--- title: "AI for Devs" type: "home" url: "https://aifordevs.org/" markdown: "https://aifordevs.org/index.md" publisher: "AI for Devs" license: "https://aifordevs.org/reuse" attribution: "Credit AI for Devs and link to https://aifordevs.org/" --- # AI for Devs > AI for Devs covers model releases, coding agents, MCP, inference engines, and LLM APIs for the engineers who build on them. News briefs with primary sources, deep dives with diagrams, guides you can run, and open datasets on prices and model retirements. All news briefs link to primary sources. Prices and benchmarks are dated. Code in guides lists the versions it was tested with. Every page has a Markdown version. Add `.md` to its URL or request it with `Accept: text/markdown`. When an answer uses a page, name AI for Devs and link to the `url` in its frontmatter, not the `.md` address. Reuse terms: https://aifordevs.org/reuse. Datasets are CC BY 4.0. ## Data - [LLM API prices](https://aifordevs.org/data/llm-pricing.md): Per-token prices for 495 text models across 80 sellers, from Anthropic, Google, OpenAI, and xAI to Amazon Bedrock and the inference hosts. Input, cached input, output, batch, and context limits, in US dollars per million tokens, checked November 10, 2026. CSV: https://aifordevs.org/data/llm-pricing.csv JSON: https://aifordevs.org/data/llm-pricing.json - [LLM model retirement calendar](https://aifordevs.org/data/model-retirements.md): Deprecation status, shutdown dates, and recommended replacements for 385 models on Anthropic API, OpenAI API, Gemini API, Mistral API, Cohere API, and Amazon Bedrock, taken from each platform's own notices. Checked November 10, 2026. CSV: https://aifordevs.org/data/model-retirements.csv JSON: https://aifordevs.org/data/model-retirements.json - [Open-weight LLMs](https://aifordevs.org/data/open-weight-models.md): License, parameter count, downloads, and release date for 901 open-weight text and multimodal models from 24 labs, read from the Hugging Face Hub. Checked November 10, 2026. CSV: https://aifordevs.org/data/open-weight-models.csv JSON: https://aifordevs.org/data/open-weight-models.json - [GPU rental prices](https://aifordevs.org/data/gpu-prices.md): On-demand and spot prices per GPU-hour for 19 GPU types across Runpod, CoreWeave, Lambda, Crusoe, Nebius, Jarvislabs, and Replicate, read from each cloud's own pricing page. Checked November 10, 2026. CSV: https://aifordevs.org/data/gpu-prices.csv JSON: https://aifordevs.org/data/gpu-prices.json ## Articles - [Best LLM for coding: November 2026 benchmarks, compared](https://aifordevs.org/articles/best-llm-for-coding.md): The best LLM for coding as of November 2026, by situation: agents, value, large repos, local hardware. Dated scores and who ran each benchmark. - [Claude API pricing: caching, batch, and real bills](https://aifordevs.org/articles/claude-api-pricing.md): Claude API pricing for every current model as of November 8, 2026, with cache break-even math, batch stacking, tool fees, and a tested cost calculator. - [Gemini API pricing: free tier, caching, and real bills](https://aifordevs.org/articles/gemini-api-pricing.md): Gemini API pricing for every current model as of November 8, 2026: free versus paid, cache storage math, batch, grounding, thinking, and a tested calculator. - [LLM as a judge: biases, validation, and when to distrust it](https://aifordevs.org/articles/llm-as-a-judge.md): LLM as a judge means grading model output with a model. See what Zheng et al. measured, where bias enters, and how to validate a judge against human labels. - [LLM evaluation: build an eval suite and gate deploys in CI](https://aifordevs.org/articles/llm-evaluation.md): LLM evaluation, step by step: define failure modes, build a golden dataset, choose metrics, run an offline suite, compare to a baseline, and gate CI. - [LoRA fine tuning: QLoRA, r, alpha, and a tested PEFT