Skip to main content
AI Choice Engine

Model comparison

Claude Haiku 4.5 vs Claude Sonnet 5

Two Anthropic tiers compared on the figures that decide which one a workload actually needs.

Recorded profile verification October 1, 2026Individual provider fields may changeEvidence confidence: Medium — see receipts below

Anthropic

Claude Haiku 4.5

Budget

vs

Anthropic

Claude Sonnet 5

Balanced

AI model capability comparison
SpecificationClaude Haiku 4.5Claude Sonnet 5
ProviderAnthropicAnthropic
TierBudgetBalanced
Context window200KWinner: 1M
Max output64KWinner: 128K
Input / 1M tokensWinner: $1$2
Output / 1M tokensWinner: $5$10
WeightsClosedClosed
ParametersNot verifiedUnverifiedNot verifiedUnverified
Reasoning levelsextended thinking (budget_tokens)low, medium, high, xhigh, max
Modalitiestext, imagetext, image
API model idclaude-haiku-4-5-20251001claude-sonnet-5
ReleasedOctober 15, 2025June 30, 2026
SWE-bench Verified [high] · source date Claude Haiku 4.5: 2026-02-1766.6Not verifiedUnverified
SWE-bench Verified · source date Claude Haiku 4.5: 2025-10-1573.3Not verifiedUnverified
Terminal-Bench · source date Claude Haiku 4.5: 2025-10-1540.21Not verifiedUnverified
Terminal-Bench 2.1 · source date Claude Sonnet 5: 2026-06-30Not verifiedUnverified80.4
Humanity's Last Exam · source date Claude Sonnet 5: 2026-06-30Not verifiedUnverified57.4
LiveBench · source date Claude Sonnet 5: 2026-09-05Not verifiedUnverified76

Dates beside benchmark scores refer to the linked source’s publication or capture date unless that source explicitly states when it measured the result. A shared URL alone does not establish comparable runs; unverified setups are marked. Prices are USD per million tokens at standard rates, excluding batch and caching discounts. Values we could not confirm from the provider are shown as “Not verified” rather than estimated.

Benchmark receipts

Where each score comes from, and how far it can be compared across models.

Pricing tiers

Claude Haiku 4.5: Standard $1/$5 per MTok; cache reads $0.10, 5-minute writes $1.25 and 1-hour writes $2. Batch $0.50/$2.50. Context 200K and output 64K. Reliable knowledge cutoff Feb 2025; training cutoff Jul 2025. The alias claude-haiku-4-5 resolves to claude-haiku-4-5-20251001. Retirement not sooner than October 15, 2026; no definite shutdown is announced.

Claude Sonnet 5: Standard $2/$10 per MTok with no long-context surcharge. Cache reads $0.20; 5-minute writes $2.50 and 1-hour writes $4. Batch $1/$5. US-only inference adds 10% where supported. Batch supports 300K output with output-300k-2026-03-24; standard stays 128K. Knowledge cutoff Jan 2026; retirement not sooner than June 30, 2027.

BudgetRecord checked October 1, 2026

Claude Haiku 4.5

Claude Haiku 4.5 is Anthropic's lower-cost Haiku tier for high-volume classification and extraction at $1/$5 per million input/output tokens.

Best for

  • High-volume classification
  • Routine extraction
  • Latency-sensitive stacks

Watch out

No adaptive thinking (manual extended thinking via budget_tokens only); 200K context. Anthropic lists 2026-10-15 as the earliest possible retirement date, and Haiku 5.5 is announced but not released.

BalancedRecord checked October 1, 2026

Claude Sonnet 5

Claude Sonnet 5 is Anthropic's previous Sonnet generation for high-volume agentic work at $2/$10.

Best for

  • Everyday generation
  • High-volume agents
  • Cost-sensitive work

Watch out

Active legacy. Sonnet 5.5 launched September 28 at the same token price, with breaking changes to thinking, forced tool use, computer use, advisor choices and progress blocks. Sonnet 5 rejects non-default temperature/top_p/top_k; test the exact target model before switching.

When the cheaper one wins

Claude Haiku 4.5 is cheaper on output at $5 per million tokens against $10 for Claude Sonnet 5 — about 2.0×. Use the cheaper tier for classification, extraction, summarisation, and any task where the expensive model’s extra score does not change the accepted output. The expensive one only pays if your hardest task actually fails on the cheap tier. This compares standard short-context token rates, not total cost per accepted task. Include input, cache, context tiers, schedules, retries and review in your pilot.

