from both non-streaming responses and every streaming chunk (previously chunks leaked them), and the model field is rewritten back to the public model id. Responses look like plain OpenAI responses.
  • More accurate billing. Streaming cost is only resolved from chunks that actually carry usage. Streams that end without usage are billed on observed output and tagged completed_no_usage, and the whole flow is typed end to end, so you get charged on real usage numbers more reliably.
  • Better error messages. An unknown model is now a 400 with code: "model_not_found" (previously a bare 404). Accounts without a plan get a 403 with code: "no_active_plan" and a human-readable message. Validation errors were consolidated for consistent messages and parameters.
  • More precise usage tracking. Usage accounting is tighter and more reliable across both streaming and non-streaming paths.
  • Higher cache hit rate. Caching now hits far more often, cutting latency and cost.
  • Slightly faster requests. The balance snapshot is read once and reused across the windowed-credit refresh and the affordability check, cutting redundant database roundtrips on /v1/chat/completions and /v1/balance.
​
First tracked release
July 24, 2026
The starting point for our public changelog.
  • OpenAI-compatible gateway live at https://api.kyara-intelligence.com/v1.
  • Curated catalog of high-performance models behind one familiar API.
  • Dashboard for creating API keys and managing your account.
  • Plans and credits with a bucket-based balance system.
  • Documentation covering quickstart, authentication, integrations, and the API reference.