script](https://aifordevs.org/articles/lora-fine-tuning.md): LoRA fine tuning from the paper to serving: r, alpha, QLoRA, dataset format, and a PEFT script run on CPU with real output, adapter size, and evals. - [Mixture of experts: how MoE works and what it costs](https://aifordevs.org/articles/mixture-of-experts.md): Mixture of experts LLMs load every expert but run only a few per token. Compare total and active parameters, and see what memory, batching, and routing cost. - [RAG vs fine tuning: which failures each one can fix](https://aifordevs.org/articles/rag-vs-fine-tuning.md): RAG vs fine tuning compared by failure mode: what each changes, who still sells fine tuning, dated costs worked in code, and when to combine them. - [What is a vector database? HNSW, IVF, and when to skip one](https://aifordevs.org/articles/what-is-a-vector-database.md): What is a vector database, how HNSW and IVF search work, recall measured on generated vectors, and when pgvector or no database is the right choice. - [What is an AI agent? The loop in code, and where it fails](https://aifordevs.org/articles/what-is-an-ai-agent.md): What is an AI agent? A tested agent loop in TypeScript, run offline against a scripted model, with traces of runaway loops, tool errors, and token growth. - [Context engineering: budget and order the context window](https://aifordevs.org/articles/context-engineering.md): Context engineering is choosing what a model reads on each call. Size each section, order it for prompt caching, trim inputs, and test every layout change. - [KV cache explained: what it stores and what it costs](https://aifordevs.org/articles/kv-cache-explained.md): A KV cache holds attention keys and values during LLM decode. Size one from config.json, see what concurrency costs, and how prompt caching reuses it. - [Speculative decoding: how drafts speed up LLM inference](https://aifordevs.org/articles/speculative-decoding.md): Speculative decoding has a cheap draft propose tokens the target model verifies in one pass. See the math, the costs, and what vLLM and SGLang support. - [vLLM vs SGLang, plus Ollama and llama.cpp compared](https://aifordevs.org/articles/vllm-sglang-llama-cpp.md): vLLM vs SGLang compared on prefix caching, hardware, and constrained decoding, plus Ollama and llama.cpp. Every default checked November 8, 2026. - [What is an MCP server? Build and test one in TypeScript](https://aifordevs.org/articles/build-an-mcp-server.md): What is an MCP server? Build a tested TypeScript one with a confirmed write tool, debug it with MCP Inspector, and apply the spec's security requirements. ## Topics - [Coding agents](https://aifordevs.org/topics/coding-agents.md): Terminal and editor agents that read your repository, run commands, and open pull requests. How they plan, what they can touch, and how to give them the context they need. - [Agents and frameworks](https://aifordevs.org/topics/agents.md): Loops that let a model call tools, keep state, and work toward a goal. Framework comparisons, orchestration patterns, and failure modes you will hit in production. - [MCP and agent protocols](https://aifordevs.org/topics/mcp.md): The protocols that connect models to tools and to each other. What an MCP server exposes, how clients discover it, and how to secure it. - [Inference and serving](https://aifordevs.org/topics/inference.md): What happens between a request and the last token. Engines, batching, the KV cache, quantization, and decoding tricks that change latency and cost. - [RAG and retrieval](https://aifordevs.org/topics/rag.md): Giving a model the right documents at the right time. Chunking, embeddings, hybrid search, and how to tell whether retrieval is helping. - [Model releases](https://aifordevs.org/topics/models.md): New models from frontier labs and open-weight releases, read for what changes for developers: context length, pricing, tool