Run the model picker

Evidence confidence: Medium

How strong and complete the evidence behind this comparison is — not a prediction of which model is better.

  • Pricing verified on both sides — Input and output rates are verified for both models.
  • 4/5 core specs verified on both sides — Not published for at least one side: parameter count.
  • No directly aligned benchmark setup — No benchmark has matching cited sources, source dates, units, effort and recorded run details on both models.
  • Verified within the last 90 days — Older of the two catalog checks was 25 days ago.
  • Both models carry source citations — Each side has at least two catalog sources on record.

Source receipts

Each catalog figure was checked against the provider or an independent second source on the date shown.

Related comparisons

Diving deeper on one model? Claude Haiku 4.5 · Claude Sonnet 5

Common questions

Claude Haiku 4.5 vs Claude Sonnet 5

Answered from the verified figures on this page rather than general guidance.

Is Claude Haiku 4.5 or Claude Sonnet 5 cheaper for input?
Claude Haiku 4.5 is cheaper at $1 per million input tokens, against $2 for Claude Sonnet 5 — roughly 2.0× the price. Estimate both input and output token volume for your workload. These are base rates; Claude Haiku 4.5: Standard $1/$5 per MTok; cache reads $0.10, 5-minute writes $1.25 and 1-hour writes $2. Batch $0.50/$2.50. Context 200K and output 64K. Reliable knowledge cutoff Feb 2025; training cutoff Jul 2025. The alias claude-haiku-4-5 resolves to claude-haiku-4-5-20251001. Retirement not sooner than October 15, 2026; no definite shutdown is announced. Claude Sonnet 5: Standard $2/$10 per MTok with no long-context surcharge. Cache reads $0.20; 5-minute writes $2.50 and 1-hour writes $4. Batch $1/$5. US-only inference adds 10% where supported. Batch supports 300K output with output-300k-2026-03-24; standard stays 128K. Knowledge cutoff Jan 2026; retirement not sooner than June 30, 2027.
Is Claude Haiku 4.5 or Claude Sonnet 5 cheaper for output?
Claude Haiku 4.5 is cheaper at $5 per million output tokens, against $10 for Claude Sonnet 5 — roughly 2.0× the price. Estimate both input and output token volume for your workload. These are base rates; Claude Haiku 4.5: Standard $1/$5 per MTok; cache reads $0.10, 5-minute writes $1.25 and 1-hour writes $2. Batch $0.50/$2.50. Context 200K and output 64K. Reliable knowledge cutoff Feb 2025; training cutoff Jul 2025. The alias claude-haiku-4-5 resolves to claude-haiku-4-5-20251001. Retirement not sooner than October 15, 2026; no definite shutdown is announced. Claude Sonnet 5: Standard $2/$10 per MTok with no long-context surcharge. Cache reads $0.20; 5-minute writes $2.50 and 1-hour writes $4. Batch $1/$5. US-only inference adds 10% where supported. Batch supports 300K output with output-300k-2026-03-24; standard stays 128K. Knowledge cutoff Jan 2026; retirement not sooner than June 30, 2027.
Which has the larger context window, Claude Haiku 4.5 or Claude Sonnet 5?
Claude Sonnet 5 accepts 1M tokens against 200K for Claude Haiku 4.5. This only matters if you routinely send very long documents or large codebases.
Do Claude Haiku 4.5 and Claude Sonnet 5 support the same reasoning levels?
Claude Haiku 4.5 exposes extended thinking (budget_tokens), while Claude Sonnet 5 exposes low, medium, high, xhigh, max.
Should I use Claude Haiku 4.5 or Claude Sonnet 5?
We classify Claude Haiku 4.5 in the budget tier and Claude Sonnet 5 in the balanced tier. Test whether either meets your accuracy, tool-use and latency requirements before choosing on price.

Next step

Choosing between them

The verified figures that separate this pair, computed from the catalog rather than restated boilerplate.

  • Input price: Claude Haiku 4.5 costs $1 per 1M tokens versus $2 for Claude Sonnet 5 — a 2x difference at the headline tier.
  • Context: Claude Sonnet 5 takes 1M against 200K for Claude Haiku 4.5 — only decisive if your prompts approach the smaller window.
  • Positioning: Claude Haiku 4.5 sits in the budget tier, Claude Sonnet 5 in the balanced tier. Compare accuracy, reliability, latency, and cost on representative tasks before choosing.
Run the model pickerEstimate stack costAll model comparisons

Choosing a harness rather than a model — Cursor, Copilot, Claude Code, Windsurf, or Lovable? Compare agentic harnesses · Latest releases.