Skip to main content
Anthropic’s Claude is a model family prized for code, agents and long-document work. Every model speaks the OpenAI-compatible protocol, so you connect with any OpenAI SDK — just set base_url to https://www.ruapi.ai/v1. Below: how the three tiers are organized, how to read the version numbers, and how to send a first request.

Three tiers: Haiku, Sonnet, Opus

Claude has three named tiers. The idea is simple: the “higher” the tier, the more capable the model, but the slower and pricier it is.
Not sure? Start with Sonnet (the latest is claude-sonnet-5-5). It covers most work. Move up to Opus when Sonnet stops keeping up with the complexity; drop to Haiku when speed and cost matter more than peak quality.
Haiku is the cheapest Claude, but on prompts longer than 100K tokens its price goes up (details below), and there deepseek-flash, with one price at any length, comes out cheaper. How to estimate the cost of long requests: Long context in the API: what it costs and how to cut it.

Reading the version numbers

An ID encodes both the tier and the generation, e.g. claude-sonnet-5 or claude-opus-5. One rule: higher numbers are newer and more capable within a tier.
  • claude-haiku-5-5 — the current Haiku. It is priced by prompt length: up to 100,000 tokens the lower tier applies; above 100,000 (cached input counts too) the whole request is billed at the higher tier — that is Anthropic’s own rule. The higher tier is exactly 5× the lower one. Both tiers are on the pricing page.
  • claude-haiku-4-5-20251001 — the previous Haiku. Some snapshots carry a release-date suffix like this one.
  • claude-sonnet-4-5-20250929, claude-sonnet-4-6, claude-sonnet-5, claude-sonnet-5-5 — the Sonnet tier; -5-5 is the newest, -5 is newer than -4-6, which is newer than -4-5. From 30 November 2026, requests to claude-sonnet-4-5-20250929 will be served by claude-sonnet-5-5 automatically, at its price — see the changelog.
  • claude-opus-4-5-20251101, claude-opus-4-6, claude-opus-4-7, claude-opus-4-8, claude-opus-5, claude-opus-5-5 — the Opus tier; claude-opus-5-5 is the newest version, and generation 5 supersedes the whole 4-x branch.
  • claude-fable-5, claude-fable-5-1, claude-fable-5-2 — Fable, a standalone flagship that sits above the tiers (see below); -5-2 is the newest version (released 9 November 2026). It isn’t part of the tier numbering.
Comparing numbers across tiers is meaningless: opus-4-8 beats sonnet-5 not because of the number but because it’s the Opus tier.
Exact current IDs, versions and per-token prices are on the Pricing page at www.ruapi.ai. Names match Anthropic’s official ones, and we add new versions to the catalog as they ship.

Claude Fable 5 — the flagship

claude-fable-5 (and its newer versions claude-fable-5-1 and claude-fable-5-2) is Anthropic’s most capable generally available line, built for the most demanding reasoning and long-horizon agentic work: large migrations, complex multi-step implementations, and agent runs that stay on task for hours. It has a 1M-token context window and outperforms the Opus tier on hard, long-horizon coding and analysis — though on short, well-scoped tasks Opus stays close and costs less. Fable or Opus? Reach for Fable on the hardest jobs: big refactors, agents that run for hours, deep analytical work. For everyday coding and chat, use Opus: the newest claude-opus-5-5 costs about half as much as the newest claude-fable-5-2 for input and output. Among the Fable versions, pick claude-fable-5-2 for new work: it is newer and 20% cheaper than claude-fable-5-1. Fable sits at the top of the price range — the exact per-token rate is on the Pricing page.
Fable 5 ships with safety classifiers that decline a small share of requests (cybersecurity, biological and chemical topics, model distillation). A declined request comes back as a normal HTTP 200 with stop_reason: "refusal" — not an error — so have your client handle that case. Haiku, Sonnet and Opus don’t behave this way.

What Claude is best at

  • Code — writing, refactoring and debugging; one of the family’s strongest suits, especially in Sonnet and Opus.
  • Agents and tool use — the model returns structured function calls that agents and pipelines are built on (see function calling for an example).
  • Long documents — a large context window fits whole codebases and long texts.
  • Vision — you can pass images as input: screenshots, diagrams, scans (see image input for the request format).

Connecting Claude

The base_url is always https://www.ruapi.ai/v1. Take any OpenAI SDK and put the model ID in the model field:
Step-by-step key, base_url and first-request setup in Python and curl are in the Quickstart. For long answers, streaming is handy. Get your key and balance on the top-up page. Claude also works in the native Anthropic format, which is what Claude Code uses. For how the two formats differ and which one to choose, see OpenAI or Anthropic format.

A page for each model

Specs from Anthropic’s official documentation, the current RuAPI price and an FAQ — one page per model:

Next

Connect and first request

base_url, key, Python and curl code.

GPT models

OpenAI GPT tiers: which to choose.

Gemini models

Google Gemini: tiers and capabilities.

Claude API key in Russia

Where to get a key, and the risks of virtual cards and resold keys.