All times Eastern (ET)Provider pages checked daily at

Migrating from claude-3-opus-20240229 to claude-opus-4-8

What changes when you move from claude-3-opus-20240229 to claude-opus-4-8: prices, limits, features and parameters, read from each company's own pages.

Status
Retired
Shutdown
Jan 5, 2026
Time left
—
Status
Active
Shutdown
not before May 28, 2027
Time left
—

Prices

USD per 1M tokens, standard tier
Typeclaude-3-opus-20240229claude-opus-4-8Change
InputNot published$5.00first seen October 1, 2026 · source—
Cached inputNot published$0.50first seen October 1, 2026 · source—
OutputNot published$25.00first seen October 1, 2026 · source—

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

Limits

Tokens
Limitclaude-3-opus-20240229claude-opus-4-8Change
Context windowNot published1,000,000 tokensin place when tracking began (October 6, 2026) · source—
Max output tokensNot published128,000 tokensin place when tracking began (October 6, 2026) · source—

Benchmarks

Same benchmark and source on both sides; settings named where they differ
Benchmarkclaude-3-opus-20240229claude-opus-4-8Change
Arena TextArena, high effort (vs no setting). Ranges don't overlap.
Other settings
  • 1322 ±3 → 1474 ±4
1322 ±31482 ±4+160
Arena Text: CodingArena, high effort (vs no setting). Ranges don't overlap.
Other settings
  • 1355 ±6 → 1529 ±6
1355 ±61533 ±6+178
Arena VisionArena, high effort (vs no setting). Ranges don't overlap.
Other settings
  • 1061 ±10 → 1279 ±7
1061 ±101286 ±6+225
GPQA DiamondEpoch AI, max effort (vs no setting).
Other settings
  • not run → 88.4% low effort
  • not run → 85.4% no reasoning
47.2%91.0%+43.8 pts
OTIS Mock AIME 2024-2025Epoch AI, max effort (vs no setting).
Other settings
  • not run → 97.8% low effort
  • not run → 84.4% no reasoning
4.7%98.3%+93.6 pts
SimpleQA VerifiedEpoch AI, max effort (vs no setting).12.6%53.0%+40.4 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-3-opus-20240229: 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.

No aliases point at either model.

On cloud platforms

All platform dates
ModelPlatformPlatform IDShutdownTime left
claude-3-opus-20240229Google Cloud Vertex AIclaude-3-opusAug 1, 2025Retired on August 1, 2025
claude-opus-4-8Amazon Bedrockanthropic.claude-opus-4-8not before May 28, 2027Active
claude-opus-4-8Microsoft Foundryversion 1claude-opus-4-8Sep 1, 2027Active321 days
claude-opus-4-8Microsoft Foundryversion 2claude-opus-4-8Sep 1, 2027Active321 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

  1. Change the model string from claude-3-opus-20240229 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-3-opus-20240229, claude-opus-4-8.