Model APIs
DeepSeek Model List: API IDs, Capabilities, and Prices
Compare the two models listed for DeepSeek’s own API, their documented capabilities and token prices, and how to verify availability with GET /models.
AI model and infrastructure insights
Insights, page 18 of 95
Model APIs
DeepSeek 0528: Model Identity, Benchmarks, and API Selection
Learn what DeepSeek-R1-0528 refers to, how its published benchmark results compare with the earlier R1, and what to verify before using it through a production API.
Model APIs
Gemini 3.0 How to Use It: App Steps and a Production API Example
Learn how to use Gemini in the app and call a currently documented Gemini model through Google’s API. Find out why the original Gemini 3 Pro API preview is no longer available and see a runnable Python example.
Coding agents
Copilot CLI Models: How to Choose, Switch, and Check API Access
See how to list and select models in GitHub Copilot CLI, choose one for your task, troubleshoot models missing from the CLI, and distinguish Copilot model access from production API access.
Model APIs
MiniMax-M2 5 Parameters: M2 vs. M2.5 and API Settings
“MiniMax-M2 5 parameters” could mean M2’s model size, five API settings, or the separate M2.5 model. Here’s what the M2 repository says—and what remains unverified for production API use.
Coding agents
How to Install Codex CLI on Linux
Install OpenAI Codex CLI on Linux with the official standalone installer, then launch it in a project, sign in, and begin a task. Learn when npm or Linux binaries may be alternatives—and why an app’s production API integration is a separate concern.
Video generation
Veo API Key: How to Create a Key and Generate Video
Learn how to create a Gemini API key, secure it, and check current video model availability and pricing.
Audio and speech
Qwen TTS Model: Voices, API Options, Pricing, and Production Fit
Compare documented Qwen TTS models, supported languages and voices, API paths, and published character-based pricing before choosing a production fit.
Model APIs
Who Makes Kimi K2? Moonshot AI and API Access
Kimi K2 is developed by Moonshot AI. Learn how to distinguish the model maker from an API provider and what to verify before considering an API for production.
Coding agents
What Are Skills in Claude Code? How They Work and API Support
Claude Code skills are reusable workflows built around SKILL.md files. Learn where to put one, how to invoke it, when to use it, and what changes when using skills through a production API.
Model APIs
Anthropic API Rates: Claude Model Pricing and a Production Call
See Anthropic’s listed Claude API rates per million tokens, how to estimate a request’s cost, and a minimal Messages API call you can adapt for production.
Model APIs
Qwen Documentation: Official Guides, API Docs, and Model Selection
Find Qwen documentation, distinguish hosted Model Studio APIs from self-hosting, and shortlist models by task before checking current model and regional support.
Model APIs
DeepSeek R1 Parameters: Model Size, Generation Settings, and API Status
DeepSeek-R1 has 671B total parameters and 37B activated per token in the published V3 architecture specification. Learn how that differs from API generation settings—and what to use for production requests now.
Video generation
Veo 3 API Key: Choose the Right Google Credential and Make a First Request
Looking for a Veo 3 API key? See which Gemini API preview models were retired, how Agent Platform credentials differ, and what to check before generating a Veo 3.1 video.
Model APIs
Qwen Code Agent: Choose the Tool, Model, and API Route
Understand the difference between Qwen Code, Qwen-Coder models, and Qwen-Agent, then assess a production API setup, compatibility, and region-specific cost.
Pricing and plans
Is DeepSeek V3.2 Free? Chat Access, API Pricing & Costs
Find out what is free—and what is not—with DeepSeek V3.2. See app access, official API availability, OpenRouter token rates, and sample production budgets.
Model APIs
DeepSeek-V3.2 on Ollama: Availability, Variants, and API Options
The DeepSeek-V3.2 Ollama listing is reported as retired, with no models pushed. Learn what that means for local use, how V3.2 differs from Speciale, and what DeepSeek’s current API docs show.
Model APIs
Claude New Model Release Date: Fable 5.2 and Mythos 5.2
Anthropic announced Claude Fable 5.2 and Mythos 5.2 on November 9, 2026. See what that date means, which model is available through the Claude API, and key production considerations.
Model APIs
MiniMax M3 Model Size: 428B Parameters, 23B Active
MiniMax M3 has about 428B total parameters and 23B activated per token. Learn how those figures differ from its 1M-token API context and what to check before choosing a production route.
Model APIs
GLM-4.6 Exacto: What It Is, API Routing, and Workload Fit
GLM-4.6 Exacto uses OpenRouter’s quality-first provider routing; it is not a separate model. Learn how the selector works, see a clearly labeled API example, and assess workload fit and routing costs.
Coding agents
“Context Left Until Auto-Compact” in Claude Code: Meaning and What to Do
Learn what Claude Code documents about auto-compaction, how to inspect context with /context, what to do when the status is low, and how Claude Code behavior differs from production API compaction.
Pricing and plans
ChatGPT 5.5 Free: What You Can Use for $0—and API Costs
OpenAI’s current Free FAQ names GPT-5.6 Luna; it does not confirm whether GPT-5.5 is available in another Free mode. See third-party offer terms and GPT-5.5 API pricing.
Audio and speech
Suno API Documentation: Official Access, Wrapper Setup, and Production Checks
Find Suno’s API account portal, distinguish it from the third-party gcui-art wrapper, and see what its setup guide does—and does not—establish about music-generation integration and production use.
Model comparisons
Gemini 3 Pro vs GPT-5: Which Production API Fits Your Workload?
A version-specific comparison of Gemini 3 Pro Preview and GPT-5 APIs, including documented limits, lifecycle status, and a historical token-cost example with its billing assumption made explicit.