Zumik
Sign inSign up

xAI · context caching

Grok 4.20 (Non-Reasoning)

Grok 4.20 (Non-Reasoning) on Zumik: live pricing, context, and caching, routable by id or alias through one OpenAI-compatible endpoint.

Call it through ZumikAbout xAI
$1.25
Input / 1M tokens
$2.50
Output / 1M tokens
$0.20
Cache read · −84%
1M
Context window

Specifications

At a glance.

ProviderxAI
Familygrok-4
Released2026-03
LicenseProprietary
Context window1M tokens
Max output30K tokens
Modalitiestext, image, pdf
Tool callingYes
Reasoning modeNo
Cachingcontext
Batch discountNo batch tier

Measured by Zumik

What reuse looks like here.

Not yet profiled

Pricing, context, and capabilities for Grok 4.20 (Non-Reasoning) 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 Grok 4.20 (Non-Reasoning) effectively costs $0.67 instead of $1.25 - blending to roughly $1.13 with a 25% output share. There is no batch tier, so cost control here leans on caching and routing.

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="grok-4-20-0309-non-reasoning",
    input="Draft a fix for the failing test.",
)
print(r.usage.input_tokens_cached)   # confirm reuse

Frequently asked

Grok 4.20 (Non-Reasoning), answered.

How much does Grok 4.20 (Non-Reasoning) cost?

Grok 4.20 (Non-Reasoning) is $1.25 per million input tokens and $2.50 per million output tokens through Zumik. Cache reads are $0.20 per million, a 84% discount on input.

What is Grok 4.20 (Non-Reasoning)'s context window?

Grok 4.20 (Non-Reasoning) supports a 1M-token context window with up to 30K output tokens.

Does Grok 4.20 (Non-Reasoning) support prompt caching?

Yes. xAI uses Context caching caching. In the Zumik corpus, Grok 4.20 (Non-Reasoning) shows a median cache capture of 77% on agent workloads.

Run Grok 4.20 (Non-Reasoning) 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