AI Models
Claude Opus 4.8
Anthropic's Opus model released May 28, 2026, and its recommended default until Opus 5.5 shipped in September 2026. 1M context, 128K output, $5/$25 per million tokens.
Try Claude Opus 4.8Visit anthropic.comanthropic.com/news/claude-opus-4-8
Share
Claude Opus 4.8 (`claude-opus-4-8`) was Anthropic's most capable Opus-tier model at its May 28, 2026 launch and the recommended default for complex reasoning, long-horizon agentic coding, and high-autonomy work until Claude Opus 5.5 replaced it on September 22, 2026. It keeps Opus 4.7 pricing at $5 per million input tokens and $25 per million output tokens, with a 1M token context window, 128K max output, and a January 2026 knowledge cutoff. Anthropic reports it is around four times less likely than its predecessor to let flaws in its own code pass unremarked, and the `effort` parameter defaults to high on all surfaces including the Claude API and Claude Code. It also serves as the fallback model that handles requests Fable 5's safety classifiers decline. At half of Fable 5's price, it was the workhorse choice for most production agent stacks through the summer of 2026.
Claude Opus 4.8 at a glance
Last verified
- Pricing
- Claude API - $5 per million input tokens, $25 per million output tokens
- Prompt caching - $6.25/MTok 5-minute cache write, $10/MTok 1-hour cache write, $0.50/MTok cache read
- Batch API - 50% off input and output ($2.50/MTok input)
- Fast mode (research preview, Claude API only) - $10/MTok input, $50/MTok output
- Models
- Call it as claude-opus-4-8 on the Claude API, Google Cloud, Microsoft Foundry, and Claude Platform on AWS, or anthropic.claude-opus-4-8 on Amazon Bedrock. It is now a legacy model with a 1M context window, 128K max output (300K through the Batch API beta), adaptive thinking at high default effort, and a January 2026 knowledge cutoff. Anthropic points new work to Claude Opus 5.5.
- Recent changes
- Claude Opus 5.5 launches as the current Opus model, and Opus 4.8 moves to legacy status. It stays available, with retirement not sooner than May 28, 2027.
- Claude Opus 4.1 retires on the Claude API, with claude-opus-4-8 named as its recommended replacement.
Sources: Anthropic: Introducing Claude Opus 4.8, Claude Opus 4.8 model overview, Claude pricing, Model deprecations, Models overview, Claude Opus 5.5 model overview
Similar Tools
AI Models
Claude
Anthropic's model family. As of October 2026: Opus 5.5 as the default, Fable 5.1 for the hardest long-horizon work, Sonnet 5.5 for speed, Haiku 5.5 for cost. 1M context. Max from $100/mo.
AI Models
Claude Fable 5
Anthropic's first generally available Mythos-class model, released June 9, 2026. 1M context, 128K max output, $10/$50 per million tokens. Built for long-horizon agentic work.
AI Models
Gemini
Google's model family. As of October 2026 Gemini 4 Argon (GA October 13, 1M token context) is the flagship for coding and agents, with Gemini 3.8 Flash (free tier in AI Studio) as the fast, cheaper option.
AI Models
Claude Haiku 4.5
Anthropic's smallest Claude 4.5 model, released October 2025 and succeeded by Haiku 5.5 in October 2026. Sonnet 4-level coding at one-third the cost. $1/$5 per million tokens.
Get started with Claude Opus 4.8
Anthropic's Opus model released May 28, 2026, and its recommended default until Opus 5.5 shipped in September 2026. 1M context, 128K output, $5/$25 per million tokens.
Try Claude Opus 4.8Get weekly tool reviews
Honest takes on AI dev tools, frameworks, and infrastructure - delivered to your inbox.
Subscribe FreeMore AI Models Tools
Claude
Anthropic's model family. As of October 2026: Opus 5.5 as the default, Fable 5.1 for the hardest long-horizon work, Sonnet 5.5 for speed, Haiku 5.5 for cost. 1M context. Max from $100/mo.
ChatGPT
OpenAI's chat app. As of October 2026 Free and Go run GPT-6 Luna; Plus ($20/mo) adds GPT-6.1 Sol and GPT-6 Astra. Agent mode, Codex, image generation, code interpreter.
OpenRouter
Unified API for hundreds of models. One API key, one billing dashboard. OpenAI, Anthropic, Google, Meta, Mistral, and more. Automatic fallbacks and load balancing.
Related Guides
Guide
Model Aliases - Claude Code
Use opus, sonnet, haiku, and best to switch models easily.
Claude CodeGuide
Claude Code Setup Guide
Configure Claude Code for maximum productivity -- CLAUDE.md, sub-agents, MCP servers, and autonomous workflows.
AI AgentsGuide
MCP Servers Explained
What MCP servers are, how AI clients like Claude Code call their tools, how to add one through .mcp.json, and how to build your own in TypeScript.
AI AgentsRelated Posts
8 min read
OpenAI
OpenAI's GPT 5.4 in 10 Minutes
State-of-the-art computer use, steerable thinking you can redirect mid-response, and a million tokens of context. GPT 5....
8 min read
Claude
Claude Opus 4.6: Anthropic's Smartest Model Gets Agent Teams
Claude Opus 4.6 adds agent teams, a million-token context window, adaptive thinking and context compaction. The benchmar...
5 min read
Claude
Claude Opus 4.5: Anthropic's Most Intelligent Model
Claude Opus 4.5 is the Anthropic model built for coding agents and computer use. Its pricing, benchmarks, token efficien...
9 min read
Claude Code
Claude Code: The Future of Coding?
Claude Code is a terminal-based AI agent that writes code, runs commands and tests its own output. A 30-day review of it...
6 min read
News
Claude Code Projects: Coordinator, Threads, and Limits
Claude Code Projects is open to waitlisted Pro and Max users. How the coordinator and cloud threads work, what they cost...
15 min read
AI Models
Cheapest Subagent Model: Haiku 5.5 or GPT-6 Luna? Routing, Compaction and Cost per Task
Which cheap model belongs under your orchestrator? Haiku 5.5 vs GPT-6 Luna as a subagent or worker: routing by prompt le...
Try the member tools free
Get Smarter About AI Dev
New tutorials, open-source projects, and deep dives on coding agents - delivered weekly.
One email per weekReal code, not theoryFree forever