Guides & pricing notes
Practical guides for developers who want frontier models for less.
Track AI API Spend: Usage Page and CSV Export Guide
How to read the Usage page, filter by product and status, export CSV, and build habits that keep your LLM API bill predictable.
Best LLM for coding in 2026: Claude vs GPT vs DeepSeek vs Grok, with prices
A practical comparison of Claude Opus and Sonnet, GPT-6, DeepSeek V4, Grok and Kimi for coding and agents, with real per-token prices on apillms.
Text to speech API: turn text into natural voice audio
How to use apillms Voice Studio to turn text into speech: picking a voice, the character counter, cost per 1,000 characters, and the media library.
Cheap Claude Code API: run Claude Code on a lower-cost key in 2 minutes
Step-by-step guide to using Claude Code with apillms: cheaper Claude Opus and Sonnet, prompt caching included, pay-as-you-go from $5. Works on macOS, Linux and Windows.
Claude API pricing per token: Opus, Sonnet and Haiku costs explained
Current Claude API prices per 1M tokens for Opus 5.5, Opus 5, Sonnet 5 and Haiku 4.5, worked cost examples, and a comparison with OpenRouter.
OpenRouter alternative: cheaper Claude and GPT API, prices compared
Looking for an OpenRouter alternative? Compare apillms and OpenRouter prices for Claude, GPT, Grok, DeepSeek and Kimi, and see when switching saves money.
Prompt caching explained: how cache reads cut LLM API costs
How prompt caching works for Claude, GPT and DeepSeek, how it is billed, and practical rules to structure prompts so repeated context costs a fraction of normal input.
AI video generation API: settings, cost and wait times
How to generate AI video in the apillms Video Studio: model, resolution, duration, audio, cost per clip, refunds on failed jobs, and wait times.
AI image generation API: Nano Banana, Flux and Seedream in one place
How to use apillms Image studio and API to generate images: picking a model, aspect ratio, reference images, cost, and the media library.
LLM playground: compare Claude, GPT and DeepSeek before you code
Try Claude, GPT, DeepSeek and other models in the apillms Playground, tune settings, then export a working code snippet with one click.
Anthropic SDK custom base URL: point Python and Node at any Claude API
Call Claude, GPT, DeepSeek and Kimi models through the official Anthropic SDK by pointing it at the apillms base URL. Python and Node examples.
Node.js LLM API quickstart: Claude, GPT and DeepSeek with one key
Call Claude, GPT and DeepSeek from Node.js with the openai npm package and one apillms key. Includes model switching and error handling.
Python LLM API quickstart: Claude and GPT with the OpenAI SDK
Call Claude and GPT models from Python using the standard OpenAI SDK and one apillms key. Code examples, model switching, async, and cost tracking.
Open WebUI, Cherry Studio and Chatbox: add a custom OpenAI API
Connect Open WebUI, Cherry Studio or Chatbox to apillms with one OpenAI-compatible base URL and key. Setup steps, models, and costs.
MCP server for chat, image, video and voice tools in Claude Code and Cursor
Connect any MCP-capable agent to apillms and call chat, image, video and voice models as tools. Setup command, tool list, costs, and example prompts.
Blender MCP with Claude Code: control Blender from an AI agent
Set up the Blender MCP server with one command, drive Blender from Claude Code, and keep agent-turn costs under control.
n8n AI workflow with an OpenAI-compatible API: credentials step by step
Connect n8n to apillms with an OpenAI credential and a custom base URL, run a chat model node, and track cost on the Usage page.
OpenCode custom provider: opencode.json setup for Claude and GPT
Step-by-step guide to wiring OpenCode's terminal agent to apillms using a custom OpenAI-compatible provider, with model ids and cost tips.
Cline and Continue custom API: use Claude, GPT and DeepSeek in VS Code
Step-by-step guide to configure Cline and Continue in VS Code with apillms as an OpenAI-compatible provider. Test in Playground, then start coding.
Cursor custom OpenAI base URL: use your own API key
Point Cursor at apillms's OpenAI-compatible endpoint, paste your key, and pick from Claude, GPT, DeepSeek and Grok models.
Codex CLI config.toml: use a custom provider and base URL
Step-by-step guide to point Codex CLI at apillms using config.toml, with the one-line installer and gpt-6-astra as your model.
Claude Desktop custom API: connect a base URL and key
Step-by-step guide to point Claude Desktop at apillms: find your base URL and key, pick a model, test the connection, and troubleshoot issues.
VS Code chat custom endpoint: any model without Copilot
Set up VS Code Chat with Claude, GPT, Grok, DeepSeek or Kimi using one command and a custom endpoint — no GitHub or Copilot account required.
Claude Code setup with ANTHROPIC_BASE_URL: step by step
Step-by-step guide to connect Claude Code to apillms: sign up, grab an API key, set env variables, pick a model, and check usage.
Claude Code token usage: why it burns tokens and how to cut the bill
Claude Code resends your whole context every turn. Here's why that's expensive, what cache reads actually save, and how /clear and /compact help.