22 articles tagged
One Cerebras model page carries two different prices and two speeds for Gemma 4 31B. The GPT-OSS-120B page forks its free-tier limit 6x. Here is what each source says and which to plan against.
Cursor's 19 August 2026 release runs each cloud subagent on its own VM. No machine-hour fee exists, so a five-way swarm costs roughly five times the tokens instead, and the docs restrict CI autofix to Teams.
OpenAI released a Prompt Caching dashboard on 20 August 2026 that reports cache reads per write. On GPT-5.6 that ratio decides whether caching cuts your input bill by 78 percent or raises it by 25 percent, and Azure
Perplexity's 13 August 2026 post gives Sonar 45 days, ending 27 September 2026. The migration guide names no date, the changelog names none, and the docs' benchmarks show 5.46x where the blog claims 7x.
Editing the tools array mid-session invalidates the entire Claude prompt cache. The mid-conversation-tool-changes-2026-07-01 beta replaces that edit with two content blocks, and the price gap between a cache read and
Poolside's 118B open-weight coding model is 100x cheaper on input than Claude Fable 5 and scores 70.2% to Fable's 88% on Terminal-Bench 2.1. Here is the routing decision that follows from those two numbers.
Qwen3.8-Max shipped on 3 August 2026 at $2 input and $6 output per million tokens, with a 1M context and 15,000 requests per minute. But Qwen3.7-Max is on a 50% discount at $1.25 and $3.75, so the newer flagship costs
In 2026, 98% of FinOps teams manage AI spend, and LLM prices span more than 140x from budget to frontier. An AI gateway with cost-aware routing and caching cuts that bill 40-70% without downgrading quality. How eCorpIT
Alibaba's Qwen3.7 Flash is the cheapest way into a 1M-token vision model, until you fill the window. Here is the tier-by-tier cost math against Gemini 3.5 Flash-Lite and GPT-5.6 Luna for high-volume agents.
Agentic RAG makes multiple retrieval and reasoning passes, costing about 2.5x a single-pass classic RAG. A 2026 baseline study shows a lightweight query router recovering most accuracy at 28.1% token savings. When each
GitHub Copilot moved to usage-based AI Credits on June 1, 2026 and Cursor split its seats into usage pools. That reshapes the BYOK-versus-subscription math for every dev team. A worked cost model and a decision guide.
Anthropic's Claude Opus 5 matches near-Fable-5 intelligence at 26% lower cost per task. A guide to the coding-agent benchmarks, the token economics, and when Opus 5 should be your default.
Google cut the Gemini Flash output rate from $9.00 to $7.50 per million tokens and made the model emit 17% fewer of them. Stack that against GPT-5.6 Luna at $1/$6 and Claude Sonnet 5's tokenizer change, and
Frontier LLM output prices fell about 94% since 2023, and a 100x spread now separates the cheapest models from the priciest. How to migrate off deprecated models and cut your AI bill.
Kimi K3 leads the Frontend Code arena and ships open weights by July 27, 2026. A senior engineer's read on its coding benchmarks, $3/$15 API pricing, self-host reality and the adopt-vs-wait decision.
Stanford found RAG-backed legal tools still hallucinate 17-34% of the time. Here is what an enterprise RAG knowledge assistant costs in 2026, which retrieval setup actually works, and how eCorpIT builds one.
Z.ai's GLM-5.2 is the strongest open-weight coding model of 2026 and a third of Claude Opus 4.8's input price. Self-hosting it is another bill: 753B parameters, 1.5 TB of weights, a GPU node rented by the hour.
US firms routed up to 46% of their OpenRouter tokens to Chinese open models in 2026 because they cost 60-90% less. Here is how DeepSeek, Qwen and GLM compare with OpenAI and Google on price, quality and risk.
Over 40% of agentic AI projects will be canceled by the end of 2027, per Gartner. These are the five lessons eCorpIT learned shipping enterprise AI agents that actually reach production, priced in 2026 dollars
LLM API prices run from $0.14 to $30 per million tokens in June 2026, and agentic workloads multiply the bill. Seven free, open-source tools that make engineering teams' LLM spend measurable and attributable.
With 98% of FinOps teams now managing AI spend, LLM cost control is a 2026 priority. Here are 6 free, mostly open-source tools, from LiteLLM and Langfuse to tokencost and OpenCost, to measure LLM spend.
Strategic optimisation can cut LLM costs by 60 to 80 percent. Seven AI cost tools, from observability with Langfuse to prompt compression with LLMLingua, that engineering teams use to cut token spend in 2026.
