anthropic
Claude Opus 5.5
Claude Opus 5.5 is a step-change improvement over Opus 5 for agentic coding, long-running agentic tasks, knowledge work, communication, and vision. It is more token-efficient per completed task and reports progress, findings, and next steps in clear language.
explicit cachingfastfile inputreasoningtool usevisionweb searchstructured outputtextimagepdf
Overview
- Type
- language
- Context
- 1M
- Max output
- 128K
- Input / output
- text, image, pdf / text
API
Model identifier
anthropic/claude-opus-5.5Providers and live performance
Rolling Gateway metrics. Latency is time to first token; throughput is output tokens per second.
| Provider | Status | Latency | Throughput | Uptime 15m / 1h / 1d | Input | Output | Cache read / write | Discount | Regions | ZDR | No training |
|---|---|---|---|---|---|---|---|---|---|---|---|
| anthropic | Operational | 1.20s / 4.09s | 291.5 / 331.0 tok/s | 100.00% / 99.99% / 99.98% | $4.00/M | $20.00/M | $0.20/M / $5.00/M | — | us | Yes | Yes |
| bedrock | Operational | 2.21s / 5.55s | 129.0 / 137.7 tok/s | 100.00% / 100.00% / 99.99% | $4.00/M | $20.00/M | $0.20/M / $5.00/M | — | us, eu-central-1, ap-southeast-2, ap-northeast-1 | Yes | Yes |
| claudeaws | Operational | 3.09s / 5.80s | 116.0 / 151.1 tok/s | 100.00% / 100.00% / 100.00% | $4.00/M | $20.00/M | $0.20/M / $5.00/M | — | — | Yes | Yes |
| vertexAnthropic | Operational | 1.57s / 6.85s | 121.0 / 128.4 tok/s | 100.00% / 100.00% / 99.98% | $4.00/M | $20.00/M | $0.20/M / $5.00/M | — | us, eu | Yes | Yes |
Pricing
input
0.000004
output
0.00002
input cache read
0.0000002
input cache write
0.000005
web search
10
fast
{
"input": "0.000008",
"output": "0.00004",
"input_cache_read": "0.0000004",
"input_cache_write": "0.00001"
}
regional
{
"au": {
"input": "0.0000044",
"output": "0.000022",
"input_cache_read": "0.00000022",
"input_cache_write": "0.0000055"
},
"eu": {
"input": "0.0000044",
"output": "0.000022",
"input_cache_read": "0.00000022",
"input_cache_write": "0.0000055"
},
"jp": {
"input": "0.0000044",
"output": "0.000022",
"input_cache_read": "0.00000022",
"input_cache_write": "0.0000055"
},
"us": {
"input": "0.0000044",
"output": "0.000022",
"input_cache_read": "0.00000022",
"input_cache_write": "0.0000055",
"fast": {
"input": "0.0000088",
"output": "0.000044",
"input_cache_read": "0.00000044",
"input_cache_write": "0.000011"
}
}
}
Capabilities
explicit cachingfastfile inputreasoningtool usevisionweb searchstructured outputtextimagepdf
Supported parameters
max tokens
Yes
stop
Yes
tools
Yes
tool choice
Yes
reasoning
Yes
include reasoning
Yes
response format
Yes
structured outputs
Yes
Reasoning options
options
{
"type": "effort",
"values": [
"low",
"medium",
"high",
"xhigh",
"max"
]
}
Metadata
type
language
context window
1M
max output
128K
knowledge cutoff
2026-06
released
Sep 22, 2026
temperature control
No
zero data retention
all
no training
all
regions
au, eu, jp, us
api specifications
v2, v3, v4