Speed
Output tokens / second
Claude Opus 4.8 overview
Claude Opus 4.8 by Anthropic
Sharper reasoning, more honest output, and the best agentic performance the company has shipped.
Claude Opus 4.8 specs
- Model ID
anthropic/claude-opus-4.8- 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 |
Use cases
Claude Opus 4.8 is documented as suited to coding, especially navigating real codebases, planning before editing, and maintaining context across long sessions.
It is also documented as suited to agentic workflows and long-running agents, where it can handle multi-step tool use, complex dependency chains, and extended tasks with less oversight.
Claude Opus 4.8 is documented as suited to professional work and enterprise workflows, including synthesizing long, complex sources into briefs, analyses, reports, and other polished deliverables.
It is additionally documented as suited to financial analysis and cybersecurity, including investment research and earnings analysis, as well as threat intelligence synthesis, vulnerability finding, and incident response.
Capabilities
- Function calling
- Streaming
- Structured outputs
- Reasoning
- Web search
Claude Opus 4.8 benchmarks by 
Artificial Analysis
See how Claude Opus 4.8 compares in generation speed and latency. Data retrieved Nov 4, 2026.
Benchmark results
Compare 8 models available on AI/ML API across 5 independent benchmarks.
Humanity's Last Exam
Expert-written questions across academic subjects.
GPQA Diamond
Graduate-level science questions written to resist web search.
Terminal-Bench 4.0
Agentic tasks completed in a command-line environment.
AA-LCR
Reasoning across long documents of about 100k tokens.
SciCode
Python coding tasks drawn from scientific research.
Claude Opus 4.8 API pricing
| Usage | Price | Unit |
|---|---|---|
| Input | $5 | 1M tokens |
| Output | $25 | 1M tokens |
| Cached input | $0.529 | 1M tokens |
Prices from the AI/ML API price list, checked on Nov 4, 2026.
Claude Opus 4.8 vs other models: token prices
AI/ML API input and output rates for 5 models, per million tokens.
| Model | Input | Output |
|---|---|---|
 Claude Opus 4.8 | $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 4.8 API
View docs
Build with your agent
Give your agent the model details, code and documentation.
Paste it into your coding agent to build the integration.
1Get your API key
Create API keyexport 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-4.8",
"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-4.8",
"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-4.8",
"messages": [
{
"role": "user",
"content": "Write a haiku about the ocean."
}
]
}),
});
if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());Models similar to Claude Opus 4.8
Related articles
Claude Opus 4.8 FAQ
How much does Claude Opus 4.8 cost?
Claude Opus 4.8 costs $5 input and $25 output per 1M tokens on AI/ML API, billed as you go with no subscription.
What is the Claude Opus 4.8 model ID?
Use anthropic/claude-opus-4.8 as the model parameter. Requests go to the OpenAI-compatible endpoint with your AI/ML API key.
What is the context window of Claude Opus 4.8?
Claude Opus 4.8 accepts up to 1,000,000 tokens of context and returns up to 128,000 output tokens.