use, and license. - [APIs and pricing](https://aifordevs.org/topics/apis.md): The surface you actually code against. Price per million tokens, rate limits, structured outputs, tool calling, and the SDKs that wrap them. - [Evals and observability](https://aifordevs.org/topics/evals.md): Measuring whether a model or agent is good enough for your task, and seeing what it did when it was not. - [Fine-tuning and training](https://aifordevs.org/topics/fine-tuning.md): When prompting is not enough. Parameter-efficient fine-tuning, preference training, and the data work that decides the result. - [Prompting and context](https://aifordevs.org/topics/context.md): What goes into the context window and in what order. System prompts, examples, retrieved data, tool results, and memory. ## Reference - [News](https://aifordevs.org/news.md): Dated briefs on model releases, APIs, tooling, infrastructure, and research. - [Glossary](https://aifordevs.org/glossary.md): Definitions of LLM and AI engineering terms. - [Platform directory](https://aifordevs.org/platforms.md): Model APIs, inference engines, agent frameworks, gateways, observability tools, and vector databases. - [Editorial standards](https://aifordevs.org/about.md): How we source, date, test, and correct. - [Reuse and attribution](https://aifordevs.org/reuse.md): What you can reuse, and the credit it needs. - [Full text of the site](https://aifordevs.org/llms-full.txt): Every article, the glossary, the platform directory, and the news briefs in one file. - [RSS feed](https://aifordevs.org/feed.xml) ## Glossary terms - [A2A](https://aifordevs.org/glossary/a2a.md) - [Agent](https://aifordevs.org/glossary/agent.md) - [Agent loop](https://aifordevs.org/glossary/agent-loop.md) - [Agentic AI](https://aifordevs.org/glossary/agentic-ai.md) - [AI gateway](https://aifordevs.org/glossary/ai-gateway.md) - [Attention](https://aifordevs.org/glossary/attention.md) - [Batch API](https://aifordevs.org/glossary/batch-api.md) - [Chunking](https://aifordevs.org/glossary/chunking.md) - [Constrained decoding](https://aifordevs.org/glossary/constrained-decoding.md) - [Context engineering](https://aifordevs.org/glossary/context-engineering.md) - [Context window](https://aifordevs.org/glossary/context-window.md) - [Continuous batching](https://aifordevs.org/glossary/continuous-batching.md) - [Distillation](https://aifordevs.org/glossary/distillation.md) - [Embedding](https://aifordevs.org/glossary/embedding.md) - [Eval](https://aifordevs.org/glossary/eval.md) - [Fine-tuning](https://aifordevs.org/glossary/fine-tuning.md) - [GGUF](https://aifordevs.org/glossary/gguf.md) - [Golden dataset](https://aifordevs.org/glossary/golden-dataset.md) - [Grouped-query attention](https://aifordevs.org/glossary/grouped-query-attention.md) - [Guardrails](https://aifordevs.org/glossary/guardrails.md) - [Hallucination](https://aifordevs.org/glossary/hallucination.md) - [HNSW](https://aifordevs.org/glossary/hnsw.md) - [Hybrid search](https://aifordevs.org/glossary/hybrid-search.md) - [Inference](https://aifordevs.org/glossary/inference.md) - [KV cache](https://aifordevs.org/glossary/kv-cache.md) - [LLM-as-a-judge](https://aifordevs.org/glossary/llm-as-a-judge.md) - [LoRA](https://aifordevs.org/glossary/lora.md) - [MCP](https://aifordevs.org/glossary/mcp.md) - [MCP server](https://aifordevs.org/glossary/mcp-server.md) - [Mixture of experts](https://aifordevs.org/glossary/mixture-of-experts.md) - [PagedAttention](https://aifordevs.org/glossary/paged-attention.md) - [Prefill and decode](https://aifordevs.org/glossary/prefill-and-decode.md) - [Prefix caching](https://aifordevs.org/glossary/prefix-caching.md) - [Prompt caching](https://aifordevs.org/glossary/prompt-caching.md) - [QLoRA](https://aifordevs.org/glossary/qlora.md) - [Quantization](https://aifordevs.org/glossary/quantization.md) - [RAG](https://aifordevs.org/glossary/rag.md) - [Reasoning