Phaseo

Claude Haiku 5.5 vs Claude Opus 5

Pick a route and service tier under each model. Prices, the calculator and the verdicts follow your choice.

Try Claude Haiku 5.5 in Chat
Claude Haiku 5.5
Claude Opus 5

At a glance

Generated from the rows below

Choose Claude Haiku 5.5 for

  • The lowest cost per typical request ($0.0005)

Choose Claude Opus 5 for

  • The most routes on Phaseo: 7

The models are statistically tied on the Epoch Capabilities Index: their 95% confidence intervals overlap.

Overview

Lab
Anthropic
Anthropic
Context window
1Mtokens
1Mtokens
Max output
128Ktokens
128Ktokens
Takes
Text, Image
Text, Image
Returns
Text
Text
Routes on Phaseo
1 provider
7 providers
 (best)
Released
7 Oct 2026
24 Jul 2026

Pricing

Prices on the route and tier chosen under each model

Anthropic · StandardAnthropic · Standard
Input
from $0.10/ 1M tokensInput ≤ 100K$0.10Input ≤ 100K · Region: US$0.11Input > 100K$0.50
$5.00/ 1M tokensRegion: US$5.50
Output
from $0.50/ 1M tokensInput ≤ 100K$0.50Input ≤ 100K · Region: US$0.55Input > 100K$2.50
$25.00/ 1M tokensRegion: US$27.50
Cache read
from $0.01/ 1M tokensInput ≤ 100K$0.01Input ≤ 100K · Region: US$0.011Input > 100K$0.05
$0.50/ 1M tokensRegion: US$0.55
Cache write, 5 minutes
from $0.125/ 1M tokensInput ≤ 100K$0.125Input ≤ 100K · Region: US$0.1375Input > 100K$0.625
$6.25/ 1M tokensRegion: US$6.875
Cache write, 1 hour
from $0.20/ 1M tokensInput ≤ 100K$0.20Input ≤ 100K · Region: US$0.22Input > 100K$1.00
$10.00/ 1M tokensRegion: US$11.00
Typical request2K tokens in, 500 out
$0.0005 (best)
$0.0225

What will it cost?

Estimate a month of requests on the route and tier chosen for each model

ModelPer requestPer month
Claude Haiku 5.5Anthropic · Standard$0.0005$13.50
Claude Opus 5Anthropic · Standard$0.0225$675.00

Uses the route and tier chosen under each model, over 30 days. Cached input is billed at the cache-read rate.

Performance

Live gateway traffic

Latency p50last 24 hours
0.73 s
No traffic in the last 5 days
Throughput p50last 24 hours
5.5 tps
No traffic in the last 5 days
Requests, last 24 hours
6
None in the last 24 hours

Activity

Tokens sent through Phaseo each day over the last 30 days

Tokens, last 30 days
9.75K
No traffic through Phaseo in the last 30 days
Per day
5.04K
7 Oct5 Nov
Input
8.96K
–
Output
788
–
Reasoning
0
–
Requests
44
–

Features

Features from the parameters Phaseo routes support

Tool calling
Yes
Yes
Structured outputs
Yes
Yes
Reasoning effort
Yes
Yes
Web search
Not listed
Yes
Prompt cachingon the chosen route
Yes
Yes
Quantisationon the chosen route
Not stated
Not stated

Benchmarks

Only results that two or more of the selected models report get a row

Compare at effort

Epoch Capabilities Index Independent

Higher is better · dot is the estimate, band is the 95% confidence interval · Epoch AI, CC BY 4.0

Claude Haiku 5.5160.2 95% CI 158.0–162.6
Claude Opus 5164.4 95% CI 162.0–167.2

Every interval overlaps, so these models are statistically tied on this index.

Artificial Analysis Intelligence Index Independent

Higher is better · at Max effort · 2 of 2 models tested

Claude Haiku 5.543.4
Claude Opus 550.8

Where they rank

The five leaders on each capability index, then the compared models. Each model at its best-scoring setting.

Artificial Analysis Intelligence Index52 models ranked

  1. #1Claude Opus 5.559.1
  2. #2GPT-6 Astra56.9
  3. #3GPT-6.1 Sol54.6
  4. #4Claude Sonnet 5.554.5
  5. #5GPT-6.1 Terra51.3
  6. #10Claude Opus 544.2
  7. #14Claude Haiku 5.536.5

Artificial Analysis Coding Index171 models ranked

  1. #1Claude Fable 5.181.6
  2. #2GPT 5.6 Sol78.3
  3. #3Claude Opus 578.0
  4. #4GPT-6 Astra77.1
  5. #5Grok 4.676.8

