Claude 5 API release date: what's live right now

Quick answer: Opus 5 and Sonnet 5 are callable now.

"Claude 5" is not one release. Each size in the generation has its own model ID and rollout schedule. The two callable IDs in the current catalog are claude-opus-5 and claude-sonnet-5; Haiku remains on the 4.x line. That makes a search for the Claude 5 API release date three separate questions bundled into one. The Opus and Sonnet questions now have concrete answers because both IDs resolve through the API. Haiku 5 still has no catalog entry, so production integrations should continue to pin an exact available ID instead of relying on a generation-wide alias. The rest of this page separates current availability, request cost, and migration mechanics so you can test Opus 5 without replacing your existing fallback path.

Why Anthropic ships tiers separately instead of all at once.

None of this is specific to Anthropic. Every lab that ships multiple sizes under one generation name stages the rollout, and the numbering rarely lands on the same day across sizes. The reliable signal is the catalog entry for the exact model ID you plan to call, not a generation-wide announcement that may only describe one size of it.

• Sonnet is the default workhorse size, so it typically gets the first stable release inside a new generation.
• Opus carries the heaviest evaluation and safety review of the three sizes, which routinely pushes its release weeks or months behind Sonnet.
• Haiku is usually distilled from the larger models after they stabilize, so it tends to ship last rather than first.
• Model catalogs and pricing pages update per model ID, not per generation, so "Claude 5 pricing" really means whichever Claude 5 model IDs exist on the day you check.

Worked example: what a Sonnet 5 request actually costs.

Sonnet 5 is billed like any other Claude model: a rate per million input tokens and a separate rate per million output tokens, with the total scaling directly with request size. The table below prices three representative request sizes for claude-sonnet-5 at Anthropic's own list rate and at a lower per-token rate available through third-party gateways.

Why the release-date question keeps resurfacing.

A generation number does not map to one launch event: Sonnet, Opus, and Haiku each ship on their own schedule under their own model ID, so a "Claude 5" mention can sit on a page for months before every size in that generation exists. Default model aliases sometimes start resolving to a new tier without any announcement, which reads like a release even when none went out. The catalog entry for the exact model ID you plan to call is the fact that changes your integration and your bill; a generation-wide announcement is marketing copy layered on top of it.

Where each Claude 5-era model stands right now.

"Claude 5" today means two callable models sitting alongside the previous generation. The table below is pulled from the same catalog that prices every model on this site.

How to prepare your integration for a staggered rollout.

Treat the model ID as the unit of change, not the generation name. That is the one habit that keeps a staggered, size-by-size rollout from turning into an emergency migration later.

• Pin the exact model ID, claude-opus-5, instead of a generation alias, so a later routing change cannot silently change your default model.
• Add a fallback path: if a call to claude-opus-5 errors, retry against claude-opus-4-8 or claude-sonnet-5 instead of failing the request outright.
• Budget from today's catalog: Opus 5 is listed at $4.00 input and $20.00 output per million tokens through APIsRouter, against a $5.00 / $25.00 official reference.
• Watch the context window field in the catalog, not just the price. All five models above currently list a 1M-token window, so a version bump alone will not force a chunking rewrite.
• If you are testing tiers side by side to control cost, route the cheaper fallback calls through an OpenAI-compatible gateway instead of paying official list rates on every retry.
• Re-check the catalog before a larger migration. A model ID that does not exist yet, such as a future haiku-5 slug, should fail cleanly rather than silently falling through to a different tier.

Config example: call Claude Opus 5 today.

Pointing an existing client at Opus 5 is a model-name change, not an SDK upgrade. APIsRouter mirrors the OpenAI chat completions shape at https://api.apisrouter.com/v1, so the same request structure already in use for claude-opus-4-8 works by swapping the model field. Verify the ID resolves before wiring it into a default:

curl https://api.apisrouter.com/v1/chat/completions \
  -H "Authorization: Bearer sk-APIsRouter-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "claude-opus-5",
    "messages": [{"role": "user", "content": "Reply with one word: ok"}],
    "max_tokens": 16
  }'

FAQ