Model APIs
Anthropic API Model List: Exact IDs and How to Find Current Models
Find Anthropic model IDs, query the live Models API, and check lifecycle and capabilities without mistaking a catalog snapshot for a current inventory.
AI model and infrastructure insights
Insights, page 2 of 95
Model APIs
Which ChatGPT Model Is Best for Research? (2026 Guide)
For multi-source research, start with ChatGPT Deep Research. Learn when ChatGPT Search or GPT-6 Pro may fit better, plus how to choose an API model by workload, tool support, and price.
How-to guides
How to Use Grok 3: Current Access and API Guide
Grok 3 has been retired from xAI’s API. Learn what happens if you call its old model ID, how to use Grok on the web or mobile, and how to make a first API request with a current model.
How-to guides
How to Use DALL·E 3 in ChatGPT: Current Image Guide
Create and refine images with ChatGPT Images, understand what the documented workflow does—and doesn’t—establish about DALL·E 3, and see how image generation differs from using OpenAI’s API.
Model APIs
Grok 4 Model: API Status, Capabilities, Pricing, and What to Use Instead
The original Grok 4 API model has been retired. Learn what happens to grok-4-0709 requests, how to evaluate current models, and which pricing details still need confirmation.
Model APIs
GPT-OSS-20B Model Card: Capabilities, Evidence, and API Availability
A source-based guide to GPT-OSS-20B’s model card, specifications, safety considerations, workload fit, and hosted API availability.
Model APIs
OpenAI ChatGPT Agents: ChatGPT Work, Workspace Agents, and API Options
Learn what happened to ChatGPT Agent, how Workspace Agents differ, and which OpenAI API route to evaluate for a production agent.
How-to guides
How to Switch Back to GPT-4: ChatGPT and API Status
GPT-4 and GPT-4o are different models. Find out why original GPT-4 can no longer be selected in ChatGPT or used through the OpenAI API.
Image generation
Gemini 2.5 Flash Image API: Model ID and Python Integration
Find the Gemini API model ID, install the Python SDK, configure a key, and follow a dated Google example for sending an image request and handling the result.
Video generation
Veo 3 Fast Price: Historical Rate and Current Veo 3.1 Fast API Access
Google announced a historical Veo 3 Fast Gemini API rate of $0.15 per second. For current Veo 3.1 Fast on Gemini Enterprise Agent Platform, Google lists fixed quota and Provisioned Throughput—not pay-as-you-go—and the model listing does not give a per-video dollar price.
How-to guides
How to Use ChatGPT Agents: ChatGPT Work, Workspace Agents, and the API
Learn when to use ChatGPT Work, when a workspace agent fits a team workflow, and how to start a separate Python agent project with the OpenAI Agents SDK.
Pricing and plans
OpenAI GPT-4o API Pricing: Rates and Cost Examples
As of November 12, 2026, GPT-4o is listed at $2.50 per 1M standard input tokens and $10 per 1M output tokens. See qualifying cached-input pricing, Batch rates, and example budgets.
Pricing and plans
Grok 4 Fast API Pricing: Retirement and Current Redirect Rates
Grok 4 Fast was retired from the xAI API on May 15, 2026. See what happens to requests using its old model IDs, the Grok 4.3 rates they are billed at, and how this differs from Grok 4.7 Fast.
Model APIs
Kimi K2.5 API: Retirement Status and Migration Steps
Moonshot retired Kimi K2.5 from its API platform on August 31, 2026. Find out what that means for existing integrations and how to choose and test a supported model before migrating.
Model APIs
ChatGPT Agent Access: Where to Find Work and API Options
The original ChatGPT agent is no longer available. Find the Work option in ChatGPT, check cloud-browser eligibility, and compare current OpenAI API routes for agent workflows.
Model APIs
Anthropic API: Setup, First Request, and Production Checks
Learn how to call Anthropic’s own Claude API with Python, create and configure an API key, and distinguish direct Anthropic access from compatible third-party APIs.
Pricing and plans
Gemini 2.5 API Price: Reported Rates, Cost Examples & Availability
See reported Gemini 2.5 Pro, Flash, and Flash-Lite API prices per million tokens, calculate a text-token budget, and understand pricing and access caveats.
Model APIs
GPT-5 Coding Benchmarks: Scores, Caveats, and API Status
OpenAI reported GPT-5 scores of 74.9% on SWE-bench Verified and 88% on Aider Polyglot. Here’s what those results mean—and why GPT-5’s current API status matters.
Image generation
Midjourney Video Prompts: A Practical Guide and API Reality Check
Learn how to write motion-focused Midjourney video prompts, use a starting image, choose motion controls, and assess whether Midjourney fits a production API workflow.
Model comparisons
ChatGPT Team vs Plus: Differences, Pricing, and Which to Choose
Compare ChatGPT Plus with ChatGPT Business, formerly Team: U.S. prices, workspace and administration features, model access, and separate API billing.
Model APIs
OpenAI Model Names: Find and Choose an API Model ID
Learn the difference between an OpenAI model name and API model ID, retrieve IDs available to your API, and compare documented flagship options by workload.
Model APIs
GLM 5.2 API Key: Get One and Make Your First Request
Learn where to create a Z.ai Standard API key for GLM-5.2, how to send a minimal chat-completions request, and what to check if it fails.
Model APIs
Z.ai GLM-4.6 API: Setup, Pricing, and Production Checks
Connect to GLM-4.6 through Z.ai’s standard API with a cURL example. Check the model ID, authentication, token limits, listed prices, and what remains to confirm before production.
How-to guides
How to Use DALL·E in ChatGPT: Create and Edit Images
Learn how to create and revise images in ChatGPT, write a useful prompt, and understand how ChatGPT image generation differs from production API use.