Artificial Analysis Agentic Index112 models ranked

  1. #1Claude Fable 5.157.9
  2. #2Claude Opus 556.5
  3. #3Qwen 3.8 Max 090256.0
  4. #4Muse Spark 1.355.5
  5. #5Qwen 3.8 Flash Next53.6

Epoch Capabilities Index164 models ranked

  1. #1GPT-6 Astra169.1
  2. #2GPT-6.1 Sol168.9
  3. #3Claude Opus 5.5168.4
  4. #4GPT-6.1 Terra167.8
  5. #5Claude Fable 5.1166.9
  6. #8Claude Opus 5164.4
  7. #14Claude Haiku 5.5160.2
Cost
Artificial Analysis Evaluation Cost (USD)matched by effort level · lower is better
$330.25 (best)
$7,275
Artificial Analysis Evaluation Cost (USD)matched by effort level · lower is better
$339.47 (best)
$9,010
General
Artificial Analysis Intelligence Indexmatched by effort level
36.5
44.2 (best)
Artificial Analysis Progress Index v1matched by effort level
326.1
333.7 (best)

Lab-reported results come from each lab’s own launch materials and may use different settings, so none is marked best. Independent results come from third-party evaluators.

Providers

Where each model runs on Phaseo, with standard-tier prices per 1M tokens. Providers that serve more of these models come first.

Anthropic
$0.10 in · $0.50 out (best)1M context · Standard, Batch
$5.00 in · $25.00 out$10.00 per 1K requests Native web search requests1M context · Standard, Batch, Priority
Amazon Bedrock
—
$5.00 in · $25.00 out1M context
DeepInfra
—
$5.00 in · $25.00 out1M context
Google Vertex
—
$5.00 in · $25.00 out1M context
Inference.net
—
$5.00 in · $25.00 out1M context
Google Vertex (EU)
—
$5.50 in · $27.50 out
Venice
—
$10.00 in · $50.00 out$10.00 per 1K requests Web search1M context · Priority
Also listed, not routed
10 providers
22 providers

To price the whole page on one of these providers, pick it under the model’s name at the top.

Details

Knowledge cutoff
Not published
Jan 2026
Status
Available
Available
Licence
Proprietary
Proprietary
Subscription plans
None mapped
19 plansClaude Enterprise, Claude Max, Claude Max 5x…
API docs
Not published
Not published

Claude Haiku 5.5 vs Claude Opus 5: side-by-side summary

Claude Haiku 5.5 and Claude Opus 5 are both available through the Phaseo API, so switching between them is a change of model id rather than a new integration.

Claude Haiku 5.5 is from Anthropic. It has a 1,000,000-token context window. On its cheapest route it costs $0.10 per 1M input tokens and $0.50 per 1M output tokens.

Claude Opus 5 is from Anthropic. It has a 1,000,000-token context window. On its cheapest route it costs $5.00 per 1M input tokens and $25.00 per 1M output tokens.

Claude Haiku 5.5 model details, providers and pricingClaude Opus 5 model details, providers and pricing

Claude Haiku 5.5 vs Claude Opus 5 at a glance

Claude Haiku 5.5 and Claude Opus 5 compared on price, context window and benchmark score
AttributeClaude Haiku 5.5Claude Opus 5
LabAnthropicAnthropic
Input price per 1M tokens$0.10$5.00
Output price per 1M tokens$0.50$25.00
Context window1,000,000 tokens1,000,000 tokens
Max output128,000 tokens128,000 tokens
Artificial Analysis Intelligence Index36.5 (#14)44.2 (#10)

Prices are each model's cheapest standard route on Phaseo. Benchmark ranks use each model's best-scoring evaluated setting.

Frequently asked questions

Which is cheaper, Claude Haiku 5.5 or Claude Opus 5?

Claude Haiku 5.5 is cheaper for both input and output tokens. Claude Haiku 5.5 costs $0.10 per 1M input tokens and $0.50 per 1M output tokens; Claude Opus 5 costs $5.00 and $25.00, each on its cheapest standard route on Phaseo.

Which has the longer context window, Claude Haiku 5.5 or Claude Opus 5?

Both have a 1,000,000-token context window.

Which scores higher on the Artificial Analysis Intelligence Index, Claude Haiku 5.5 or Claude Opus 5?

Claude Opus 5 scores higher on the Artificial Analysis Intelligence Index. Claude Opus 5 scores 44.2, ranked #10 of 52. Claude Haiku 5.5 scores 36.5, ranked #14 of 52.

Can I use Claude Haiku 5.5 and Claude Opus 5 through one API?

Yes. Both are served through the Phaseo API, so you can switch between them by changing the model id.

Help keep public data accurate

See something missing, incorrect, or out of date? Tell us about this page.