Tag archive
For anyone experiencing issues with tools not being called in Ollama's OpenAI-compatible API, this article explains why the specified 16,384 context length was actually running at 4,096 and how to fix the sending route.
OpenAI cut GPT-6 Sol and Luna prices in half, improved caching for agent workloads, and published alignment numbers worth reading before granting an agent more autonomy. Here is what changed, what to verify yourself, and where OpenAI's own benchmark comparisons need a caveat.
OpenAI Responses API calls fail in predictable ways when a tool result loses its call_id, the...
GPT-6.1 Sol keeps GPT-6 Sol’s standard token rates while changing the safe integration path. This...
Unsupported parameter errors can break GPT-6 Astra API migrations. Fix model, reasoning, cache, tool, region, and safety-stop issues before
Abstract Between August and September 2026, Anthropic, OpenAI, and major Chinese AI labs...
FreeLLMAPI aggregates the free tiers of 18 LLM providers into a single OpenAI-compatible /v1 endpoint, then leans on per-key rate tracking a
A wire-format comparison of Claude, OpenAI, and Gemini SSE streaming: event shapes, tool-call reassembly from partial JSON, and what to do when the stream dies mid-response.
Originally published at norvik.tech Introduction Explore the nuances of Claude API and...
OpenAI API: Complete Developer Guide Picture this: you're in a meeting where stakeholders...
OpenAI is filing its IPO S-1 this week, targeting a $1T+ listing in September 2026. Here is what API pricing, model cadence, and the Microsoft restructure mean
Here's an endpoint that looks completely fine: routes/chat.ts import OpenAI from "openai"; const...