Skip to content
Pricing
Anthropic

Claude Opus 4.8 API

Claude Opus 4.8 is a legacy Opus model supporting adaptive reasoning for complex analysis and professional tasks.

MODALITIES
TextText
Available
INPUT / OUTPUT70% OFF
$1.5/ 1M
/
$7.5/ 1M
USD per million tokens
CACHED INPUT
$0.15/ 1M
Platform price · USD
CONTEXT WINDOW
1,000,000tokens
Max output: 128,000 tokens
Input
Sign in to choose a key from your account.
Choose a level supported by this model. Default keeps the model’s own settings; thinking also consumes output tokens.
Advanced request options are available in JSON mode.
Request preview
{
  "model": "claude-opus-4-8",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "A quiet mountain lake at sunrise, soft morning light."
    }
  ],
  "stream": true
}
Output

Your next idea starts here.

Run the model to preview your result.

API Usage Examples

API documentation ↗
POSTGet API Key ↗
curl 'https://newrouters.com/v1/messages' \
  -H "Content-Type: application/json" \
  -H "x-api-key: $MODEL_API_KEY" \
  -H "anthropic-version: 2023-06-01" \
  --data '{
  "model": "claude-opus-4-8",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Explain how an HTTP request works in three concise steps."
    }
  ],
  "stream": false
}'

Set MODEL_API_KEY in your server environment. Requests use this model’s native API and your account pricing.

Docs: authentication and keys · Error handling

Claude Opus 4.8 pricing

Estimate one request, then choose a budget for your workflow.

UsageQuantityRateCost
tokens$1.5/ 1M$0.0015
tokens$0.15/ 1M$0
tokens$1.875/ 1M$0
tokens$3/ 1M$0
tokens$7.5/ 1M$0.00375
tokens$7.5/ 1M$0
Cost per request$0.00525

Public USD estimate. Your account rate and final recorded usage determine the actual charge.

Model pricing details
SpecificationOur priceOfficial reference
Input$1.5 / 1M tokens$5 About 70% less than official
Cached input$0.15 / 1M tokens$0.5 About 70% less than official
Cache write · 5m$1.875 / 1M tokens$6.25 About 70% less than official
Cache write · 1h$3 / 1M tokens$10 About 70% less than official
Output$7.5 / 1M tokens$25 About 70% less than official
Reasoning$7.5 / 1M tokens$25 About 70% less than official

Claude Opus 4.8 API · Examples

Original prompts adapted to documented capabilities; these are not vendor-generated outputs.

Official source ↗ · 2026-10-14

EXAMPLE PROMPT

Infer the failure chain from these logs. Separate observations from possible causes and propose a low-risk verification order. Logs: [paste redacted logs]

USER MESSAGE
01

Structured analysis

Tie diagnostic conclusions to log evidence and prioritize low-risk checks.

EXAMPLE PROMPT

Draft a technical proposal from these project notes. Separate facts, assumptions and open questions; include goals, implementation and acceptance criteria. Notes: [paste notes]

USER MESSAGE
02

Professional document draft

Turn project notes into goals, implementation steps and acceptance criteria.

What Is Claude Opus 4.8?

Claude Opus 4.8 is a legacy Opus model supporting adaptive reasoning for complex analysis and professional tasks.

Official model information ↗ · 2026-10-14

Claude Opus 4.8 Platform specifications

SpecificationClaude Opus 4.8
Model IDclaude-opus-4-8
ProviderAnthropic
API/v1/messages
Context window1,000,000 tokens
Maximum output128,000 tokens
Declared capabilitiesTools · Streaming · Reasoning · Structured output
Protocol & capability details

Protocol & capabilities

claude · claude-opus-4-8

Context limit
1000000
Maximum output
128000

tools · stream · reasoning · structured_output

Compare Claude Opus 4.8 with related models

SpecificationClaude Opus 4.8Claude Fable 5Claude Fable 5.1
ProviderAnthropicAnthropicAnthropic
Input → outputTextTextTextTextTextText
Selection basisCurrent modelSame claude protocol · Same billing unitsSame claude protocol · Same billing units
Context / max output1,000,000 / 128,0001,000,000 / 128,0001,000,000 / 128,000
Starting price$1.5 / 1M tokens$3 / 1M tokens$3 / 1M tokens

Choose by the input types, output settings and billing unit your workflow needs. Try the same prompt across models to compare results for your own use case.

Integrate Claude Opus 4.8 into your app

Keep the native request format and point your application to the platform API. Prepare a key with model access, then review status and charges in your usage records.

View API examples

Claude Opus 4.8 API · Common Questions

Everything you need to know about API access, pricing and model capabilities.

How is Claude Opus 4.8 billed?

Charges depend on the recorded token usage and your account rates. Input, output and supported cache or reasoning categories are listed separately in the pricing table. The calculator uses public USD prices; the final usage receipt determines the charge.

How do I get an API key?

Choose “Get API access” to open the integration guide. Sign in to your NewRouters account, prepare a key with access to this model and copy an API example.

Which API endpoints can I use?

Supported endpoints: /v1/messages、/v1/messages/count_tokens. Choose an endpoint in the API examples to see its native request format.

Does the model support streaming?

The current model route declares streaming support. Use the native endpoint’s streaming option and consume its events. Usage already completed may still be billed if the connection is interrupted.

Can I use tools or structured output?

Tools: supported. Structured output: supported. Request fields follow the selected native endpoint.

Where can I check usage and charges?

Keep the request ID and open your account’s LLM usage records to inspect request status, token counts and charges. Prompt and answer content are not a conversation history in this view.

Explore LLM Use Cases

All LLM models ↗

Integration topics / Documentation

All documentation ↗