Current Models & Pricing
This is the one page in AILmanac with a hard freshness guarantee. Every model fact elsewhere on the site links here instead of hard-coding a name or number, so there's a single place to keep current.
Current Claude models
Last verified: 2026-06-20 · Official models & pricing
| Model | API model ID | Tier | Best for |
|---|---|---|---|
| Claude Opus 4.8 | claude-opus-4-8 | Opus — most capable | The hardest reasoning, long-horizon agents, and complex coding where quality matters more than cost. |
| Claude Sonnet 4.6 | claude-sonnet-4-6 | Sonnet — balanced | The default workhorse: strong coding and reasoning at a fraction of Opus cost. Start here for most production work. |
| Claude Haiku 4.5 | claude-haiku-4-5-20251001 | Haiku — fastest & cheapest | High-volume, latency-sensitive tasks: classification, extraction, routing, simple chat, and cheap sub-agents. |
| Fable 5 | claude-fable-5 | Latest generation | One of the newest Claude models. Capabilities and positioning evolve quickly — check the official page above before choosing it. |
Model IDs are exact; tiers and 'best for' are guidance. Pricing, context-window sizes and rate limits change frequently and are intentionally NOT listed here — always read them on the official page above. This file is the single source of truth: never hard-code model facts in prose, link to this table instead.
Why pricing and context limits aren't in the table
They change too often to copy safely — a stale price is worse than no price. We list the identity of each model (name, API ID, what it's for) and send you to the official page for pricing, context windows, and rate limits, which is always authoritative.
How we keep this fresh
- The table is rendered from a single data file (
data/models.json) carrying a "last verified" date. - Updating it is a one-line change — a perfect first contribution.
- In a later phase, automation will diff this file against the official models endpoint and open a pull request when something drifts — but a human always reviews before it ships. (See How Our Automation Works.)
Choosing between them
A quick rule of thumb (full guidance in Choosing a Model):
- Start with Sonnet. Best balance of quality, speed, and cost for most work.
- Reach for Opus when quality on a hard problem matters more than cost.
- Drop to Haiku for high-volume, latency-sensitive, or simple tasks.
See also
- Choosing a Model — the full decision framework
- Tokens & Pricing — how cost is actually calculated
- Deprecation & Migration Watch — retired models and breaking changes