Featured
Claude API Key: How to Get, Configure, and Use It
Set up a Claude API key on OurToken. Copy the exact Messages API endpoint, model ID, and Bearer auth, then test with cURL and Python.
O
OurToken Team·OurToken Blog
AI APIで構築するための実践メモ
OpenAI、Claude、Geminiなどにまたがるモデル選定、API価格、ルーティング、本番信頼性についてのわかりやすいガイド。
Article
Claude Sonnet 5 API: Endpoint, Model ID, and Python Example
Set up the Claude Sonnet 5 API on OurToken. Copy the exact Messages endpoint, model ID, and pricing, then run a cURL test and call Sonnet 5 from Python.
O
OurToken Team·
Article
Agentic RAG: Build Retrieval Loops That Decide
Build an agentic RAG loop that decides when to retrieve, which tools to use, whether evidence is sufficient, and when to stop. Includes Python checks.
O
OurToken Team·
Article
AI Agent Guardrails: Input, Tool, and Output Checks
Build AI agent guardrails with input, tool, and output checks. Learn policy schemas, Python middleware, safe tool calls, review, tests, and rollout.
O
OurToken Team·
Article
AI Agent Memory Architecture: Build 3 Memory Layers
Learn AI agent memory architecture with working, vector, and summary memory. Cover storage schemas, embedding retrieval, context budgets, expiry, and evaluation.
O
OurToken Team·
Article
OpenAI API Migration Guide for Multi-Model Endpoints
Migrate OpenAI API clients to an OpenAI-compatible multi-model endpoint with adapters, routing, shadow traffic, fallback, rollback, and cost checks.
O
OurToken Team·
Article
MCP Server Authentication: API Keys, OAuth, TLS, and Tool-Level Authorization
Learn MCP server authentication for local and remote deployments: protect stdio and Streamable HTTP transports, choose API keys or OAuth, enforce tool-level authorization, and connect the model layer safely.
O
OurToken Team·
Article
OpenAI API Rate Limit: Fix 429 Errors with Retry, Backoff, and Model Routing
Learn how to handle OpenAI API rate limits in production: distinguish 429 causes, honor Retry-After, add exponential backoff with jitter, control concurrency, and route across verified models.
O
OurToken Team·
Article
MCP Server Tutorial: Build a Custom Tool with Python and an OpenAI-Compatible API
Follow this MCP server tutorial to build a Python tool that exposes internal ticket data, connect it to an AI client, and use an OpenAI-compatible API for model responses.
O
OurToken Team·
Article
OpenCode Model Not Found: Fix Provider, Model ID, and API Configuration Errors
Fix OpenCode model not found errors by separating provider IDs from model IDs, checking Base URL paths, validating API keys, and debugging 401, 404, and custom-provider configuration issues.
O
OurToken Team·
Article
OpenAI Batch API: Cut Async LLM Costs 50% with Python and JSONL
Learn how the OpenAI Batch API works in 2026: JSONL input files, Python upload and retrieval, 50% cost savings, 24-hour completion, status handling, and when to use batch vs real-time APIs
O
OurToken Team·
Article
OpenCode vs Claude Code: Open Source Flexibility, MCP, Costs, and Custom API Endpoints
Compare OpenCode vs Claude Code in 2026 across open source flexibility, MCP support, custom API endpoints, model routing, token costs, and private-code controls.
O
OurToken Team·
Article
Gemini API Key Setup: AI Studio, Auth Keys, and the OpenAI-Compatible Endpoint (2026)
Step-by-step Gemini API key setup for 2026: get a key in Google AI Studio, migrate from standard keys to auth keys before the September deadline, store it securely, and call Gemini through the OpenAI-compatible endpoint.
O
OurToken Team·
Article
Embedding Model Comparison: text-embedding-3 vs Voyage 4 vs GLM — Dimensions, Cost, and Recall
Compare OpenAI text-embedding-3, Voyage 4, and GLM embedding models on dimensions, pricing, context length, and recall. Pick the right embedding model for RAG and search in 2026.
