Anthropic: Claude Opus 5.5

anthropic/claude-opus-5-5

Anthropic Claude Opus 5.5 API pricing

Claude Opus 5.5 costs $1.60 per million input tokens and $8.00 per million output tokens on Oxyy. These are the pay-as-you-go prices after the current 60% discount (Launch Promo; standard price $4.00 input and $20.00 output), and cached input tokens are billed at $0.080 per million. It accepts text and images and returns text, with a 1M-token context window and up to 128K output tokens per response. A cheaper Anthropic option is Claude Sonnet 4.5 at $1.20 / $6.00 per 1M tokens; for every model and rate, see Claude API pricing.

Built for long-running agentic coding and knowledge work. Anthropic's current default flagship.

ModalitiesTextImageText
Price$1.60 / $8.00 per 1M tokens in / outAll Claude API pricing
Context1M
ReleasedSep 22, 2026

Providers

Where this model runs, and what each route costs. Requests are sent to a healthy provider automatically; if one errors, the gateway retries against another serving the same model.

ProviderInput /MOutput /MCache read /MLatencyThroughput
Anthropic$1.60$8.00$0.08025.96s146 tps

Capabilities (21)

StreamingTool callingParallel tool callsStructured outputThinkingReasoningSystem promptVisionMultilingualPrompt cachingBatchFast ModeWeb searchWeb FetchCode executionComputer useBrowser UseBash ToolText Editor ToolManaged AgentsData Residency

Supported parameters (14)

modelmessagesmax_tokenssystemstreamstop_sequencestoolstool_choiceeffortspeedinference_georesponse_formatstopreasoning_effort

Any other parameter you send is ignored rather than rejected.

Pricing

What this model costs on Oxyy, pay as you go. "Charged" is the rate a request is billed at; the standard price is shown beside it for reference.

Input price
$1.60
per 1M input tokens · standard price $4.00
Output price
$8.00
per 1M output tokens · standard price $20.00
RateStandard priceChargedUnit
Input$4.00$1.60per 1M input tokens
Output$20.00$8.00per 1M output tokens
Cached input$0.200$0.080per 1M cached input tokens
Cache write (5 min)$5.00$2.00per 1M cache-write tokens, 5-minute
Cache write (1 hour)$8.00$3.20per 1M cache-write tokens, 1-hour

Discount. Charged rates include the current "Launch Promo" discount of 60% on every rate.

UTC

Specifications

Model ID
claude-opus-5-5
Developer
Anthropic
Type
Text
Input
Text and images
Output
Text
Context window
1,000,000 tokens
Max output
128,000 tokens
Knowledge cutoff
June 2026
Released
Sep 22, 2026
Tokenizer
Claude
Series
Claude 5.5
Image input
Up to 20 MB each · PNG, JPEG, WebP, GIF
Endpoint
/v1/chat/completions
Status
Deprecation scheduled for Sep 22, 2027

Best for

Agentic codingKnowledge workLong horizon tasks

Quickstart

Call claude-opus-5-5 with a POST to /v1/chat/completions on https://api.oxyy.ai, using your Oxyy API key from the OXYY_API_KEY environment variable. The same key works for every model in the catalog.

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.oxyy.ai/v1",
    api_key=os.environ["OXYY_API_KEY"],
)

response = client.chat.completions.create(
    model="claude-opus-5-5",
    messages=[
        {"role": "user", "content": "Explain unified AI APIs in one sentence."},
    ],
)
print(response.choices[0].message.content)

Performance

Throughput is how fast the model writes (tokens per second — higher is better). Latency is total round-trip time (lower is better). TTFT is time-to-first-token — how long before you see anything appear (lower is better). Throughput and TTFT are measured on streaming requests, which are the only ones with a first-token moment to time.

Throughput
146tok/s
P50, streaming requests
Latency
25.96s
P50, end to end
UTC

Throughput

P992935054 tok/s
P956338 tok/s
P50147 tok/s

Latency

P5027.9s
P7568.7s
P95158.4s
P99275.2s

Time to first token

P509736ms
P9595.3s

Cache hit rate

52.80%
Share of input tokens served from the prompt cache over the window.

Availability

The share of requests to this model that completed successfully over the last 30 days. When an upstream provider errors, the gateway retries against another provider serving the same model, so a single provider incident does not necessarily show up here.

Success rate (30 days)
83.40%
over 8,772 requests
Days with traffic
9
of the last 30 days

Days are UTC days. Days with no completed requests are omitted rather than drawn at 100% — no traffic is not evidence of availability.

Activity

Token volume and request traffic to this model over time. Daily totals, UTC.

Prompt373.4M
Reasoning9.1M
Completion30.7M

Prompt tokens measure input size. Reasoning tokens show internal thinking before a response. Completion tokens reflect total output length.

Frequently asked questions

What is Claude Opus 5.5?
Built for long-running agentic coding and knowledge work. Anthropic's current default flagship.
How much does Claude Opus 5.5 cost?
Claude Opus 5.5 costs $1.60 per million input tokens and $8.00 per million output tokens on Oxyy. These are the pay-as-you-go prices after the current 60% discount (Launch Promo; standard price $4.00 input and $20.00 output), and cached input tokens are billed at $0.080 per million. You pay per request, with no subscription.
What is the context length of Claude Opus 5.5?
Claude Opus 5.5 has a context window of 1,000,000 tokens, and can return up to 128,000 tokens in one response.
Does Claude Opus 5.5 support tool calling and structured outputs?
Yes — Claude Opus 5.5 supports both tool calling and structured outputs.
What inputs and outputs does Claude Opus 5.5 support?
Claude Opus 5.5 accepts text and images as input and returns text.
Which API endpoint does Claude Opus 5.5 use?
Send a POST request to https://api.oxyy.ai/v1/chat/completions with "model": "claude-opus-5-5", authenticated with your Oxyy API key.
What is the knowledge cutoff of Claude Opus 5.5?
Claude Opus 5.5's training data runs up to June 2026.
When was Claude Opus 5.5 released?
Claude Opus 5.5 was released on Sep 22, 2026.
What other models does Anthropic have?
Anthropic also offers Claude Fable 5, Claude Fable 5.1, Claude Haiku 4.5 and Claude Opus 4.5 through Oxyy.

Alternatives to Claude Opus 5.5

Models of the same kind from other vendors, closest in price first. Prices are pay-as-you-go on Oxyy, through the same API key.

Explore more models

More models from Anthropic