Hamed Nilforoshan evaluated OpenAI Decisions API against Jev on HiringCafe, reporting that OpenAI's API was twice as expensive and 5% to 10% worse for ranking job query relevance.
Cloudflare AI Gateway now standardizes credential rejection responses across all providers, returning an HTTP 401 status code with error code 2009 for consistent error handling.
OpenAI has consolidated its five paid API usage tiers into three—Build, Launch, and Grow. Qualifying for Grow, the new highest tier, now requires $500 in total API payments instead of $1,000.
OpenAI’s premium Ultrafast tier offers up to 8x faster token generation in Codex, at 300 tokens per second, and up to 6x faster generation in the API.
OpenAI Developers says GPT-6.1 Sol is available today in the API, as well as in ChatGPT Work and Codex. It recommends Astra when maximizing quality matters most, and GPT-6.1 Sol for complex work meant to run more often, citing near-Astra performance at a substantially lower cost.
OpenRouter says developers already calling Jev can switch to Kev by changing only the model field to jaredpalmer/kev-4b.
The three models can be requested through one API from comfy, wavespeed, runware, fal, and higgsfield, with the destination chosen by price and availability.
Comfy Router keeps the same model string and arguments, with no new SDK, key, or redeploy. It uses Comfy credits, with no subscription or Router fee, and launches with Comfy, Runware, Wavespeed, Fal, and Higgsfield.
He says OpenRouter routes Batch API requests to the cheapest provider, and that callers can use /chat/completions, /responses, or /messages on all models. Requests can be polled for a full response without a files API, and bring-your-own-key works.
Luna is available on all plans and the API; the $10 GOAT plan is given as an example with about 30,000 requests and about 1.5 billion tokens. Sol is available on the Pro and Max plans and the API.
Higher default cache-hit rates let more GPT-6 input tokens receive cached-input discounts of up to 90%. OpenAI Developers says the change helps agents run faster and cost less.
A new Prompt Caching Dashboard on platform.openai.com tracks cache-hit rates. A diagnostics API identifies changes that prevented cache reuse and estimates how many tokens were affected.
Command Code now offers Claude Opus 5.5 in Command Code Max and through its API. No pricing, quota, or other access conditions were stated.
GPT-6 Sol and GPT-6 Luna are available in the API and are rolling out in Codex and ChatGPT Work for Plus, Pro, Business, and Enterprise users.
On September 22, 2026, Plus, Pro, Business, Enterprise, and Edu users get both models in ChatGPT Work and Codex, and both are available in the API. Free and Go users can try GPT-6 Luna in the desktop app.
OpenRouter’s Batch API is available for work that does not need an immediate answer. It cuts per-token pricing in half on most models and returns results within 24 hours.
Entering one of the listed model IDs in Codex starts a query. The IDs cover named GLM, Kimi, DeepSeek, and GPT variants, with request details in B.AI’s LLM service API documentation.
Command Code said Grok 4.7 is now live in Command Code and available on GOAT, Pro, Max, and via API. It also listed 40% for the next 7 days and $35 credits (3.5x usage) in GOAT.
Zixuan Li (@ZixuanLi_) said Faster GLM-5.3-Flash is now live, with model code glm-5.3-flashx and speeds up to 200 tokens/s. It is priced at 2.5× GLM-5.3-Flash on both the Coding Plan and API, open to all API users, while Coding Plan users can apply via a Google Form.
Runway announced a one-day in-person hackathon in San Francisco on September 30th at the Masonic, alongside the Runway AI Summit, to build an agent, app, or creative workflow with Runway's API. A working demo by 5pm is required for a chance at $25K and 200K credits.