O
OurToken Team·
Article
Aider OpenAI-Compatible API Setup: Base URL, API Key, and Model Configuration
Configure Aider with an OpenAI-compatible API provider on OurToken. Learn the correct base URL, API key settings, model prefix, .aider.conf.yml, and model_not_found troubleshooting.
O
OurToken Team·
Article
Vercel AI SDK Model Fallback: Multi-Provider Retry with an OpenAI-Compatible API
Build resilient AI apps with Vercel AI SDK model fallback. Learn provider chains, retry strategies, cost-aware routing, and multi-model fallback using one OpenAI-compatible API endpoint.
O
OurToken Team·
Article
Claude Opus 4.7 API Key Setup: Endpoint, Model ID, Pricing, and Python Example
Set up a Claude Opus 4.7 API key with OurToken. Copy the exact Messages API endpoint, model ID, cURL request, Python example, pricing table with 60% savings, and troubleshooting checklist.
O
OurToken Team·
Article
Streaming Chat Completion SSE: Build Reliable Real-Time AI Responses
Learn how streaming chat completion SSE works with an OpenAI-compatible API. Includes cURL, JavaScript, Python, event parsing, reconnects, usage tracking, and production patterns.
O
OurToken Team·
Article
Tencent HY3 API Setup: Endpoint, Model ID, Pricing, and Python Example
Set up a Tencent HY3 API key on OurToken. Copy the exact OpenAI-compatible endpoint, model ID hy3, cURL request, Python example, pricing table with 60% savings, and troubleshooting checklist.
O
OurToken Team·
Article
Claude Opus 4.8 API Key Setup: Endpoint, Model ID, Pricing, and Python Example
Set up a Claude Opus 4.8 API key with OurToken. Copy the exact Messages API endpoint, model ID, cURL request, Python example, pricing table, and troubleshooting checklist.
O
OurToken Team·
Article
OpenCode Custom Provider Setup: Base URL, API Key, and Model Configuration
Learn how to configure an OpenCode custom provider with a compatible API base URL, API key, and model ID. Includes JSON configuration, environment variables, testing, and troubleshooting.
O
OurToken Team·
Article
RAG Evaluation Metrics: Faithfulness, Relevance, Recall, and RAGAS
Learn the core RAG evaluation metrics: faithfulness, answer relevancy, context precision, and context recall. Includes Python examples, RAGAS concepts, multi-model API tests, and token cost tracking.
O
OurToken Team·
Article
Vercel AI SDK OpenAI-Compatible API: Custom Provider Setup
Set up a Vercel AI SDK OpenAI-compatible API provider with custom baseURL, API key, model aliases, streaming, fallback routing, and OurToken model examples.
O
OurToken Team·
Article
DeepSeek V4 API Pricing: Flash vs Pro Cost Calculator
Compare DeepSeek V4 API pricing for Flash and Pro, including token costs, cached input pricing, Python cost calculator code, and API key setup notes.
O
OurToken Team·
Article
Qwen API Key Setup: OpenAI-Compatible Endpoint and Python Example
Learn how to get a Qwen API key, copy the endpoint and model ID, run cURL and Python examples, compare Qwen API pricing, and avoid common setup errors.
O
OurToken Team·
Article
OpenAI Prompt Caching API: Reduce LLM Input Costs with Cached Tokens
Learn how the OpenAI Prompt Caching API works with cached tokens, cache writes, prompt_cache_key, and GPT-5.6 breakpoints. Includes Python examples, cost math, and OurToken setup notes.
O
OurToken Team·
Article
OpenAI Structured Outputs JSON Schema: Python Guide
Learn how to use OpenAI Structured Outputs with JSON Schema in Python. See strict schema examples, validation tips, error handling, and OurToken-compatible API setup.
O
OurToken Team·
Article
MiniMax M3 API Key Setup: Endpoint, Model ID, and Python Example
Set up a MiniMax M3 API key with OurToken's OpenAI-compatible endpoint. Copy the exact model ID, test cURL, and call MiniMax M3 from Python.
O
OurToken Team·
Article
DeepSeek V4 vs GLM 5.2: Coding, Long-Context, and Cost Compared
DeepSeek V4 Pro and Flash vs GLM 5.2 on OurToken: compare endpoint, model ID, pricing, 1M context, coding and long-text workflows, and pick the right route.
