Claude Opus 4.8 API

anthropic/claude-opus-4.8
Across the tested dimensions — coding, agentic task completion, knowledge work, reasoning, and computer use — Opus 4.8 either matches or improves on its predecessor, and frequently outperforms competing frontier models.
Context
1M tokens
Input
$6.877 / 1M tokens
Output
$32.5 / 1M tokens

How to use Claude Opus 4.8 API

Install any OpenAI-compatible SDK, point it at api.aimlapi.com/v1, and set the model to anthropic/claude-opus-4.8.
import requests

r = requests.post(
    "https://api.aimlapi.com/v1/chat/completions",
    headers={"Authorization": "Bearer " + AIMLAPI_KEY},
    json={
      "model": "anthropic/claude-opus-4.8",
      "messages": [
        {
          "role": "user",
          "content": "Hello!"
        }
      ]
    },
)
print(r.json())
const r = 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": "Hello!"
      }
    ]
  }),
});
console.log(await r.json());
curl -X POST 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":"Hello!"}]}'

OpenAI-compatible — swap the base URL and it works with your existing SDK.

Claude Opus 4.8 API Pricing

TypePrice
Input
$6.877 / 1M tokens
Output
$32.5 / 1M tokens
Cached input
$0.6877 / 1M tokens

Claude Opus 4.8 Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
OSWorld
83.4%
Computer-use across real desktop applicationsSourceJuly 8, 2026
GPQA Diamond
93.6%
Google-proof graduate science questions (hardest subset)SourceJuly 8, 2026
Terminal-Bench
74.6%
Autonomous shell/terminal task completionSourceJuly 8, 2026
SWE-bench Verified
88.6%
Resolving verified real GitHub issuesSourceJuly 8, 2026
Intelligence
42
Composite score across standardised reasoning, knowledge and problem-solving evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026
Coding
74.3
Composite score across standardised coding evaluations, measured independently by Artificial AnalysisSourceSeptember 12, 2026

Claude Opus 4.8 vs other models

ModelInputOutputContextBest for
$6.877 / 1M tokens
$32.5 / 1M tokens
1M tokens
Chat + assistants
$6.5 / 1M tokens
$39 / 1M tokens
1.05M tokens
Reasoning + agents
$2.6 / 1M tokens
$13 / 1M tokens
1M tokens
Balanced coding + agents
$3.9 / 1M tokens
$19.5 / 1M tokens
1M tokens
Long-context, multimodal & agentic workflows
$0.65 / 1M tokens
$3.9 / 1M tokens
1.05M tokens
Reasoning + agents

Frequently asked questions

No items found.

Start building with Claude Opus 4.8

Get API Key
1000+ models, one API.