Claude Opus 4.8 (Fast) API

anthropic/claude-opus-4.8-fast
Claude Opus 4.8 (Fast) is Anthropic's fast-mode configuration of Opus 4.8, running at roughly 2.5x the speed of the standard model.
Context
1M tokens
Input
$13.754 / 1M tokens
Output
$68.77 / 1M tokens
Released
May 27, 2026

How to use Claude Opus 4.8 (Fast) API

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

import requests

r = requests.post(
   "https://api.aimlapi.com/v1/chat/completions",
   headers={"Authorization": "Bearer " + AIMLAPI_KEY},
   json={
     "model": "anthropic/claude-opus-4.8-fast",
     "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-fast",
    "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-fast","messages":[{"role":"user","content":"Hello!"}]}'

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

Claude Opus 4.8 (Fast) API Pricing

TypePrice
Input
$13.754 / 1M tokens
Output
$68.77 / 1M tokens
Cached input
$1.3754 / 1M tokens

Fast mode for Claude Opus 4.8 is a research preview, is available only on the Claude API (first-party), and its pricing stacks with prompt caching and data residency multipliers; it is not available with the Batch API.

Claude Opus 4.8 (Fast) Benchmarks

BenchmarkScoreWhat it measuresSourceRetrieved
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 (Fast) vs other models

ModelInputOutputContextBest for
$13.754 / 1M tokens
$68.77 / 1M tokens
1M tokens
Agentic workflows and structured output
$6.5 / 1M tokens
$32.5 / 1M tokens
1M tokens
Complex agentic coding and enterprise workflows
$6.5 / 1M tokens
$32.5 / 1M tokens
1M tokens
Chat + assistants
$13 / 1M tokens
$65 / 1M tokens
1M tokens
Chat + assistants

Frequently asked questions

Claude Opus 4.8 (Fast) has a 1,000,000 tokens context window and can return up to 128,000 tokens.

Claude Opus 4.8 (Fast) takes image, text as input and returns text.

Use anthropic/claude-opus-4.8-fast as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.

Claude Opus 4.8 (Fast) became available on May 27, 2026.

Claude Opus 4.8 (Fast) is priced at input $13.754 / 1M tokens, output $68.77 / 1M tokens, cached input $1.3754 / 1M tokens.

Yes, Claude Opus 4.8 (Fast) can stream responses as they are generated.

Yes, Claude Opus 4.8 (Fast) accepts image input alongside text.

Claude Opus 4.8 (Fast) was built by Anthropic.

Start building with Claude Opus 4.8 (Fast)

Get API Key
1000+ models, one API.