O
OurToken Team·
Article
Claude Sonnet 4.6 API Key Setup: Endpoint, Model ID, and Python Example
Set up a Claude Sonnet 4.6 API key with OurToken's Messages API endpoint. Copy the exact model ID, test a cURL request, and call Claude Sonnet 4.6 from Python.
O
OurToken Team·
Article
GLM 5.2 API Key Setup: OpenAI-Compatible Endpoint, Model ID, and Python Example
Set up a GLM 5.2 API key with OurToken's OpenAI-compatible endpoint. Copy the exact model ID, test cURL, and call GLM 5.2 from Python.
O
OurToken Team·
Article
DeepSeek V4 API Key Setup: Endpoint, Model ID, and Python Example
Set up a DeepSeek V4 API key with OurToken's OpenAI-compatible endpoint. Use the deepseek-v4-pro model ID, test cURL, and call the API from Python.
O
OurToken Team·
Article
Kimi K3 API Key Setup: Endpoint, Model ID, and Python
Set up a Kimi K3 API key with OurToken's OpenAI-compatible endpoint. Get the exact model ID, cURL and Python examples, pricing, and production checks.
O
OurToken Team·
Article
GPT-5.6 API Key Setup: First Responses API Request
Learn how to get a GPT-5.6 API key, configure the Responses API endpoint, and make your first Sol, Terra, or Luna request with cURL and Python.
O
OurToken Team·
Article
GPT-5.6 API Cost Calculator (JS): Sol vs Terra vs Luna
Use a JavaScript GPT-5.6 API cost calculator for Sol, Terra, and Luna. Compare Standard OpenAI and OurToken input, cache, and output rates.
O
OurToken Team·
Article
Cline OpenAI Compatible API: Custom Base URL Setup Guide
Configure a Cline OpenAI-compatible API with a custom base URL, API key, model ID, capability settings, verification steps, and troubleshooting.
O
OurToken Team·
Article
Claude Code API Pricing vs Subscription: 2026 Cost Guide
Compare Claude Code API pricing with Pro, Max 5x, and Max 20x subscriptions. Use real token-cost examples to choose the right billing model.
O
OurToken Team·
Article
Codex CLI Custom API: How to Use an OpenAI-Compatible Endpoint for Multi-Model Coding
Configure Codex CLI with a custom OpenAI-compatible API endpoint using config.toml and auth.json, then route coding work across multiple models safely.
O
OurToken Team·
Article
OpenAI-Compatible Tool Calling: Make Function Calls Reliable Across Models
Learn how openai compatible tool calling works across GPT, Claude, and GLM, with schema design, fallback patterns, error handling, and production-ready code.
O
OurToken Team·
Article
OpenAI-Compatible Prompt Caching: Reduce LLM Costs Across GPT and Claude
Learn how openai compatible prompt caching works in practice across OpenAI and Claude, with provider-aware architecture, accurate code examples, and cache-hit optimization tips.
O
OurToken Team·
Article
Structured Outputs JSON Schema: How to Get Reliable LLM Output Without Regex Fixes
Learn when to use Structured Outputs JSON Schema instead of JSON mode or function calling, with production patterns, code examples, and cross-provider pitfalls.
O
OurToken Team·
Article
Responses API Migration: A Practical Guide to Moving from Chat Completions and Assistants
Planning a responses api migration? Learn the safest path from Chat Completions and Assistants to Responses API, with code examples, architecture patterns, and rollback advice.
O
OurToken Team·
Article
LLM Model Routing: Cut AI Costs 60% Without Losing Quality
Learn how LLM model routing sends simple queries to cheap models and complex ones to strong models, with production code, cost analysis, and fallback architecture.
O
OurToken Team·
Article
OpenAI Compatible API for RAG: Build Retrieval-Augmented Generation Without Vendor Lock-In
Build a RAG pipeline on an OpenAI Compatible API: route embeddings, reranking, and synthesis to different models without rewriting code. Cut inference cost with per-stage model routing.
O
OurToken Team·
Article
AI Gateway Explained: Architecture, Benefits, and How to Build One in 2026
Learn what an AI Gateway is, how it works, why developers use AI Gateways to reduce costs and manage multiple LLM providers, and how to build an OpenAI-compatible AI Gateway in 2026.
