Trace an AI API Request Across Every AttemptDisclosure: I work on Modelflare, an OpenAI-compatible AI API gateway. The canonical version of this article lives on modelflare.dev. Decision first Trace an AI API Request Across Every Attempt is an 5h ago · 4 min readmatthewmodelflare.hashnode.dev
Apply Backpressure to AI API WorkloadsDisclosure: I work on Modelflare, an OpenAI-compatible AI API gateway. The canonical version of this article lives on modelflare.dev. Apply Backpressure to AI API Workloads: a production guide with an2A1d ago · 6 min readmatthewmodelflare.hashnode.dev
Kimi K3.1 Pro: Parameters, Capabilities, Prices, and Model ComparisonsDisclosure: I work on Modelflare, an OpenAI-compatible AI API gateway. The canonical version of this article lives on modelflare.dev. Kimi K3.1 Pro is Moonshot AI's new flagship for coding, visual and1d ago · 18 min readmatthewmodelflare.hashnode.dev
Load Test an LLM API Without Misleading ResultsProduction guide: Load Test an LLM API Without Misleading Results. It includes a deterministic artifact, failure boundaries, rollout checks, and source-qualified limitations. Disclosure: I work on Mod3d ago · 4 min readmatthewmodelflare.hashnode.dev
GPT-6.1 Terra: Capabilities, Parameters, Pricing, and Model ComparisonGPT-6.1 Terra is the GPT-6 family model aimed at the practical middle ground: fast visual reasoning, precise computer use, and clear writing at a lower token price than GPT-6.1 Sol and GPT-6 Astra. Th3d ago · 9 min readmatthewmodelflare.hashnode.dev
