Migrating from claude-opus-4-20250514 to claude-opus-4-8

What changes when you move from claude-opus-4-20250514 to claude-opus-4-8: input price −66.7%, output price −66.7%.

From: claude-opus-4-20250514
Status: Retired
Shutdown: Jun 15, 2026
Time left: —

To: claude-opus-4-8
Status: Active
Shutdown: not before May 28, 2027
Time left: —

Prices

USD per 1M tokens, standard tier

Type	claude-opus-4-20250514	claude-opus-4-8	Change
Input	$15.00first seen October 1, 2026 · source	$5.00first seen October 1, 2026 · source	−66.7%
Cached input	$1.50first seen October 1, 2026 · source	$0.50first seen October 1, 2026 · source	−66.7%
Output	$75.00first seen October 1, 2026 · source	$25.00first seen October 1, 2026 · source	−66.7%

At 1M input and 250K output tokens a month: $33.75 on claude-opus-4-20250514, $11.25 on claude-opus-4-8 (−66.7%).

Other tiers, prompt-size bands and modalities are on each model's page.

Limits

Tokens

Limit	claude-opus-4-20250514	claude-opus-4-8	Change
Context window	Not published	1,000,000 tokensin place when tracking began (October 6, 2026) · source	—
Max output tokens	Not published	128,000 tokensin place when tracking began (October 6, 2026) · source	—

Benchmarks

Same benchmark and source on both sides; settings named where they differ

Benchmark	claude-opus-4-20250514	claude-opus-4-8	Change
Arena TextArena, high effort (vs thinking 16k). Ranges don't overlap. Other settings 1414 ±4 → 1474 ±4	1426 ±4	1482 ±4	+56
Arena Text: CodingArena, high effort (vs thinking 16k). Ranges don't overlap. Other settings 1464 ±7 → 1529 ±6	1498 ±8	1533 ±6	+35
Arena VisionArena, high effort (vs thinking 16k). Ranges don't overlap. Other settings 1188 ±13 → 1279 ±7	1208 ±16	1286 ±6	+78
Arena SearchArena. Ranges don't overlap.	1152 ±6	1195 ±6	+43
GPQA DiamondEpoch AI, max effort (vs 16k). Other settings not run → 88.4% low effort not run → 85.4% no reasoning	76.3%	91.0%	+14.7 pts
OTIS Mock AIME 2024-2025Epoch AI, max effort (vs 27k). Other settings not run → 97.8% low effort not run → 84.4% no reasoning	64.4%	98.3%	+33.9 pts

A score from one source is never compared with another source's, and company-reported scores are compared only within the same company; settings named where they differ. Data: Arena (arena.ai), CC BY 4.0; Epoch AI, Capabilities & benchmarking (epoch.ai/benchmarks), CC BY.

Features and parameters

Compare models

No feature is published for both models, so none can be compared.

Not published for claude-opus-4-20250514: Structured outputs, Function calling, Prompt caching, Batch API, Image input, PDF input, Reasoning / thinking, Fine-tuning, Built-in web search, temperature parameter, top_p parameter, logprobs, Context window, Max output tokens.

Not published for claude-opus-4-8: Structured outputs, Function calling, PDF input, Fine-tuning, Built-in web search, temperature parameter, top_p parameter, logprobs.

Aliases

All aliases

No aliases point at either model.

On cloud platforms

All platform dates

Model	Platform	Platform ID	Shutdown	Time left
claude-opus-4-8	Amazon Bedrock	anthropic.claude-opus-4-8	not before May 28, 2027Active
claude-opus-4-8	Microsoft Foundryversion 1	claude-opus-4-8	Sep 1, 2027Active	321 days
claude-opus-4-8	Microsoft Foundryversion 2	claude-opus-4-8	Sep 1, 2027Active	321 days

Read daily from each platform's own pages. The status above uses each company's own date. Time left counts to 00:00 UTC on the shutdown date, which is the evening before in ET.

Checklist

Change the model string from claude-opus-4-20250514 to claude-opus-4-8.

Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: claude-opus-4-20250514, claude-opus-4-8.