Changelog
Recent updates to apiToken.sale — new GPT and Gemini models, guides, localization, and platform improvements.
New models, price changes and platform updates are posted first in our Telegram channel @apiTokenSale.
2026-10-15GPT-5.5 withdrawn
OpenAI retired GPT-5.5 from ChatGPT-authenticated Codex on October 14, 2026 at 19:00 UTC. Our subscription catalog no longer offers gpt-5.5. Choose gpt-6.1-sol for supported new requests; the OpenAI Platform API is unaffected. Historical usage remains available. GPT-5.4 and GPT-5.5 model-page URLs now redirect directly to GPT-6.1 Sol.
2026-10GPT-5.4 withdrawn
OpenAI no longer serves GPT-5.4 on the subscriptions this pool runs on, so gpt-5.4 is gone from the catalogue, GET /v1/models and the docs. The original replacement was GPT-5.5; after its October 14 retirement, both model-page URLs redirect to GPT-6.1 Sol.
2026-10Kimi models retired
apiToken.sale no longer serves Kimi. The kimi/* models are gone from the catalogue, GET /v1/models and the docs; a request for a kimi/* model returns 404 model_not_found. GPT and Gemini are unchanged on the same key and endpoint. Past Kimi spend stays in your usage history.
2026-09Daily and monthly spend caps, model allowlist, customer Activity API
Each customer key can now take an optional UTC-day period spend cap, UTC-month period spend cap, and a model allowlist from the published catalog, on top of the lifetime spending limit and expiration date. Authenticated customers can query GET /activity for request-level tokens, charged nanoUSD, public errors, and agent session grouping.
2026-09Public error envelopes match each official API
Every supported lane now returns the official error envelope of that protocol: Anthropic JSON (HTTP 402 is billing_error), OpenAI {error:{message,type,param,code}} (prepaid money stays HTTP 402 insufficient_quota, never 429), and Google {error:{code,message,status,details}} (invalid keys remain 400 API_KEY_INVALID; money is 402 FAILED_PRECONDITION). The KIMI lane on kimi/* uses that same Anthropic envelope; the extra 400s are documented_limitation for mcp_servers and provider-executed tools, plus unsupported_parameter for count_tokens. A present official field this endpoint cannot honour is fail-closed 400 documented_limitation or unsupported_parameter with a named field and a workaround — never a silent 200. Exact strings: /docs/errors.
2026-08One unified router endpoint for every provider
https://router.apitoken.sale now serves every provider on a single endpoint: the Anthropic Messages lane (POST /v1/messages), the OpenAI lanes (POST /v1/responses and the OpenAI-compatible universal lane POST /v1/chat/completions for any catalog model) and the native Gemini lane (/v1beta/models/{model}:generateContent) — all with the same sk-pool key. A unified namespaced catalog (openai/*, google/*) is available at GET /v1/models. The legacy per-provider hosts (openai.api.apitoken.sale/v1, gemini.api.apitoken.sale) remain fully supported for existing integrations.
2026-07One flat 50% discount — tiers retired
B2C pricing is now a flat 50% off official provider spend on every request, for every account and any top-up amount. The Starter/Builder/Pro/Studio/Scale ladder, cumulative top-up thresholds and 30-day tier retention are gone — there is nothing to unlock and nothing to keep.
2026-07GPT-5.6 on the same key — apiToken.sale is now multi-provider
The OpenAI-compatible API at openai.api.apitoken.sale/v1 serves the GPT-5.6 line (sol, terra, luna), gpt-5.5 and gpt-5.4 through Responses and Chat Completions with SSE streaming. One sk-pool key and one prepaid balance cover every model.
2026-07Tier ladder rebalanced
B2C tier discounts now progress from 60% to 70% off official spend (Starter 60%, Builder 62.5%, Pro 65%, Studio 67.5%, Scale 70%). Thresholds and 30-day holds are unchanged; Starter stays free at 60%.
2026-07Guides in Russian and Chinese
The full API guide library is now available in English, Russian and Simplified Chinese with per-language URLs.
2026-07Per-key lifetime guardrails
Set an optional lifetime spending limit and expiration date when you create a key, then update or remove either guardrail from the dashboard.
2026-05Progressive discount tiers
B2C accounts start 60% below official spend and progress up to 70% off as cumulative top-ups grow.