Model comparison
Claude Opus 5 vs Claude Opus 4.8: same price, what changed
Claude Opus 5 and Claude Opus 4.8 cost exactly the same, from $5 input to $0.50 cache hits. How Anthropic positions each, and what it now recommends instead.
· Prices as of September 26, 2026
Claude Opus 5
Anthropic · Released July 24, 2026 · Previous generation
The previous everyday Opus, pitched as close to Claude Fable 5 at half the price. Anthropic now recommends moving to Claude Opus 5.5.
Claude Opus 5 facts and comparisonsClaude Opus 4.8
Anthropic · Released May 28, 2026 · Previous generation
An Opus upgrade over 4.7 focused on judgment and collaboration. Anthropic still recommends it for cybersecurity work that needs reduced guardrails.
Claude Opus 4.8 facts and comparisons
The short answer
Claude Opus 5 and Claude Opus 4.8 have identical prices, so the example agentic coding session costs $6.00 on either, and the choice comes down to what Anthropic says each is for. Anthropic pitched Opus 5 as close to Claude Fable 5 at half the price, and still recommends Opus 4.8 for cybersecurity work that needs reduced guardrails. Both are legacy models, and Anthropic's current recommendation for everyday Opus work is Claude Opus 5.5.
Choose Claude Opus 5 if
- You want the more recent of the two, which Anthropic describes as designed for everyday coding and knowledge work.
- You relied on it as Claude Code's opus default before Opus 5.5 and want the same behavior while you evaluate the newer model.
- Anthropic's claim that Opus 5 works more efficiently than other models matters to you, since at equal rates spending less means using fewer tokens.
Choose Claude Opus 4.8 if
- Your cybersecurity work needs reduced guardrails, and Anthropic still recommends Opus 4.8 for exactly that.
- You have agents built around xhigh effort, the starting point Anthropic recommends for Opus 4.8 on coding and agentic work.
Side by side
Specs and prices
| Fact | Claude Opus 5 | Claude Opus 4.8 |
|---|---|---|
| Maker | Anthropic | Anthropic |
| API model id | claude-opus-5 | claude-opus-4-8 |
| Released | July 24, 2026 | May 28, 2026 |
| Status | Previous generation | Previous generation |
| Context window | 1M tokens | 1M tokens |
| Max output | 128K tokens | 128K tokens |
| Open weights | No | No |
| Input, per 1M tokens | $5 | $5 |
| Cache hit, per 1M | $0.50 | $0.50 |
| Cache write, per 1M | $6.25 (5-minute), $10 (1-hour) | $6.25 (5-minute), $10 (1-hour) |
| Output, per 1M tokens | $25 | $25 |
| Runs in | Claude Code, Cursor, OpenCode, OpenRouter, and GitHub Copilot | Claude Code, Cursor, OpenCode, OpenRouter, and GitHub Copilot |
Standard API rates in US dollars, as published by each maker on September 26, 2026. Batch and priority tiers, taxes, and subscription plans are not included. Claude Opus 5: The full 1M context window is billed at standard rates. Fast mode, a research preview on the Claude API, costs $10 input and $50 output per million tokens. Claude Opus 4.8: The full 1M context window is billed at standard rates. Fast mode, a research preview on the Claude API, costs $10 input and $50 output per million tokens.
Cost
What the same work costs
The same token counts, priced at each model’s published rates. Cached tokens are billed at each maker’s cache prices, so the session shows what caching is worth on each model.
Real sessions differ: the two models count the same code as different numbers of tokens, and reasoning settings change how much each one writes. Your own history is the real test.
| Workload | Claude Opus 5 | Claude Opus 4.8 |
|---|---|---|
| Agentic coding session, 100K input, 400K written to cache, 2M read from cache, 50K output | $6.00 | $6.00 |
| Large one-off review, 150K input with no cache hits, 10K output | $1.00 | $1.00 |
| Output-heavy generation, 30K input, 80K output | $2.15 | $2.15 |
| A month of sessions, 110 sessions: 5 a day, 22 working days | $660.00 | $660.00 |
| Where the session’s cost goes | ||
| Cache writes | $3.25 | $3.25 |
| Cache reads | $1.00 | $1.00 |
| Uncached input | $0.50 | $0.50 |
| Output | $1.25 | $1.25 |
- caching saves on the session with Claude Opus 5 (56%)
- $7.75
- caching saves on the session with Claude Opus 4.8 (56%)
- $7.75
Do Claude Opus 5 and Claude Opus 4.8 cost the same?
