Context
n/a
Max output
n/a
Serving providers
1
Cheapest input
$1.00 /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 AnalysisSpeed & latency
Output speed
103 t/s
tokens / second
Time to first token
6.18s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| CritPt | 0% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| GDPval | 906.6 | reasoning: true | — | |||||||||||||
| GPQA Diamond | 67% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Humanity's Last Exam | 10% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| IFBench | 54% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| IT-Bench SRE | 27% | reasoning: true | — | |||||||||||||
| LiveCodeBench | 61% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Long-Context Reasoning | 70% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| MMLU-Pro | 80% | default | — | |||||||||||||
| ||||||||||||||||
| MMMU-Pro | 59% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| Omniscience | -4.2 | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| SciCode | 43% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
| TerminalBench Hard | 27% | default | — | |||||||||||||
| ||||||||||||||||
| TerminalBench v2.1 | 44% | reasoning: true | — | |||||||||||||
| τ-bench Banking | 9% | reasoning: true | — | |||||||||||||
| τ²-bench | 55% | reasoning: true | — | |||||||||||||
| ||||||||||||||||
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expand| Serving provider | Input /1M | Output /1M | Endpoints | ||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| ReplicateCheapest | $1.00 | $5.00 | 1 | ||||||||||||||||
| |||||||||||||||||||
Price history
input + output $/1M since we started tracking Input Output
Cost calculator
estimate your monthly spend on this model$600
estimated / month
Model IDs
copy the exact identifier for your platformreplicate/anthropic/claude-4.5-haiku
Frequently asked questions
Claude 4.5 Haiku pricing, context and availabilityHow much does Claude 4.5 Haiku cost?
Claude 4.5 Haiku costs $1.00 per 1M input tokens and $5.00 per 1M output tokens at its cheapest provider via Replicate.
What can Claude 4.5 Haiku do?
Claude 4.5 Haiku supports image input (vision), tool use, prompt caching and structured output.
Other Anthropic models
compare pricing across the Anthropic lineupClaude Sonnet 4.5$3.00/1M · 8 providersClaude Haiku 4.5$1.00/1M · 7 providersClaude Opus 4.5$5.00/1M · 7 providersClaude Sonnet 4.6$3.00/1M · 6 providersClaude Opus 4.6$5.00/1M · 6 providersClaude Opus 4.1$15.00/1M · 6 providersClaude Sonnet 4$3.00/1M · 5 providersClaude 3.7 Sonnet$3.00/1M · 5 providers
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