All times Eastern (ET)Provider pages checked daily at

Migrating from claude-sonnet-4-20250514 to claude-sonnet-5-5

What changes when you move from claude-sonnet-4-20250514 to claude-sonnet-5-5: input price −33.3%, output price −33.3%.

Status
Retired
Shutdown
Jun 15, 2026
Time left
—
Status
Active
Shutdown
not before Sep 28, 2027
Time left
—

Prices

USD per 1M tokens, standard tier
Typeclaude-sonnet-4-20250514claude-sonnet-5-5Change
Input$3.00first seen October 1, 2026 · source$2.00first seen October 1, 2026 · source−33.3%
Cached input$0.30first seen October 1, 2026 · source$0.10first seen October 8, 2026 · source−66.7%
Output$15.00first seen October 1, 2026 · source$10.00first seen October 1, 2026 · source−33.3%

At 1M input and 250K output tokens a month: $6.75 on claude-sonnet-4-20250514, $4.50 on claude-sonnet-5-5 (−33.3%).

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

Limits

Tokens
Limitclaude-sonnet-4-20250514claude-sonnet-5-5Change
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-sonnet-4-20250514claude-sonnet-5-5Change
Arena TextArena, xhigh effort (vs thinking 32k). Ranges don't overlap.1402 ±41475 ±8+73
Arena Text: CodingArena, xhigh effort (vs thinking 32k). Ranges don't overlap.1474 ±81527 ±15+53
Arena VisionArena, xhigh effort (vs thinking 32k). Ranges don't overlap.1206 ±171266 ±14+60
GPQA DiamondEpoch AI, max effort (vs 59k).79.2%95.6%+16.4 pts
OTIS Mock AIME 2024-2025Epoch AI, max effort (vs 32k).71.1%100.0%+28.9 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-sonnet-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-sonnet-5-5: Structured outputs, Function calling, PDF input, Fine-tuning, Built-in web search, logprobs.

No aliases point at either model.

On cloud platforms

All platform dates
ModelPlatformPlatform IDShutdownTime left
claude-sonnet-4-20250514Amazon Bedrockanthropic.claude-sonnet-4-20250514-v1:0Oct 14, 2026Retired on October 14, 2026
claude-sonnet-5-5Amazon Bedrockanthropic.claude-sonnet-5-5not before Sep 28, 2027Active

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-sonnet-4-20250514 to claude-sonnet-5-5.

Compared from AIWire's published data when this page loaded. Each fact links to the page it came from. Model pages: claude-sonnet-4-20250514, claude-sonnet-5-5.