Claude Haiku 5.5 vs Claude Sonnet 5.5

Side-by-side pricing per provider, context window, benchmark scores and speed, all on one OpenAI-compatible API.

Estimate monthly cost for these models
Metric
Claude Haiku 5.5Anthropicanthropic/claude-haiku-5.5
Claude Sonnet 5.5Anthropicanthropic/claude-sonnet-5.5
Creator
Anthropic
Anthropic
Released
Oct 7, 2026
Sep 28, 2026
Context window
1M
1M
Input / 1MLowest provider price
$0.10 (best)
$2.00
Output / 1MLowest provider price
$0.50 (best)
$10.00
Providers
3
4 (best)
IntelligenceArtificial Analysis index
34.6
54.5 (best)
LatencyMedian time to first token
2.0s (best)
5.1s
ThroughputMedian tokens per second
<1 t/s
<1 t/s (best)
Accepts
Image, Text
Text, Image
Produces
Text
Text
Tool calling
Yes
Yes
Structured output
Yes
Yes
Reasoning
Yes
Yes

Claude Haiku 5.5 vs Claude Sonnet 5.5: summary

Claude Haiku 5.5 and Claude Sonnet 5.5 are both available through FastRouter's OpenAI-compatible API, so switching between them is a change of model id, not a new integration.

Claude Haiku 5.5, from Anthropic, has a 1,000,000-token context window, costs from $0.10/1M input and $0.50/1M output tokens across 3 providers and scores 34.6 on the Artificial Analysis Intelligence Index.

Claude Sonnet 5.5, from Anthropic, has a 1,000,000-token context window, costs from $2.00/1M input and $10.00/1M output tokens across 4 providers and scores 54.5 on the Artificial Analysis Intelligence Index.

Claude Haiku 5.5 is the cheapest on input, 20× cheaper than the next model, Claude Sonnet 5.5 scores highest for intelligence and Claude Sonnet 5.5 has the highest throughput.

Switch with one line

client = OpenAI(base_url="https://api.fastrouter.ai/api/v1", api_key="<FASTROUTER_API_KEY>") client.chat.completions.create(model="anthropic/claude-haiku-5.5", messages=[...]) # or client.chat.completions.create(model="anthropic/claude-sonnet-5.5", messages=[...])
Full API docs

Frequently asked questions

More comparisons

Benchmark scores sourced from ArtificialAnalysis