By the toolist.ai editors. Researched from public sources, not hands-on tested by toolist.ai. Updated November 3, 2026; prices checked November 3, 2026.
Claude Haiku 5.5 vs Claude Sonnet 5.5
Verdict
Use Claude Sonnet 5.5 for coding and agent work, and Claude Haiku 5.5 for high-volume, narrowly scoped jobs. Haiku costs a twentieth of Sonnet's token price on prompts up to 100,000 tokens ($0.10 and $0.50 against $2 and $10 per million), but Sonnet scores higher on all five Artificial Analysis scores both have, including 64% against 33% on Terminal-Bench 4.0. Above 100,000 prompt tokens Haiku's price rises fivefold, so Sonnet costs four times as much rather than twenty.
Verdict based on published prices, limits and benchmarks, not on our own tests.
Choose Claude Haiku 5.5 if
- You run high-volume, latency-sensitive jobs such as classification, extraction or routing
- Your prompts stay under 100,000 tokens: Haiku's input and output prices are a twentieth of Sonnet's
- You want a fast subagent for summaries or compaction under Sonnet or Opus, which Anthropic suggests
- Speed matters more than depth: Artificial Analysis measures 168.2 output tokens a second at medium effort against 103 for Sonnet at high
Choose Claude Sonnet 5.5 if
- You do everyday coding and agent work, where Sonnet scores 64% against 33% on Terminal-Bench 4.0
- Your prompts often pass 100,000 tokens, since Sonnet has no long-context surcharge
- You need the stronger reasoning model at the everyday setting: 42 against 25 on the Intelligence Index at each model's default effort
Price
Input costs 20 times as much on Claude Sonnet 5.5 as on Claude Haiku 5.5. Output costs 20 times as much on Claude Sonnet 5.5 as on Claude Haiku 5.5.
| Per million tokens | Claude Haiku 5.5 | Claude Sonnet 5.5 |
|---|---|---|
| Input | $0.10 source | $2 source |
| Cached input | $0.01 source | $0.10 source |
| Output | $0.50 source | $10 source |
Claude Haiku 5.5: Prompts over 100,000 tokens are billed at $0.50 in, $2.50 out and $0.05 for cache reads per million tokens for the whole request; the prompt length counts cache reads and writes. Cache writes cost $0.125 per million tokens (5-minute cache) or $0.20 (1-hour cache), or $0.625 and $1 for prompts over 100,000 tokens. The Batch API costs half.
Claude Sonnet 5.5: Cache writes cost $2.50 per million tokens (5-minute cache) or $4 (1-hour cache). The Batch API costs half. There is no long-context surcharge and no fast mode.
Worked example: what a month costs
We priced three monthly workloads at the standard rates. The provider does not publish these figures.
| Workload | Claude Haiku 5.5 | Claude Sonnet 5.5 |
|---|---|---|
| Support chatbot 100,000 replies, each 3,000 input and 400 output tokens, no caching (300M in, 40M out) | $50.00 | $1,000 |
| Document Q&A 5,000 questions over the same 60,000-token document set (90% cache hits), 800 output tokens each (300M in, 4M out) | $7.70 | $127 |
| Coding agent 200 tasks, each 1.5 million input tokens (90% cache hits) and 50,000 output tokens (300M in, 10M out) | $10.70 | $187 |
Price your own workload
| Model | Cost a month |
|---|---|
| Claude Haiku 5.5 | $7.50 |
| Claude Sonnet 5.5 | $150 |
Standard API prices, no batch or priority discounts. Cached input is billed at the cache-read price; cache-write charges are not included. Reasoning models bill their thinking as output tokens.
Limits and release dates
| Claude Haiku 5.5 | Claude Sonnet 5.5 | |
|---|---|---|
| Released | October 7, 2026 source | September 28, 2026 source |
| Context window | 1,000,000 tokens source | 1,000,000 tokens source |
| Maximum output | 128,000 tokens source | 128,000 tokens source |
| Knowledge cutoff | June 2026 source | June 2026 source |
| Input and output | Text and images in; text out source | Text and images in; text out source |
| API model name | claude-haiku-5-5 | claude-sonnet-5-5 |
Benchmarks
Scores as published by the provider or measured by Artificial Analysis; higher is better. A dash means no score was published.
| Benchmark | Claude Haiku 5.5 | Claude Sonnet 5.5 |
|---|---|---|
| Artificial Analysis Intelligence Index max effort | 36.0 source | 55.0 source |
| Intelligence Index at everyday effort | 25.0 (medium effort, the API default) source | 42.0 (high effort, the API default) source |
| Terminal-Bench 4.0 max effort | 33.0% source | 64.0% source |
| HLE-Diamond max effort | 30.0% source | 53.0% source |
| Terminal-Bench-Science 0.1 max effort | 20.0% source | 53.0% source |
| Output speed | 168.2 tokens/s (medium effort, Artificial Analysis) source | 103 tokens/s (high effort, Artificial Analysis) source |
Benchmark and speed data from Artificial Analysis where linked.
Read more
- Claude Haiku 5.5: price, context window and benchmarks
- Claude Sonnet 5.5: price, context window and benchmarks
- Claude Opus 5.5 vs Claude Sonnet 5.5
- GPT-6.1 Sol vs Claude Sonnet 5.5
- GPT-6.1 Terra vs Claude Sonnet 5.5
- GPT-6 Luna vs Claude Haiku 5.5
- AI model API price table
Sources
- Claude Haiku 5.5 vs Claude Sonnet 5.5 (checked 2026-11-03)
- Anthropic: Introducing Claude Haiku 5.5 (checked 2026-10-21)
- Claude docs: Claude Haiku 5.5 (checked 2026-10-21)
- Claude docs: What's new in Claude Haiku 5.5 (checked 2026-10-21)
- Claude docs: Effort (checked 2026-10-21)
- Claude docs: Pricing (checked 2026-11-03)
- Claude plans and pricing (checked 2026-10-21)
- Claude docs: API and data retention (checked 2026-10-21)
- Claude Haiku 5.5 (max) (checked 2026-11-03)
- Claude Haiku 5.5 (medium) (checked 2026-11-03)
- OpenRouter: Claude Haiku 5.5 (checked 2026-11-03)
- Anthropic: Introducing Claude Sonnet 5.5 (checked 2026-10-21)
- Claude docs: Claude Sonnet 5.5 (checked 2026-10-21)
- Claude docs: What's new in Claude Sonnet 5.5 (checked 2026-10-21)
- Artificial Analysis: Claude Sonnet 5.5 (max) (checked 2026-11-03)
- Artificial Analysis: Claude Sonnet 5.5 (high) (checked 2026-11-03)
- Artificial Analysis: GPT-6.1 Sol vs Claude Sonnet 5.5 (checked 2026-11-03)
- OpenRouter: Claude Sonnet 5.5 (checked 2026-11-03)