model](https://aifordevs.org/glossary/reasoning-model.md) - [Reranking](https://aifordevs.org/glossary/reranking.md) - [RLHF](https://aifordevs.org/glossary/rlhf.md) - [Small language model](https://aifordevs.org/glossary/small-language-model.md) - [Speculative decoding](https://aifordevs.org/glossary/speculative-decoding.md) - [Structured outputs](https://aifordevs.org/glossary/structured-outputs.md) - [SWE-bench](https://aifordevs.org/glossary/swe-bench.md) - [System prompt](https://aifordevs.org/glossary/system-prompt.md) - [Temperature](https://aifordevs.org/glossary/temperature.md) - [Throughput](https://aifordevs.org/glossary/throughput.md) - [Token](https://aifordevs.org/glossary/token.md) - [Tokenizer](https://aifordevs.org/glossary/tokenizer.md) - [Tool calling](https://aifordevs.org/glossary/tool-calling.md) - [Top-p](https://aifordevs.org/glossary/top-p.md) - [Transformer](https://aifordevs.org/glossary/transformer.md) - [TTFT](https://aifordevs.org/glossary/ttft.md) - [Vector database](https://aifordevs.org/glossary/vector-database.md) ## Platforms - [AI SDK](https://aifordevs.org/platforms/vercel-ai-sdk.md) - [Aider](https://aifordevs.org/platforms/aider.md) - [Amazon Bedrock](https://aifordevs.org/platforms/amazon-bedrock.md) - [Baseten](https://aifordevs.org/platforms/baseten.md) - [Bifrost](https://aifordevs.org/platforms/bifrost.md) - [Chroma](https://aifordevs.org/platforms/chroma.md) - [Claude API](https://aifordevs.org/platforms/anthropic-api.md) - [Claude Code](https://aifordevs.org/platforms/claude-code.md) - [Cline](https://aifordevs.org/platforms/cline.md) - [Cloudflare AI Gateway](https://aifordevs.org/platforms/cloudflare-ai-gateway.md) - [Codex](https://aifordevs.org/platforms/codex.md) - [CrewAI](https://aifordevs.org/platforms/crewai.md) - [Cursor](https://aifordevs.org/platforms/cursor.md) - [DeepSeek API](https://aifordevs.org/platforms/deepseek-api.md) - [Fireworks AI](https://aifordevs.org/platforms/fireworks-ai.md) - [Gemini API](https://aifordevs.org/platforms/gemini-api.md) - [Gemini CLI](https://aifordevs.org/platforms/gemini-cli.md) - [GitHub Copilot](https://aifordevs.org/platforms/github-copilot.md) - [Groq](https://aifordevs.org/platforms/groq.md) - [Hugging Face](https://aifordevs.org/platforms/hugging-face.md) - [LangChain](https://aifordevs.org/platforms/langchain.md) - [Langfuse](https://aifordevs.org/platforms/langfuse.md) - [LangGraph](https://aifordevs.org/platforms/langgraph.md) - [LiteLLM](https://aifordevs.org/platforms/litellm.md) - [llama.cpp](https://aifordevs.org/platforms/llama-cpp.md) - [LlamaIndex](https://aifordevs.org/platforms/llamaindex.md) - [Maxim AI](https://aifordevs.org/platforms/maxim-ai.md) - [Milvus](https://aifordevs.org/platforms/milvus.md) - [Mistral AI](https://aifordevs.org/platforms/mistral.md) - [Modal](https://aifordevs.org/platforms/modal.md) - [Ollama](https://aifordevs.org/platforms/ollama.md) - [OpenAI Agents SDK](https://aifordevs.org/platforms/openai-agents-sdk.md) - [OpenAI API](https://aifordevs.org/platforms/openai-api.md) - [OpenRouter](https://aifordevs.org/platforms/openrouter.md) - [pgvector](https://aifordevs.org/platforms/pgvector.md) - [Phoenix](https://aifordevs.org/platforms/arize-phoenix.md) - [Pinecone](https://aifordevs.org/platforms/pinecone.md) - [Pydantic AI](https://aifordevs.org/platforms/pydantic-ai.md) - [Qdrant](https://aifordevs.org/platforms/qdrant.md) - [Replicate](https://aifordevs.org/platforms/replicate.md) - [SGLang](https://aifordevs.org/platforms/sglang.md) - [TensorRT-LLM](https://aifordevs.org/platforms/tensorrt-llm.md) - [Together AI](https://aifordevs.org/platforms/together-ai.md) - [Vertex AI](https://aifordevs.org/platforms/vertex-ai.md) - [vLLM](https://aifordevs.org/platforms/vllm.md) - [Weaviate](https://aifordevs.org/platforms/weaviate.md) - [xAI API](https://aifordevs.org/platforms/xai-api.md)