OpenAI · automatic caching

GPT-5 Chat

GPT-5 Chat on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.

Call it through Zumik About OpenAI

$1.25

Input / 1M tokens

$10.00

Output / 1M tokens

$0.13

Cache read · −90%

400K

Context window

Specifications

At a glance.

Provider	OpenAI
Family	gpt-5
Released	2025-08
License	Proprietary
Context window	400K tokens
Max output	128K tokens
Modalities	text, image
Tool calling	No
Reasoning mode	Yes
Caching	automatic
Batch discount	50% off

Measured by Zumik

What reuse looks like here.

Not yet profiled

Pricing, context, and capabilities for GPT-5 Chat 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 GPT-5 Chat effectively costs $0.63 instead of $1.25 - blending to roughly $2.97 with a 25% output share. Background work drops a further 50% on the batch tier.

Estimate it for your workload

Best for

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="gpt-5-chat-latest",
    input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached)   # confirm reuse

Frequently asked

GPT-5 Chat, answered.

How much does GPT-5 Chat cost?

GPT-5 Chat is $1.25 per million input tokens and $10.00 per million output tokens through Zumik. Cache reads are $0.13 per million, a 90% discount on input.

What is GPT-5 Chat's context window?

GPT-5 Chat supports a 400K-token context window with up to 128K output tokens.

Does GPT-5 Chat support prompt caching?

Yes. OpenAI uses Automatic prefix caching caching. In the Zumik corpus, GPT-5 Chat shows a median cache capture of 85% on agent workloads.

Run GPT-5 Chat with reuse measured.

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

Migration quickstart Back to catalog