Claude Opus 4.8 vs Claude Opus 5

As of November 10, 2026, Claude Opus 4.8 and Claude Opus 5 cost the same: $5.00 per 1M input tokens and $25.00 per 1M output tokens, and both have a 1M-token context window.

Prices from LiteLLM's price fileChecked November 10, 2026

Claude Opus 4.8 vs Claude Opus 5 side by side

Headline prices in US dollars per 1M tokens: each model's own lab where it sells it, otherwise its cheapest provider. Source: LiteLLM model price file, as of November 10, 2026.
	Claude Opus 4.8	Claude Opus 5
Input, per 1M tokens	$5.00	$5.00
Output, per 1M tokens	$25.00	$25.00
Cache read, per 1M tokens	$0.50	$0.50
Cache write, per 1M tokens	$6.25	$6.25
Context window	1,000,000 tokens	1,000,000 tokens
Max output	128,000 tokens	128,000 tokens
Image input	Yes	Yes
Tool calling	Yes	Yes
Structured output (JSON)	Yes	Yes
Prompt caching	Yes	Yes
Reasoning	Yes	Yes
Providers on LiteLLM	8	10
Price shown is from	Anthropic	Anthropic
Added to LiteLLM	June 2026	July 24, 2026

Cheapest provider for each

Claude Opus 4.8: Anthropic at $5.00 input and $25.00 output per 1M tokens (claude-opus-4-8)
Claude Opus 5: Anthropic at $5.00 input and $25.00 output per 1M tokens (claude-opus-5)

Benchmark scores

From the Epoch AI Benchmarking Hub (CC BY 4.0), data as of August 27, 2026. Some results were run by Epoch and others collected by Epoch from each benchmark's own leaderboard, linked in the first column. Each model's best reported reasoning setting is shown in brackets. Higher is better. Only benchmarks with a score for both models are shown.
Benchmark	Claude Opus 4.8	Claude Opus 5
Overall
Epoch Capabilities Index	159.9	164.5
Coding and agents
FrontierCode	46.5%	53.4% (max)
APEX-Agents	48.9% (max)	65.8% (max)
OSWorld 2.0	20.6% (max)	31.4% (max)
Reasoning and knowledge
GPQA Diamond	91.0% (max)	93.9% (max)
ARC-AGI-2	72.1% (high)	90.4% (max)
SimpleQA Verified	53.0% (max)	59.9% (max)
Math
FrontierMath (tiers 1-3)	80.0% (max)	85.6% (max)
FrontierMath (tier 4)	56.1% (max)	73.2% (max)
OTIS Mock AIME 2024-2025	98.3% (max)	98.9% (max)

Call Claude Opus 4.8 or Claude Opus 5 with LiteLLM

Both use the OpenAI format through LiteLLM, so switching is a model name change. Set each provider's API key in the environment first.

Python SDK

from litellm import completion

messages = [{"role": "user", "content": "Hello!"}]

# Claude Opus 4.8
response = completion(model="claude-opus-4-8", messages=messages)

# Claude Opus 5
response = completion(model="claude-opus-5", messages=messages)

# Claude Opus 4.8, falling back to Claude Opus 5 if the call fails
response = completion(model="claude-opus-4-8", messages=messages, fallbacks=["claude-opus-5"])

FAQ

Which is cheaper, Claude Opus 4.8 or Claude Opus 5?

They cost the same: $5.00 per 1M input tokens and $25.00 per 1M output tokens, as of November 10, 2026.

Which has the larger context window, Claude Opus 4.8 or Claude Opus 5?

Both have a 1,000,000-token context window.

Can I switch from Claude Opus 4.8 to Claude Opus 5 without changing my code?

Yes. Through LiteLLM both use the OpenAI format, so switching means changing the model name from "claude-opus-4-8" to "claude-opus-5", or pointing a LiteLLM gateway model alias at the other model. You can also use one as a fallback for the other.