New Sign up free, 10 calls on us. Up to $1, no card needed.

Claude Opus 4.5

Released 2025-11-24

chatCodeReasoningTool callingVisionPrompt caching

Claude Opus 4.5 is a previous-generation Opus model, the release that repositioned Anthropic's top tier at $5/$25 per million tokens, down from Claude Opus 4.1's $15/$75.

Input
text image $5/M
Output
text $25/M
Cache read
$0.5/M
Context
200K
Knowledge cutoff
2025-05

Benchmarks

Above averageNo peer higher28 / 9310 / 93
Claude Opus 4.5 other models measured peer average no peer scored higher
SWE-Bench Pro
57.1%
OSWorld-Verified
66.3%
Cybergym
50.6%
MedXpertQA-MM
63.6%
SkillsBench Avg@5
45.3%
GPQA Diamond
87%
EmbSpatialBench
75.7%
BrowseComp
37%
Video-MME (w. sub)
77.6%

Vendor-published: Alibaba (Qwen) Anthropic ByteDance DeepSeek Google MiniMax Moonshot OpenAI Tencent Z.ai

Price in context

Where the price sits among 60 comparable models

Input$5/M
$0.05 · Qwen3 VL Flash GPT-5.4 Pro · $30
Output$25/M
$0.275 · DeepSeek V4 Flash GPT-5.4 Pro · $180
Cached read$0.5/M
$0.0028 · DeepSeek V4 Flash GPT-5.4 Pro · $15

The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.

Specs & limits

Tokens

Context window (vendor spec) 200,000
Max output (vendor spec) 64,000
Knowledge cutoff 2025-05
Training data through 2025-08 knowledge cutoff 2025-05

Prompt caching

How it caches explicit (opt-in)
Min prefix 4,096 provider default is 1,024
Lifetime 5m default, 1h option
Write cost 1.25x (5m) / 2x (1h)

Thinking

Vendor control thinking.type "enabled" + budget_tokens, plus output_config.effort
Accepted values budget_tokens at least 1,024 and below max_tokens; effort low · medium · high (no xhigh, no max); "adaptive" returns 400
Default thinking off; effort high applied when the request sets nothing
Can be turned off Yes
Thinking behaviour The only extended-thinking-only model that supports effort, where effort shapes the whole response and budget_tokens sets reasoning depth, so set both; earlier turns' thinking blocks are kept in context and billed as input; interleaved thinking requires the interleaved-thinking-2025-05-14 beta header.
Parameter reasoning_effort
Values minimal · low · medium · high the gateway's parameter surface - the vendor mapping above applies

Model

Modalities text + image → text
  • Legacy model
  • introduced the effort parameter (public beta at launch)
  • 200k context / 64k max output

per Anthropic official docs ↗

Use Claude Opus 4.5 in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="claude-opus-4-5",
    messages=[{"role": "user", "content": "Summarize this diff"}],
    reasoning_effort="medium",
)
print(resp.choices[0].message.content)

About Claude Opus 4.5

  • Anthropic introduced it as its most intelligent model combining maximum capability with practical performance, aimed at complex specialized tasks, professional software engineering, and advanced agents, with step-change improvements in vision, coding, and computer use.
  • It supports a 200K-token context window, up to 64K output tokens, extended thinking, vision input, and Claude's tool-use and caching features, with moderate latency.
  • It is also a hybrid in one revealing way: it is the only extended-thinking-only model that accepts the effort parameter, and Anthropic's guidance is to set both.
  • Effort shapes the overall response while the thinking budget sets reasoning depth.
  • Effort here covers low through max but not xhigh, which arrives with Opus 4.7.
  • Requesting adaptive thinking returns an error, thinking is off unless enabled, and interleaved thinking requires a beta header.
  • Unlike the Haiku tier, thinking blocks from previous turns are preserved in context and billed as input.
  • Prompt caching needs a 4,096-token minimum prefix.
  • Anthropic lists it as a legacy model and recommends migrating to newer Opus releases.
  • For teams standardized on OpenAI SDKs, Synthorai serves Claude Opus 4.5 through its OpenAI-compatible chat API.

FAQ

Is the Claude Opus 4.5 API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $5/M input tokens, that credit alone covers roughly 24 requests of ~8K tokens against Claude Opus 4.5.

What is Claude Opus 4.5 best at?

Top tier repositioned at $5/$25 per million; 200K context with extended thinking; listed as legacy, migration to newer recommended. See the About section for the full picture from the vendor's own release notes.

How much does Claude Opus 4.5 cost?

Claude Opus 4.5 costs $5 per million input tokens and $25 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.5/M.

Does Claude Opus 4.5 support prompt caching?

Yes, via opt-in: mark stable prefixes with cache_control breakpoints. Cached input tokens bill at $0.5/M vs $5/M uncached; prompts need a 4,096-token stable prefix to cache (TTL 5m default, 1h option). Prompt caching guide →

How do I get access to Claude Opus 4.5?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="claude-opus-4-5", and you're done. One API key covers every model on the gateway.

What is Claude Opus 4.5's knowledge cutoff?

Claude Opus 4.5's knowledge cutoff is 2025-05, per the vendor's official documentation (as of 2026-07-09).

Related models

Compare

Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.

Get your API key Compare your cost →