Claude Opus 4.7
The previous-generation Opus, still active and priced identically to 4.8. A reasonable pin when you need a frozen target rather than the latest capability.
At a glance.
| Provider | Anthropic |
| Family | claude-opus |
| Released | 2026-04 |
| License | Proprietary |
| Context window | 1M tokens |
| Max output | 128K tokens |
| Modalities | text, image, pdf |
| Tool calling | Yes |
| Reasoning mode | Yes |
| Caching | explicit |
| Batch discount | 50% off |
What reuse looks like here.
What you actually pay once caching works.
At a typical 55% prefix reuse, a million input tokens on Claude Opus 4.7 effectively costs $2.52 instead of $5.00 - blending to roughly $8.14 with a 25% output share. Background work drops a further 50% on the batch tier.
Estimate it for your workloadRoutes through these aliases:
Same OpenAI client, this model.
from openai import OpenAI
client = OpenAI(base_url="https://api.zumik.ai/v1", api_key="zk_live_...")
r = client.responses.create(
model="claude-opus-4-7", # or an alias like reasoning.best
input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached) # confirm reuseOther options for these workloads.
Claude Opus 4.7, answered.
How much does Claude Opus 4.7 cost?
Claude Opus 4.7 is $5.00 per million input tokens and $25.00 per million output tokens through Zumik. Cache reads are $0.50 per million, a 90% discount on input.
What is Claude Opus 4.7's context window?
Claude Opus 4.7 supports a 1M-token context window with up to 128K output tokens.
Does Claude Opus 4.7 support prompt caching?
Yes. Anthropic uses Explicit cache_control breakpoints caching. In the Zumik corpus, Claude Opus 4.7 shows a median cache capture of 92% on agent workloads.
Which Zumik aliases route to Claude Opus 4.7?
Claude Opus 4.7 is a candidate for the reasoning.best alias, selected when it wins under current routing policy.
Run Claude Opus 4.7 with reuse measured.
Point an OpenAI client at Zumik and see exactly how much of this model's input you are reusing.