AI API Bills Catch Developers Off Guard — Token Costs Explained

·1 views

Developers building with AI APIs from OpenAI, Anthropic, and Google frequently face unexpected costs because tokens do not map directly to words or characters. Output tokens are consistently more expensive than input tokens, with GPT-4o charging four times more for output and Claude Opus 4 charging five times more. Exact token counts are only possible for OpenAI models, as Anthropic and Google do not publish portable client-side tokenizers, making Claude and Gemini estimates approximate. A free token calculator has been released to help developers check prompt size, context window usage, and estimated cost across all three major providers before sending a request. Understanding token counts in advance not only reduces costs but also encourages more deliberate prompt design decisions.

Read the full story at DEV Community

This is an AI-generated summary. ShortSingh links to the original source for the complete article.

Discussion (0)

Zep vs HydraDB: How Two Temporal Graph Tools Serve Different AI Memory Needs

Zep and HydraDB are two tools that use temporal graphs to manage context for AI applications, but they operate at different levels of abstraction. Zep is a managed context platform that handles user memory automatically, offering built-in constructs like users, threads, and Context Blocks built on its proprietary Context Graph Engine. HydraDB, by contrast, exposes the underlying graph database layer, allowing engineering teams to define their own data models, ontologies, and workflows. Zep is better suited for teams focused primarily on cross-session conversational memory with minimal setup, while HydraDB targets use cases where memory is one component of a broader, company-wide context system. The choice ultimately comes down to whether a team wants ready-made conventions or full control over the application model.

0 comments Read more at DEV Community

ProgrammingHacker News ·

Blog Post Maps Every Exterior Filming Location in The Taking of Pelham 123

A blogger at iafisher.com has published a detailed analysis identifying every exterior shot used in the film The Taking of Pelham 123. The post was shared on Hacker News in July 2026, attracting minimal engagement with only 4 points and no comments at the time of posting. The article focuses on the real-world locations used for outdoor scenes in the classic thriller. Such location-scouting breakdowns are a popular genre among film enthusiasts and urban historians. The original film, set in New York City, has long been of interest to those curious about its authentic street-level cinematography.

0 comments Read more at Hacker News

ProgrammingDEV Community ·

Sluice: Open-Source Proxy Adds Tenant-Aware Traffic Control for Self-Hosted LLMs

A developer has released Sluice, an open-source proxy layer designed to enforce quality-of-service policies for self-hosted large language model inference using vLLM. The tool addresses a gap in existing infrastructure: when GPU KV-cache capacity is under pressure, standard schedulers treat all requests equally regardless of tenant priority or service agreements. Sluice assigns tenants to one of three tiers — Guaranteed, Standard, or Best-Effort — and makes per-request admission decisions based on live signals including GPU cache usage, queue depth, and SLA violation rates pulled from Prometheus and PostgreSQL. Unlike Kubernetes or generic API gateways such as Envoy or Kong, Sluice can dynamically rewrite parameters like max_tokens or shed lower-priority traffic before requests ever reach the inference engine. The project is available on GitHub and is positioned as a complement to, not a replacement for, existing routing and scheduling infrastructure.

0 comments Read more at DEV Community

ProgrammingDEV Community ·

UCIe 3.0 Chiplet Verification: Using Scenario Matrices for Runtime Recalibration

UCIe 3.0 introduces runtime recalibration as part of its link-management and power-efficiency enhancements, making cross-layer interaction testing a critical challenge for chiplet verification. The core difficulty lies not in the recalibration request itself, but in its potential overlap with concurrent link activities such as bursty traffic, lane degradation, power-state transitions, or error conditions. A single directed test cannot adequately cover this complex state space, so engineers are advised to model recalibration as a scenario matrix built from explicit, reviewable dimensions including trigger type, data rate, lane state, power state, and expected outcome. Product-specific constraints — such as unsupported lane configurations at high data rates or disabled firmware triggers — should be centralized in a shared configuration object rather than scattered across test sequence code. This approach keeps exclusions transparent, prevents invalid scenario generation, and supports consistent coverage tracking across simulation, emulation, and post-silicon sign-off.

0 comments Read more at DEV Community