CrossModel
Claude Opus 4.8
anthropic/claude-opus-4-8
Back to model catalog

Anthropic · Model guide

Claude Opus 4.8

Compare
anthropic/claude-opus-4-8

The last of the 4.x Opus line, superseded by Opus 5 in July 2026 but still available for complex agentic work. Adaptive thinking is available but off unless asked for, and all five effort levels apply. Anthropic still points cybersecurity work that needs reduced guardrails at this model rather than at Sonnet 5.

Modalities
TextImageText
Context
1M
Max output
128K
Price / 1M tokens
$ 5.00in$ 25.00out
StreamingTool callingJSON outputImage inputThinking mode · can be turned off

What this model is good at

What the vendor positions it for, and which of our models to reach for instead.

VendorLegacy model: still available, with migration to a current model recommended.source

Best for

  • Agentic coding · Anthropic recommends starting at xhigh effort for coding and agentic use cases.(vendor claim)source

  • Security research with reduced guardrails · Anthropic recommends Opus 4.8 for cybersecurity work that requires reduced guardrails.(vendor claim)source

Neighbouring models
Compare them side by side →

Pricing and billing

Billed per token. Cached input is charged at the cache-read rate.

Price / 1M tokensYou pay
Input$ 5.00
Output$ 25.00
Cache read$ 0.50
Cache write$ 6.25
Estimate a request
$ 0.1000
Estimated cost per request
10.0K × $ 5.00
+ 2.0K × $ 25.00
≈ $ 100.00 per 1,000 requests

Capabilities and limits

What CrossModel guarantees across every route this model can take right now.

Context window
1.0M tokens
Max output
128.0K tokens
Input / output modalities
Text + Image → Text
Streaming
Supported
Tool calling
Supported
Structured output (JSON)
Supported
Image input
Supported
Thinking mode
Supported· can be turned off
Reasoning effort
low · medium · high · xhigh · max
Available endpoints
/v1/chat/completions · /v1/responses · /v1/messages
First-party sources:Specsplatform.claude.comCapabilitiesplatform.claude.com 1platform.claude.com 2platform.claude.com 3platform.claude.com 4

Published benchmarks

Scores the vendor reported, with the evaluation setup each one came from.

Agentic coding
  • Terminal-Bench 2.1
    pass_rate·Anthropic · 2026-05-28setup not fully disclosed
    74.6%
Coding
  • SWE-Bench Pro
    resolved_rate·Anthropic · 2026-05-28setup not fully disclosed
    69.2%
Computer use
  • OSWorld-Verified
    success_rate·Anthropic · 2026-05-28setup not fully disclosed
    83.4%
Knowledge work
  • Finance Agent v2
    score·Anthropic · 2026-05-28setup not fully disclosed
    53.9%
  • GDPval-AA
    elo·Anthropic · 2026-05-28setup not fully disclosed
    1890
Reasoning
  • Humanity's Last Exam
    accuracy·Anthropic · 2026-05-28setup not fully disclosed

    No tools.

    49.8%
  • Humanity's Last Exam (with tools)
    accuracy·Anthropic · 2026-05-28setup not fully disclosed

    Anthropic does not disclose which tools the run had.

    57.9%

Vendor-reported numbers, not CrossModel measurements. Scores are only comparable when the benchmark version, metric and evaluation setup match, so nothing here is averaged or ranked.

Use it in your tools

Point the base URL at CrossModel and paste this model ID — every tool below has a setup guide.

Claude Code
Anthropic's official command-line coding assistant
Cursor
AI-first code editor
Cline
Open-source AI coding agent for VS Code
Codex
OpenAI's coding agent for ChatGPT desktop and the terminal
OpenCode
Open-source terminal coding assistant
Zed
High-performance, AI-native code editor
Open WebUI
Open-source, self-hosted AI chat interface
Continue
Open-source AI coding assistant for VS Code & JetBrains
See all integration guides →

Frequently asked questions

What is Claude Opus 4.8?
Claude Opus 4.8 is available on CrossModel as anthropic/claude-opus-4-8. It has a 1M-token context window and can return up to 128K tokens per request.
How much does Claude Opus 4.8 cost?
Currently $ 5.00 per 1M input tokens and $ 25.00 per 1M output tokens. Cached input is billed at $ 0.50 per 1M.
Does Claude Opus 4.8 support tool calling and structured output?
Tool calling: Supported · Structured output (JSON): Supported · Image input: Supported · Streaming: Supported · Thinking mode: Supported
Which endpoint do I call?
OpenAI Chat Completions (/v1/chat/completions), OpenAI Responses (/v1/responses) and Anthropic Messages (/v1/messages) all work — pick whichever your SDK already speaks.
Can I try it without writing code?
Yes. Sign in and open the Playground on this page to chat with the model directly — no API key needed. Usage is billed from your wallet at the normal rate.

Chat first, integrate later

Chat first, then wire it in once you like the answers.