Skip to main content
AI Choice Engine

Model comparison

Claude Haiku 4.5 vs Gemini 3.5 Flash-Lite

Anthropic against Google, compared on context, price, and attributed benchmark results.

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

Anthropic

Claude Haiku 4.5

Budget

vs

Google

Gemini 3.5 Flash-Lite

Budget

AI model capability comparison
SpecificationClaude Haiku 4.5Gemini 3.5 Flash-Lite
ProviderAnthropicGoogle
TierBudgetBudget
Context window200KWinner: 1.05M
Max output64KWinner: 66K
Input / 1M tokens$1Winner: $0.30
Output / 1M tokens$5Winner: $2.50
WeightsClosedClosed
ParametersNot verifiedUnverifiedNot verifiedUnverified
Reasoning levelsextended thinking (budget_tokens)minimal, low, medium, high
Modalitiestext, imagetext, image, video, audio, pdf
API model idclaude-haiku-4-5-20251001gemini-3.5-flash-lite
ReleasedOctober 15, 2025July 21, 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
Artificial Analysis Intelligence Index · source date Gemini 3.5 Flash-Lite: 2026-10-01Not verifiedUnverified22

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.

Gemini 3.5 Flash-Lite: Standard $0.30 input for text/image/video/audio and $2.50 output including thinking per MTok. Cached input $0.03 plus $1/MTok-hour storage. Batch/Flex $0.15/$1.25 with published cached input $0.02. Priority $0.54/$4.50, cached $0.05. Grounding tools have separate charges/quotas. The older 3.1 Flash-Lite has modality-dependent input rates.

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.

BudgetRecord checked October 1, 2026

Gemini 3.5 Flash-Lite

Gemini 3.5 Flash-Lite is Google's recommended Flash-Lite tier for high-volume, latency-sensitive agent loops.

Best for

  • High-volume agents
  • Document pipelines
  • Cost-sensitive multimodal

Watch out

Compare input modality: 3.1 Flash-Lite is $0.25 for text/image/video but $0.50 for audio, versus this model's $0.30 for either. Thinking includes minimal through high; computer use is Preview. Price alone does not establish quality on reasoning tasks.

When the cheaper one wins

Gemini 3.5 Flash-Lite is cheaper on output at $2.50 per million tokens against $5 for Claude Haiku 4.5 — 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 · Gemini 3.5 Flash-Lite

Common questions

Claude Haiku 4.5 vs Gemini 3.5 Flash-Lite

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

Is Claude Haiku 4.5 or Gemini 3.5 Flash-Lite cheaper for input?
Gemini 3.5 Flash-Lite is cheaper at $0.30 per million input tokens, against $1 for Claude Haiku 4.5 — roughly 3.3× 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. Gemini 3.5 Flash-Lite: Standard $0.30 input for text/image/video/audio and $2.50 output including thinking per MTok. Cached input $0.03 plus $1/MTok-hour storage. Batch/Flex $0.15/$1.25 with published cached input $0.02. Priority $0.54/$4.50, cached $0.05. Grounding tools have separate charges/quotas. The older 3.1 Flash-Lite has modality-dependent input rates.
Is Claude Haiku 4.5 or Gemini 3.5 Flash-Lite cheaper for output?
Gemini 3.5 Flash-Lite is cheaper at $2.50 per million output tokens, against $5 for Claude Haiku 4.5 — 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. Gemini 3.5 Flash-Lite: Standard $0.30 input for text/image/video/audio and $2.50 output including thinking per MTok. Cached input $0.03 plus $1/MTok-hour storage. Batch/Flex $0.15/$1.25 with published cached input $0.02. Priority $0.54/$4.50, cached $0.05. Grounding tools have separate charges/quotas. The older 3.1 Flash-Lite has modality-dependent input rates.
Which has the larger context window, Claude Haiku 4.5 or Gemini 3.5 Flash-Lite?
Gemini 3.5 Flash-Lite accepts 1.05M 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 Gemini 3.5 Flash-Lite support the same reasoning levels?
Claude Haiku 4.5 exposes extended thinking (budget_tokens), while Gemini 3.5 Flash-Lite exposes minimal, low, medium, high.
Should I use Claude Haiku 4.5 or Gemini 3.5 Flash-Lite?
Both are classified in our budget tier; this editorial grouping does not imply equal capability. Claude Haiku 4.5 is a candidate for high-volume classification; Gemini 3.5 Flash-Lite is a candidate for high-volume agents. Compare accuracy, tool reliability, latency and cost on representative tasks.

Next step

Choosing between them

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

  • Input price: Gemini 3.5 Flash-Lite costs $0.30 per 1M tokens versus $1 for Claude Haiku 4.5 — a 3.3x difference at the headline tier.
  • Context: Gemini 3.5 Flash-Lite takes 1.05M against 200K for Claude Haiku 4.5 — only decisive if your prompts approach the smaller window.
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.