Claude Opus 5 API

Claude Opus 5 is ideal for complex agentic coding and enterprise work. Features a 1M token context window, adaptive thinking, and top-tier performance across long-horizon agentic tasks, knowledge work, and vision.

Modalities: Text, ImageText
In / Out price: $5/$25per 1M
Context window: 1M tokens
Released: Jul 24, 2026

Claude Opus 5 overview

Claude Opus 5 by Anthropic

Sharper reasoning, more honest output, and the best agentic performance the company has shipped.1

Claude Opus 5 specs

Model ID: anthropic/claude-opus-5
Developer: Anthropic
Context window: 1,000,000 tokens
Max output: 128,000 tokens
Input: Text, Image
Output: Text
API: OpenAI-compatible, base URL https://api.aimlapi.com/v1

What is Claude Opus 4.8?

Claude Opus 4.8 is the latest version of Anthropic's top-tier AI model, succeeding Claude Opus 4.7. Rather than a ground-up redesign, it represents a focused, meaningful upgrade, one that compounds on strong foundations with measurable improvements across coding, reasoning, agentic reliability, and what Anthropic calls honesty: the model's willingness to surface uncertainty rather than paper over gaps with confident-sounding approximations.

‍4× Less likely to overlook flaws in its own generated code versus Opus 4.7‍
84% Online-Mind2Web score best computer-use and browser-agent result tested‍
>10% Legal Agent Benchmarkfirst model to break this threshold on all-pass standard

Coding and software engineering

Multiple engineering teams report that Opus 4.8 is more reliable as an autonomous coding assistant. It asks sharper clarifying questions before making large changes, pushes back when plans seem flawed, and catches more of its own mistakes before they propagate. On CursorBench, a rigorous evaluation from the Cursor team covering full end-to-end development tasks, Opus 4.8 outperformed all prior Opus models at every effort level. Tool calling is more efficient too, completing the same work with fewer intermediate steps.

Agentic task completion

In complex, multi-step autonomous workflows, Opus 4.8 shows the reliability characteristics that production AI agent deployments depend on. On a Super-Agent benchmark developed by one external partner, it was the only model to complete every case end-to-end, outperforming prior Opus versions and GPT-5.5 at equivalent cost. It's consistently better at carrying context across long sessions and following stylistic or technical direction without drift.

Legal and professional knowledge work

Opus 4.8 is the first model to surpass 10% on the all-pass standard of the Legal Agent Benchmark, a significant threshold in an industry where accuracy errors carry real professional consequences. Multiple legal AI platforms report that the improvement in consistency and reasoning quality translates directly into confidence about which attorney tasks can be delegated to AI-assisted workflows.

Computer use and browser automation

With an 84% score on Online-Mind2Web, Opus 4.8 ranks as the strongest computer-use and browser-agent model tested by any external team at launch. It maintains focus across long, complex web-based tasks in ways that directly benefit real-world automation pipelines.

Financial analysis

For financial document workflows, processing dense filings, earnings reports, and structured data, Opus 4.8 maintains the quality of Opus 4.7 while improving citation precision, reducing token consumption on retrieval tasks, and proactively flagging anomalies in inputs and outputs that other models left for human reviewers to catch.

Benchmark	Focus Area	Opus 4.8 Result
Online-Mind2Web	Browser agent and computer-use capability	84%
Legal Agent Benchmark (all-pass)	Legal reasoning accuracy and reliability	>10%
CursorBench	End-to-end software development workflows	Best-in-class
Super-Agent Benchmark	Complex multi-step agentic execution	100% completion
Code flaw detection	Honesty, verification, and error detection	4× fewer missed flaws

Mid-Task System Prompt Updates

The Messages API now accepts system entries inside the messages array, not just at the top level. Developers can update Claude's instructions mid-task, changing permissions, token budgets, or environmental context, without breaking the prompt cache or routing the update through a user turn. This makes it substantially easier to build sophisticated, adaptive agent harnesses.

Who is Opus 4.8 built for?

Opus 4.8 is Anthropic's flagship model, positioned for work where quality is the primary constraint and cost is secondary. It's the right choice when you're building production-grade AI agents, handling high-stakes professional knowledge work, or need a model that can sustain coherent context and judgment across very long sessions.

Software engineering teams building autonomous coding agents or running large-scale codebase migrations with Claude Code
Legal technology companies where citation precision, reasoning quality, and accuracy thresholds matter at the case level
Financial services platforms processing dense unstructured documents where the model needs to flag its own uncertainties
AI product teams building multi-step agentic pipelines that run autonomously for extended periods
Enterprise research and analysis workflows requiring high-density, reliable outputs across long context windows
Multimodal document workflows , Opus 4.8 reasons over PDFs, diagrams, and unstructured visual content at 61% lower token cost than Opus 4.7

Is Claude Opus 4.8 better than GPT-5.5?

On agentic benchmarks, Opus 4.8 outperforms GPT-5.5 in specific evaluations: one external partner's Super-Agent benchmark showed Opus 4.8 completing every case that GPT-5.5 could not, at cost parity. On computer use (Online-Mind2Web), Opus 4.8's 84% score beats GPT-5.5's reported result on the same evaluation. Comparative performance varies by task type; users with specific workloads should run their own evaluations.

What changed from Opus 4.7 to Opus 4.8?

The headline improvements are better honesty (Opus 4.8 flags uncertainties and code flaws at a significantly higher rate), improved judgment in autonomous tasks, more efficient tool calling, and better alignment scores. Verbose comment generation and tool-calling inconsistencies reported with Opus 4.7 are addressed in this release.

