everyais
← Model catalog

Claude Opus 4.8

everyais/claude-opus-4-8

Claude Opus 4.8 (everyais/claude-opus-4-8) availability, capabilities, context limits, and public reference pricing on everyais.

Model family claudeInput Text · ImageOutput Text
Available now

Method

The page starts with current public catalog metadata and reference costs; operational metrics are added only when measured samples are available.

Source and update

GET /models/catalog

Updated

Model type
Chat
Released
2026-05-28
Context window
1.0M
Price unit
Per 1M tokens
Maximum output
128,000
Model reference price (USD)
Input / 1M tokens
$5
Output / 1M tokens
$25
Cache read / 1M tokens
$0.5
Cache write / 1M tokens
$6.25

Capabilities

  • ✓ Streaming
  • ✓ Tool use
  • ✓ Vision
  • ✓ JSON
  • ✓ Reasoning
  • ✓ Parallel tools

Supported endpoints

  • /v1/chat/completions

Benchmarks

Evaluation results published by external sources. Only mappings approved by a human administrator are shown.

Model benchmark scores
BenchmarkScoreSource
arena-text1,452 EloLMArena LeaderboardCC-BY-4.0Source model label: claude-opus-4-8
arena-vision1,289 EloLMArena LeaderboardCC-BY-4.0Source model label: claude-opus-4-8
arena-webdev1,540 EloLMArena LeaderboardCC-BY-4.0Source model label: claude-opus-4-8
eci158.24 (source-specific scale)Epoch AI Benchmarking HubCC-BY

Scores are reproduced as published; everyais does not re-measure them. Scores using different units cannot be compared. See benchmark sources and licenses.

Browse benchmark rankings

Usage and availability trend

Daily tokensInputOutput
100K50K02026-08-252026-09-062026-08-25 · Requests 3 · Input 3,076 · Output 650 · Availability Insufficient sample2026-08-26 · Requests 0 · Input 0 · Output 0 · Availability Insufficient sample2026-08-27 · Requests 0 · Input 0 · Output 0 · Availability Insufficient sample2026-08-28 · Requests 0 · Input 0 · Output 0 · Availability Insufficient sample2026-08-29 · Requests 0 · Input 0 · Output 0 · Availability Insufficient sample2026-08-30 · Requests 0 · Input 0 · Output 0 · Availability Insufficient sample2026-08-31 · Requests 21 · Input 62,533 · Output 13,885 · Availability Insufficient sample2026-09-01 · Requests 14 · Input 9,610 · Output 4,861 · Availability Insufficient sample2026-09-02 · Requests 2 · Input 1,020 · Output 22 · Availability Insufficient sample2026-09-03 · Requests 16 · Input 12,378 · Output 5,128 · Availability Insufficient sample2026-09-04 · Requests 1 · Input 1,103 · Output 77 · Availability Insufficient sample2026-09-05 · Requests 0 · Input 0 · Output 0 · Availability Insufficient sample2026-09-06 · Requests 1 · Input 2 · Output 56 · Availability Insufficient sample

Last 13 days · 2026-09-06 Input 2 · Output 56 tokens.

Daily availability (success rate %)

Insufficient sample — not enough requests to publish a success rate.

Code example

Use the OpenAI SDK by changing only base_url.

from openai import OpenAI

client = OpenAI(
    api_key="everyais_...",
    base_url="https://api.everyais.com/v1",
)

response = client.chat.completions.create(
    model="everyais/claude-opus-4-8",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)
Full API docs

Other models in this family

Compare models side by side

Compare capabilities, context windows, and reference prices to find a model for your use case. Your actual billed rate can differ by account.

Compare with another model