Claude 3.5 Haiku
Anthropic · text, image → text
Claude 3.5 Haiku is the next generation of Claude's fastest model.
Input$1 /M
Output$5 /M
← ModelsClaude 3.5 HaikuClaude 3.5 Sonnet 20240620
Claude 3.5 Haiku vs Claude 3.5 Sonnet 20240620
Compare Claude 3.5 Haiku from Anthropic and Claude 3.5 Sonnet 20240620 from Anthropic on key metrics including benchmarks, price, context length, and other model features. Access both models and hundreds of others through the AIHubMix API.
Claude 3.5 HaikuClaude 3.5 Sonnet 20240620+ Add model · 2/4
Claude 3.5 Sonnet 20240620
Anthropic · text, image → text
Claude 3.5 Sonnet delivers performance superior to Opus and speeds faster than its predecessor, all at the same price point. Its core strengths include: Coding: Autonomously writes, edits, and executes code with advanced reasoning and troubleshooting. Data Science: Augments human expertise by analyzing unstructured data and using multiple tools to generate insights. Visual Processing: Excels at interpreting charts, graphs, and images, accurately transcribing text to derive high-level insights. Agentic Tasks: Exceptional tool use makes it highly effective for complex, multi-step agentic workflows that interact with other systems.
Input$3 /M
Output$15 /M
Pricing & Specifications
Prices are per million tokens. Time to First Token and throughput are rolling averages measured on AIHubMix.
Claude 3.5 Haiku
Claude 3.5 Sonnet 20240620
Input /M
$1
$3
Output /M
$5
$15
Cache read /M
-
-
Context length
NaN
NaN
Max output
0
0
Time to First Token
1.0 s
-
Throughput
62.4 tok/s
-
Modalities
textimage
textimage
Supported Parameters
toolsfunction callingstructured outputs
API Formats
Released
-
-
Promotional prices show the discounted rate; see each model page for promotion windows.
Activity Past 30 Days
Daily traffic served through AIHubMix — how demand for each model is trending.
claude-3-5-haikuclaude-3-5-sonnet-20240620
Tokens / day
-
Requests / day
-
Performance Past 3 Days
Measured on real AIHubMix traffic, hourly buckets. Gaps mean no traffic in that hour.
claude-3-5-haikuclaude-3-5-sonnet-20240620
Throughput (tok/s)
-
TTFT (s)
-
Uptime (%)
-
LMArena Benchmarks
LMArena ratings by capability (Bradley-Terry, commonly called Elo). Higher is better.
Text
claude-3-5-haikuclaude-3-5-sonnet-20240620
1200124012801320
Overall
12551281
Coding
12871307
Math
12441303
Instruction following
12411270
Longer query
12601275
Chinese
12241264
English
12691288
Vision
claude-3-5-haikuclaude-3-5-sonnet-20240620
10601080110011201140
Overall
10921120
OCR
10891089
Diagram
10781078
Homework
11171117
Source: LMArena (arena.ai) leaderboard, imported by AIHubMix. Models without published ratings are omitted per chart.
Cost calculator
Estimate your monthly bill for the same workload on each model.
Claude 3.5 Haiku
$135 /mo
Claude 3.5 Sonnet 20240620
$405 /mo
Monthly = daily × 30. Discounted rates applied where a promotion is active.
FAQ
Which is cheaper: Claude 3.5 Haiku, Claude 3.5 Sonnet 20240620?
Claude 3.5 Haiku: $5/M output tokens; Claude 3.5 Sonnet 20240620: $15/M. Use the cost calculator above to estimate your own workload.
How do their coding arena scores compare?
Claude 3.5 Sonnet 20240620: 1307; Claude 3.5 Haiku: 1287 (LMArena coding leaderboard).
What inputs and capabilities does each model support?
Claude 3.5 Haiku accepts text and image input and supports tool calling, function calling and structured outputs; Claude 3.5 Sonnet 20240620 accepts text and image input.
Can I call Claude 3.5 Haiku and Claude 3.5 Sonnet 20240620 with the same API key?
Yes. AIHubMix serves every model on this page behind one OpenAI-compatible endpoint, so switching between them is a one-line change to the model field — no second account, key or SDK.
Popular comparisons
Related model match-ups readers also look at.