O
OurToken Team·
Article
Looking for a Claude Code Alternative? Here's How Developers Are Building More Flexible AI Coding Workflows in 2026
Searching for a Claude Code alternative? Learn how developers combine GPT-5.5, Claude, GLM-5.2, DeepSeek, and other models to build flexible AI coding workflows with better cost control and model choice.
O
OurToken Team·
Article
MCP Servers Explained: The Missing Layer in Modern AI Agent Architecture
Learn what MCP (Model Context Protocol) servers are, how they work, and why they're becoming essential infrastructure for AI agents, Claude, OpenAI-compatible systems, and modern developer workflows.
O
OurToken Team·
Article
What Is an OpenAI-Compatible API? And Why More Developers Are Switching in 2026
Learn what an OpenAI-compatible API is, why developers are adopting OpenAI-compatible infrastructure, and how to switch AI providers without rewriting your application.
O
OurToken Team·
Article
Best AI API for Startups in 2026: How Smart Teams Cut Costs Without Limiting Growth
Looking for the best AI API for startups? Compare OpenAI, Claude, DeepSeek, GLM, and MiniMax pricing, performance, and scalability. Learn how startups reduce AI infrastructure costs while keeping access to the latest AI models.
O
OurToken Team·
Article
Why Most AI Agents Fail After 30 Minutes (And How Memory Fixes It)
Many AI agents perform well at first but break down during long workflows. Learn why memory systems have become one of the most important components in modern AI agent architecture.
O
OurToken Team·
Article
Can GLM-5.2 Beat GPT-5.5 for Coding? The 1M Context Window Test
GLM-5.2 introduces a 1 million token context window and lower API pricing than GPT-5.5. Discover how GLM-5.2 compares for coding, AI agents, repository analysis, and long-context workflows.
O
OurToken Team·
Article
Best AI Model for Coding in 2026: Claude Fable 5 vs GPT-5.5 vs DeepSeek V4 Pro
Compare Claude Fable 5, GPT-5.5, and DeepSeek V4 Pro for coding, software engineering, and AI coding assistants. Discover which AI model is best for developers in 2026.
O
OurToken Team·
Article
Claude Fable 5 Pricing: Anthropic vs OurToken Cost Comparison (2026)
Compare Claude Fable 5 pricing between Anthropic and OurToken. Learn how developers can save up to 60% on Claude Fable 5 API costs while using an OpenAI-compatible API.
O
OurToken Team·
Article
Best AI API for Startups in 2026: How to Reduce Costs Without Sacrificing Performance
Discover the best AI API options for startups in 2026. Compare cost, performance, and scalability while learning how to access multiple AI models through a single API.
O
OurToken Team·
Article
AI API Pricing Comparison 2026: GPT-5.5 vs Claude Opus 4.8 vs DeepSeek V4 vs GLM 5.1
Compare GPT-5.5, Claude Opus 4.8, DeepSeek V4, and GLM 5.1 pricing in 2026. Learn how developers reduce AI costs while choosing the best model for their applications.
O
OurToken Team·
Article
AI Agent API: How Developers Are Building Autonomous Applications in 2026
Learn how developers use AI Agent APIs to build autonomous workflows, coding assistants, and business automation systems. Discover the best approach for AI agent development in 2026.
O
OurToken Team·
Article
OpenAI API vs Claude API: Which Is Better for Developers in 2026?
Compare OpenAI API and Claude API for coding, AI agents, SaaS products, and business applications. Learn which AI API is best for developers in 2026.
O
OurToken Team·
Article
Best AI API for Startups in 2026: How to Build Faster Without Managing Multiple Providers
Looking for the best AI API for startups? Learn how developers use OpenAI, Claude, and Gemini through one API to build AI products faster and simplify infrastructure.
O
OurToken Team·
Article
GPT API Pricing Too Expensive? Save Up to 80% Without Changing Your Code
Reduce GPT and Claude API costs by up to 80%. Compare AI model pricing, monitor usage, and access leading OpenAI and Anthropic models through a unified platform.
O
OurToken Team·