Zumik
Sign inSign up

Anthropic · explicit caching

Claude Opus 4.1

Claude Opus 4.1 on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.

Call it through ZumikAbout Anthropic
$15.00
Input / 1M tokens
$75.00
Output / 1M tokens
$1.50
Cache read · −90%
200K
Context window

Specifications

At a glance.

ProviderAnthropic
Familyclaude-opus
Released2025-08
LicenseProprietary
Context window200K tokens
Max output32K tokens
Modalitiestext, image, pdf
Tool callingYes
Reasoning modeYes
Cachingexplicit
Batch discount50% off

Measured by Zumik

What reuse looks like here.

Not yet profiled

Pricing, context, and capabilities for Claude Opus 4.1 are live, but it is outside the flagship set Zumik benchmarks in depth, so measured reuse, capture, and warm TTFT are not shown yet. Run a workload estimate or route it by id to start collecting traces.

Reuse economics

What you actually pay once caching works.

At a typical 55% prefix reuse, a million input tokens on Claude Opus 4.1 effectively costs $7.57 instead of $15.00 - blending to roughly $24.43 with a 25% output share. Background work drops a further 50% on the batch tier.

Estimate it for your workload
Best for
textimagepdf

Route it directly by id, or let an alias pick it when it wins under policy.

Call it

Same OpenAI client, this model.

python
from openai import OpenAI

client = OpenAI(base_url="https://api.zumik.ai/v1", api_key="zk_live_...")

r = client.responses.create(
    model="claude-opus-4-1-20250805",
    input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached)   # confirm reuse

Frequently asked

Claude Opus 4.1, answered.

How much does Claude Opus 4.1 cost?

Claude Opus 4.1 is $15.00 per million input tokens and $75.00 per million output tokens through Zumik. Cache reads are $1.50 per million, a 90% discount on input.

What is Claude Opus 4.1's context window?

Claude Opus 4.1 supports a 200K-token context window with up to 32K output tokens.

Does Claude Opus 4.1 support prompt caching?

Yes. Anthropic uses Explicit cache_control breakpoints caching. In the Zumik corpus, Claude Opus 4.1 shows a median cache capture of 91% on agent workloads.

Run Claude Opus 4.1 with reuse measured.

Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.

Migration quickstartBack to catalog