What is dynamic workflows in Claude Code?

Dynamic workflows let Claude plan a large software task and then execute it by spinning up hundreds of parallel subagents within a single Claude Code session. It verifies its outputs before surfacing results. It's currently in research preview and available on Enterprise, Team, and Max plans.

How does Opus 4.8 compare on multimodal tasks?

Opus 4.8 can reason over PDFs, diagrams, charts, and other unstructured visual content. For document-heavy workflows, it delivers this at a 61% lower token cost compared to Opus 4.7, according to one enterprise data platform's internal benchmarks.

Use cases

Claude Opus 5 is documented as suited to scientific research, particularly where deeper reasoning is helpful. It is also described as a strong fit for secure coding, including scanning source code for vulnerabilities, triaging security issues, and building secure code.

For professional and enterprise work, it is suited to complex analysis of long, document-heavy inputs, especially tasks that require higher accuracy and structured reasoning. It is also documented for agentic workflow automation, where it can break complex jobs into sub-agents and handle multi-step work with less oversight.

Capabilities

Function calling
Streaming
Structured outputs
Reasoning
Web search

Claude Opus 5 benchmarks by Artificial Analysis

See how Claude Opus 5 compares in generation speed. Data retrieved Nov 3, 2026.

Speed#169 / 21954.1Output tokens / second Humanity's Last Exam#6 / 45854.9%Score GPQA Diamond#12 / 43993.2%Score Terminal-Bench 4.0#12 / 15449%Score

Speed

Output tokens / second

Benchmark results

Compare 8 models available on AI/ML API across 5 independent benchmarks.

Humanity's Last Exam

Expert-written questions across academic subjects.

Claude Opus 5 API pricing

Claude Opus 5 pricing in US dollars
Usage	Price	Unit
Input	$5	1M tokens
Output	$25	1M tokens
Cached input	$0.5	1M tokens

Prices from the AI/ML API price list, checked on Nov 4, 2026.

Claude Opus 5 vs other models: token prices

AI/ML API input and output rates for 5 models, per million tokens.

AI/ML API model prices in USD per million tokens
Model	Input	Output
Claude Opus 5	$5	$25
Claude Haiku 5.5	$0.1	$0.5
Claude Sonnet 5.5	$2	$10
Claude Opus 5.5	$4	$20
Claude Fable 5.1	$10	$50

How to use the Claude Opus 5 API

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "anthropic/claude-opus-5",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "anthropic/claude-opus-5",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "anthropic/claude-opus-5",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

All posts

Claude Opus 5 FAQ

What is the context window of Claude Opus 5?

Claude Opus 5 has a 1,000,000 tokens context window and can return up to 128,000 tokens.

What inputs and outputs does Claude Opus 5 support?

Claude Opus 5 takes text as input and returns text.

What is the model ID for Claude Opus 5?

Use anthropic/claude-opus-5 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

When was Claude Opus 5 released?

Claude Opus 5 became available on July 24, 2026.

How much does Claude Opus 5 cost?

Claude Opus 5 costs $5 input and $25 output per 1M tokens on AI/ML API, billed as you go with no subscription.

Does Claude Opus 5 support streaming?

Yes, Claude Opus 5 can stream responses as they are generated.

Can Claude Opus 5 read images?

Yes, Claude Opus 5 accepts image input alongside text.

Who created Claude Opus 5?

Claude Opus 5 was built by Anthropic.

Start building with Claude Opus 5

Get API key

Claude Opus 5 API

anthropic/claude-opus-5

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl 'https://api.aimlapi.com/v1/chat/completions' \
  -H "Authorization: Bearer $AIMLAPI_KEY" \
  -H 'Content-Type: application/json' \
  -d '{
  "model": "anthropic/claude-opus-5",
  "messages": [
    {
      "role": "user",
      "content": "Write a haiku about the ocean."
    }
  ]
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "anthropic/claude-opus-5",
    "messages": [
        {
            "role": "user",
            "content": "Write a haiku about the ocean."
        }
    ]
}

response = requests.post("https://api.aimlapi.com/v1/chat/completions", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "anthropic/claude-opus-5",
    "messages": [
      {
        "role": "user",
        "content": "Write a haiku about the ocean."
      }
    ]
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Claude Opus 5 API

Claude Opus 5 overview

Claude Opus 5 by Anthropic

Claude Opus 5 specs

What is Claude Opus 4.8?

Coding and software engineering

Agentic task completion

Legal and professional knowledge work

Computer use and browser automation

Financial analysis

Mid-Task System Prompt Updates

Who is Opus 4.8 built for?

Is Claude Opus 4.8 better than GPT-5.5?

What changed from Opus 4.7 to Opus 4.8?

What is dynamic workflows in Claude Code?

How does Opus 4.8 compare on multimodal tasks?

Use cases

Capabilities

Speed

Benchmark results

Humanity's Last Exam

GPQA Diamond

Terminal-Bench 4.0

AA-LCR

SciCode

Claude Opus 5 API pricing

Claude Opus 5 vs other models: token prices

How to use the Claude Opus 5 API

Build with your agent

1Get your API key

2Make your first request

Models similar to Claude Opus 5

Claude Haiku 5.5

Claude Sonnet 5.5

Claude Opus 5.5

GPT-5.5

Fugu Ultra v2

Fugu Ultra

Related articles

Best AI Models for Agentic Workflows and Tool Use in 2026

Best LLMs for Long-Context & Multimodal Tasks in 2026

Claude Opus 5 FAQ

Start building with Claude Opus 5