Tag: api

15 articles

· ai / claude

Claude Sonnet 4 for developers — what changed from Claude 3

Sonnet 4 is a reliability upgrade for agentic work, not a raw benchmark jump. What changed in the API, where reward hacking dropped 69%, and whether to upgrade now.

· llm / api

GitHub Models 2026 — free LLM API for developers reviewed

We tested GitHub Models' free-tier LLM API: rate limits, OpenAI compatibility, and whether 150 calls a day is enough for a real side project.

· claude / anthropic

Claude API 2026: Prompt Caching, Tool Use & Batches

A practical guide to the three Claude API features that separate toy prototypes from production integrations: prompt caching, tool use, and Message Batches API.

· openrouter / llm

OpenRouter vs direct API — when the gateway pays off

OpenRouter wins for multi-model projects and automatic failover. Direct API wins at high volume or for compliance-critical workloads. Here is how to decide.

· api / speech-to-text

Best speech-to-text API for podcasts in 2026: compared

Deepgram Nova-3 for speed and the largest free tier. AssemblyAI Universal-2 if transcript intelligence is the product. WER benchmarks and diarization costs.

· tts / text-to-speech

Best Text-to-Speech API in 2026: Ranked and Compared

ElevenLabs leads on voice quality, Cartesia on streaming latency, Google on cost. 8 TTS API providers scored across TTS Arena V2, P50 latency, and pricing.

· elysia / hono

Elysia vs Hono — Bun-native server picks in 2026

Hono is the safe default for Cloudflare Workers and multi-runtime projects. Elysia wins on Bun with Eden Treaty — zero-codegen end-to-end type safety.

· trpc / rest

tRPC vs REST: When to Drop OpenAPI in TypeScript Apps

Use tRPC for full-stack TypeScript monorepos where type drift bites. Use REST + OpenAPI for public APIs and non-TypeScript consumers. In 2026 you need both.

· fastify / express

Fastify vs Express — the performance gap is real (2026)

Fastify handles 55% more requests per second than Express 5.x. For new TypeScript APIs, the DX win is as compelling as the speed. Here's what the numbers show.

· email / resend

Resend vs SendGrid 2025: Same Price, Very Different Setup

At ≤100k emails/month, pricing is identical to within $0.05. The real difference: Resend takes 8 minutes to set up; SendGrid takes 45. And SendGrid killed its permanent free tier in May 2025.

· api / image-generation

Best AI image API in 2026: pricing, rate limits, SDK

fal.ai FLUX.1 [schnell] at $0.003/image for cost, FLUX.2 [pro] for production quality, Stable Diffusion open weights for self-hosting. Developer breakdown.

· hono / express

Hono vs Express: The Right Node.js API Framework in 2026

Pick Hono for edge deployments and TypeScript-first DX. Stay on Express if you rely on Passport.js or a middleware stack you cannot replace.

· python / fastapi

FastAPI vs Flask 2026: when to upgrade your Python API

FastAPI wins on async throughput, auto-docs, and type safety. Flask holds for stable legacy codebases. Covers FastAPI 0.136.1 and Flask 3.1.3.

· trpc / graphql

tRPC vs GraphQL in 2026 — when one beats the other

tRPC wins for TypeScript monorepos with no external API consumers. GraphQL wins the moment a non-TypeScript client exists. Here is when each choice pays off.

· mcp / rest

MCP vs REST: When Each Makes Sense for AI Agents

REST is battle-tested, but MCP was built for agents. Here's when to use each — with a decision matrix, migration notes, and the honest case for both.