Context
200K
Max output
8K
Serving providers
3
Cheapest input
$0.80 /1M
Prices are on-demand list rates. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.

Benchmarks

independent evaluations · source: Artificial Analysis
Headline indices
15.9
of 100
1.9
of 100
Individual benchmarks · click a row for effort variants
BenchmarkBest scoreEffortCost / task
CritPt0%default
GDPval444.2default
GPQA Diamond41%default
Humanity's Last Exam3%default
IFBench43%default
LiveCodeBench31%default
Long-Context Reasoning23%default
MMLU-Pro63%default
MMMU-Pro46%default
Omniscience-23.2default
SciCode27%default
TerminalBench Hard2%default
TerminalBench v2.110%default
τ-bench Banking6%default
τ²-bench25%default

Pricing by serving provider

standard tier · per 1M tokens · click a provider to expand

Input pricing runs from $0.80 to $1.00 per 1M tokens across 3 providers, so the dearest route costs 25% more than the cheapest for the same model.

Serving providerInput /1MOutput /1MEndpoints
Vercel AI GatewayCheapest$0.80$4.001
ComponentUnitStandardBatchCached
Text cached in/1M tok$0.0800
Text cache write/1M tok$1.00
Text input/1M tok$0.8000
Text output/1M tok$4.00
Replicate$1.00$5.001
Vertex AI$1.00$5.001

Price history

input + output $/1M since we started tracking
Input Output
Input down 20% since first tracked
$0.000$2.00$4.00$6.00Nov 4Jul 30Aug 4Jun 22$4.00$0.800

Cost calculator

estimate your monthly spend on this model
$480
estimated / month

Model IDs

copy the exact identifier for your platform
vercel_ai_gateway/anthropic/claude-3.5-haikureplicate/anthropic/claude-3.5-haikuvertex_ai/claude-3-5-haiku

Frequently asked questions

Claude 3.5 Haiku pricing, context and availability

How much does Claude 3.5 Haiku cost?

Claude 3.5 Haiku costs $0.80 per 1M input tokens and $4.00 per 1M output tokens at its cheapest provider via Vercel AI Gateway. Across 3 serving providers, input prices range from $0.80 to $1.00 per 1M tokens.

What is the context window of Claude 3.5 Haiku?

Claude 3.5 Haiku accepts up to 200K tokens of context and can return up to 8K output tokens.

Which providers serve Claude 3.5 Haiku?

Claude 3.5 Haiku is available from 3 serving providers, each with its own pricing and model ID. Vercel AI Gateway is currently the cheapest.

What can Claude 3.5 Haiku do?

Claude 3.5 Haiku supports image input (vision), tool use, prompt caching and structured output.

Other Anthropic models

compare pricing across the Anthropic lineup

Popular comparisons

head-to-head pages featuring Claude 3.5 Haiku
Pricing verified against LiteLLM + OpenRouter + provider pages · refreshed daily

Every weekday

AI moves fast. Here's your debrief.

News, analysis, tools, and more.

For people who build with AI