ModelBench
Anthropic logo
Models/Anthropic

Claude Opus 4.8

Top Claude Opus tier for the hardest reasoning, coding, and long-horizon agents

Source-linked claude-opus Closed weights Released 2026-05-28
API data Report
Input modalitiesT
Output modalitiesT
Input price$5/1M tokens
Output price$25/1M tokens
Context window1M
Max output128K
Overview

Capabilities and specifications

✓ Reasoning Yes
✓ Tool calling Yes
? Structured output Unknown
✓ Attachments Yes
✓ Vision input Yes
× Open weights No
Creator
Anthropic
Model family
claude-opus
Knowledge cutoff
2026-01
License
Not documented
Release date
2026-05-28
Model ID
anthropic/claude-opus-4-8
Inference availability

Provider pricing and availability

Provider-specific identifiers, limits, and prices per million tokens.

Report a price
Providers offering Claude Opus 4.8
ProviderProvider model IDContextInputOutputCache readCapabilitiesSource
Kenari claude-opus-4-8 1M Not listed Not listed - ReasoningTools Docs
Model Oracle AI claude-opus-4.8 1M Not listed Not listed - ReasoningTools Docs
Snowflake Cortex claude-opus-4-8 1M Not listed Not listed - ReasoningTools Docs
UnoRouter claude-opus-4-8 1M $0.425 $2.125 - ReasoningTools Docs
Xpersona claude-opus-4-8 200K $1.5 $9.25 $0.15 ReasoningTools Docs
Vercel AI Gateway anthropic/claude-opus-4.8 1M $5 $25 $0.5 ReasoningTools Docs
DigitalOcean anthropic-claude-opus-4.8 1M $5 $25 $0.5 ReasoningTools Docs
CrossModel anthropic/claude-opus-4-8 1M $5 $25 $0.5 ReasoningTools Docs
ZenMux anthropic/claude-opus-4.8 1M $5 $25 $0.5 ReasoningTools Docs
Merge Gateway anthropic/claude-opus-4-8 1M $5 $25 $0.5 ReasoningToolsJSON Docs
Pioneer claude-opus-4-8 1M $5 $25 $0.5 ReasoningTools Docs
LLM Gateway claude-opus-4-8 1M $5 $25 $0.5 ReasoningTools Docs
Abacus claude-opus-4-8 1M $5 $25 - ReasoningTools Docs
Cloudflare AI Gateway anthropic/claude-opus-4-8 1M $5 $25 $0.5 ReasoningTools Docs
DaoXE claude-opus-4-8 1M $5 $25 $0.5 ReasoningTools Docs
Vertex (Anthropic) claude-opus-4-8@default 1M $5 $25 $0.5 ReasoningTools Docs
Azure claude-opus-4-8 1M $5 $25 $0.5 ReasoningTools Docs
Anthropic claude-opus-4-8 1M $5 $25 $0.5 ReasoningToolsJSON Docs
FreeModel claude-opus-4-8 1M $5 $25 $0.5 ReasoningTools Docs
OpenCode Zen claude-opus-4-8 1M $5 $25 $0.5 ReasoningTools Docs
GMI Cloud anthropic/claude-opus-4.8 1M $5 $25 $0.5 ReasoningTools Docs
Amazon Bedrock anthropic.claude-opus-4-8 1M $5 $25 $0.5 ReasoningTools Docs
OpenRouter anthropic/claude-opus-4.8 1M $5 $25 $0.5 ReasoningToolsJSON Docs
FastRouter anthropic/claude-opus-4.8 1M $5 $25 - ReasoningTools Docs
Azure Cognitive Services claude-opus-4-8 1M $5 $25 $0.5 ReasoningTools Docs
routing.run claude-opus-4-8 1M $5 $25 - ReasoningTools Docs
AIHubMix claude-opus-4-8 200K $5 $25 $0.5 ReasoningTools Docs
AIHubMix claude-opus-4-8-think 200K $5 $25 $0.5 ReasoningTools Docs
Vertex claude-opus-4-8@default 1M $5 $25 $0.5 ReasoningTools Docs
Neon claude-opus-4-8 1M $5 $25 $0.5 ReasoningTools Docs
GitHub Copilot claude-opus-4.8 200K $5 $25 $0.5 ReasoningTools Docs
Ofox anthropic/claude-opus-4.8 1M $5 $25 $0.5 ReasoningTools Docs
Cortecs claude-opus4-8 1M $5.64 $28.198 $0.563 ReasoningTools Docs
Venice AI claude-opus-4-8 1M $6 $30 $0.6 ReasoningToolsJSON Docs

Capability badges appear only when the provider catalog explicitly lists support.

Serving quality

Performance and reliability

Observed serving measurements stay separate from model specifications and are never estimated from price or model size.

Throughput Not reported

Generation speed; higher is faster.

Latency / TTFT Not reported

Time until the first output token arrives.

Uptime Not reported

Successful requests over a measured period.

Performance varies by inference provider, region, and load. Provider-level measurements appear only when a source reports them.

Published evaluations

Benchmarks

Raw results remain attached to their original source and version.

Benchmark registry
FrontierCode - Unversioned - pass rateTop 2 reported models
Claude Fable 5
29.3
Claude Opus 4.8
13.4
Humanity's Last Exam - Unversioned - accuracyTop 7 reported models
Claude Fable 5
64.5
Muse Spark 1.1
62.1
GPT-5.4 Pro
58.7
Claude Opus 4.8
57.9
GPT-5.5 Pro
57.2
Claude Opus 4.7
54.7
GPT-5.5
52.2
OSWorld-Verified - Unversioned - success rateTop 7 reported models
Claude Fable 5
85.0
Claude Opus 4.8
83.4
Claude Sonnet 5
81.2
Muse Spark 1.1
80.8
GPT-5.5
78.7
Claude Sonnet 4.6
78.5
Gemini 3.5 Flash
78.4
SWE-Bench Pro - Unversioned - resolve rateTop 7 reported models
Claude Fable 5
80.3
Claude Opus 4.8
69.2
Grok 4.5
64.7
GPT-5.6 Sol
64.6
Claude Opus 4.7
64.3
GPT-5.6 Terra
63.4
Claude Sonnet 5
63.2
SWE-Bench Verified - Unversioned - resolvedTop 7 reported models
Claude Fable 5
95.0
Claude Opus 4.8
88.6
Claude Sonnet 5
85.2
DeepSeek V4 Pro
80.6
Qwen3.7 Max
80.4
Kimi K2.6
80.2
DeepSeek V4 Flash
79.0
Terminal-Bench - 2.1 - success rate - Terminus-2Top 7 reported models
Claude Sonnet 5
80.4
GPT-5.5
78.2
Gemini 3.5 Flash
76.2
Claude Opus 4.8
74.6
Gemini 3.1 Pro Preview
70.3
Claude Sonnet 4.6
67.0
Claude Opus 4.7
66.1
Catalog activity

Recent record changes

Detected changes from successful source imports.

Full change log
No recent changes detected

This record has not changed in the retained import history.

Public API

Use this record

Fetch the complete source-linked model record without an API key.

API documentation
Endpoint
GET https://www.modelbench.lol/api/v1/models/anthropic/claude-opus-4-8
curl
curl "https://www.modelbench.lol/api/v1/models/anthropic/claude-opus-4-8"