Yes, to the cent. Claude Opus 5 and Claude Opus 4.8 both charge $5 per million input tokens and $25 per million output tokens, $6.25 for a 5-minute cache write, $10 for a 1-hour write, and $0.50 for a cache hit. Fast mode, a research preview on the Claude API, is $10 input and $50 output on both.
Every workload therefore costs the same: $6.00 for the example agentic coding session, $1.00 for the large one-off review, $2.15 for the output-heavy generation, and $660.00 for 110 sessions a month at API rates. Cache writes are the biggest share of the session at $3.25, or 54%, and caching saves $7.75 against sending the same tokens uncached.
Both use Anthropic's newer tokenizer, which counts about 30% more tokens than earlier Claude models for the same text, and both take 1M tokens of context at standard rates with 128K of output. With rates, tokenizer, and limits all equal, any cost difference between them comes from how many tokens each spends on a task: how much it thinks, how long its answers run, and how many turns it takes.
How Anthropic positions Opus 5 and Opus 4.8
Anthropic released Opus 4.8 in May 2026 as an upgrade over Opus 4.7 focused on judgment and collaboration, crediting it with the consistency and autonomy to keep working on long-running tasks. It recommends starting at xhigh effort for coding and agentic work. Even after two newer Opus releases, Anthropic still recommends Opus 4.8 for cybersecurity work that needs reduced guardrails.
Opus 5 followed in July 2026. Anthropic called it "a thoughtful and proactive model that comes close to the frontier intelligence of Claude Fable 5 at half the price," designed for everyday coding and knowledge work, and said it works more efficiently than other models. It served as Claude Code's opus default until Claude Opus 5.5 took that place.
Should you still use either one?
Both are legacy models that stay available, so nothing forces a move. For everyday Opus work, Anthropic now recommends Opus 5.5 over Opus 5, and Opus 5.5 lists lower rates than either model here. The case for staying on Opus 4.8 is narrow and specific: the cybersecurity work Anthropic still points to it for.
Check effort before comparing them. Anthropic suggests xhigh as the starting effort for Opus 4.8 on coding, and effort changes how many tokens a model spends on a task. Output costs $25 per million on both, so if you run the two at different efforts, the cost difference will reflect the setting as much as the model.
Prompt caching
How Anthropic bills cached tokens
Anthropic
Claude caches a prompt prefix up to a breakpoint. One top-level cache_control field places the breakpoint automatically and moves it as the conversation grows, or you can mark up to 4 blocks yourself. Claude Code manages caching for you.
A 5-minute cache write costs 1.25x the input price and a 1-hour write costs 2x. A cache hit costs 0.1x input on most models, 0.05x on Claude Opus 5.5, and 0.025x on Claude Fable 5.1 and Claude Mythos 5.1. Every hit restarts the cache lifetime at no charge.
Anthropic's rule of thumb: a 5-minute write pays for itself after one cache read, and a 1-hour write after two.
In Claude Code, the main conversation uses the 1-hour cache on a Claude subscription and the 5-minute cache with an API key. Each model has its own cache, so switching models starts over.
Source: Anthropic: Prompt caching
Your own numbers
See what Claude Opus 5 and Claude Opus 4.8 really cost you.
everyaitoken reads your Claude Code, Cursor, OpenCode, and OpenRouter history on your Mac and prices every request at API rates, with what caching saved or cost. $9 once.
FAQ
Questions
Is Claude Opus 5 more expensive than Claude Opus 4.8?
No. Every rate is identical, including fast mode, so the same token counts cost the same on either. The example session is $6.00 on both.
Why would I still use Claude Opus 4.8?
Anthropic still recommends it for cybersecurity work that needs reduced guardrails. Outside that case, Anthropic's recommendations point to newer Opus models.
Which Opus is the Claude Code default now?
Claude Opus 5.5. Opus 5 was the opus default before it, and Opus 4.8 is a legacy model you can still select in Claude Code.
How can I tell which of the two costs me less?
Since the rates match, only token counts differ. EveryToken reads your local Claude Code history and prices each request at API rates by model, so you can compare the same kind of task on each.
Sources
- Anthropic: Pricing
- Anthropic docs: Claude Opus 5
- Anthropic: Introducing Claude Opus 5
- Claude Code docs: Model configuration
- Cursor docs: Claude Opus 5
- OpenRouter: Claude Opus 5
- OpenCode docs: Zen
- GitHub Docs: Supported AI models in Copilot
- Anthropic docs: Claude Opus 4.8
- Anthropic: Introducing Claude Opus 4.8
- Anthropic: Claude Opus
- Cursor docs: Claude Opus 4.8
- OpenRouter: Claude Opus 4.8
- Anthropic: Prompt caching