Requesty
Sign in

identity

endpoint
xAI Corp. logo

grok-4.6xAI Corp.

in /1M$2.00input tokens
out /1M$6.00output tokens
context500Ktokens
trainingnoon your prompts
api
chat
hosting
US
model lab
xAI
weights
closed
added
August 2026
model id
xai/grok-4.6

capabilities 6/8

visionreasoningtoolscachingweb searchjson schemacomputer useimage gen

pricing

no markup
input
$2.00
output
$6.00
cache write
$2.00
cache read
$0.50

worked cost

Estimated cost for three request volumes
volumecost
100K in + 10K out$0.26
1M in + 100K out$2.60
10M in + 1M out$26.00

Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing

provider price, passed throughper 1M tokens

measured

through Sep 12

no measured traffic for this endpoint yet. pricing above is the provider's own

benchmarks

artificial analysis
Benchmark scores, each normalised to 100
evalScore as a share of 100/100
GPQA Diamond94.9
Coding Index76.8
SciCode56.5
Intelligence Index44.4
Humanity's Last Exam42.9
5 evalsmean63.1

Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-08-12.

policy

data terms
retention
none
trains on prompts
no
hosted in
US

Terms are the provider's, not Requesty's: routing a request here puts it under them. xAI Privacy Policy

Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.

quickstart

openai compatible
xai/grok-4.6

this id pins the xai corp. deployment, with no routing and no failover. the managed id on the canonical page routes across all 1 providers instead

main.py
from openai import OpenAI client = OpenAI(    api_key="YOUR_REQUESTY_API_KEY",    base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create(    model="xai/grok-4.6",    messages=[        {"role": "user", "content": "Explain quantum computing in one paragraph."},    ],) print(response.choices[0].message.content)

Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models

notes

reference

Grok 4.6 is xAI's smartest frontier model, with leading performance on coding, knowledge work, and STEM. It accepts text and image inputs with text output, and supports tool calling, structured outputs, web search, prompt caching, and extended reasoning. 500k token context window. Pricing is tiered: requests exceeding 200k total tokens are billed at a higher rate.

questions 6

How much does grok-4.6 cost?
grok-4.6 is priced at $2.00 per million input tokens and $6.00 per million output tokens when accessed via Requesty. Prompt caching is supported, which can cut effective input cost by up to 90% on repeated context. Requesty charges exactly what the upstream provider charges, we don't add markup.
What is the context window of grok-4.6?
grok-4.6 has a context window of 500K tokens. That is roughly 667 words of input you can fit in a single prompt.
How does grok-4.6 perform on benchmarks?
grok-4.6 scores 94.9% on GPQA Diamond, 76.8% on Coding Index, 56.5% on SciCode. The benchmarks pane shows every published result, each normalised to 100.
What can grok-4.6 do?
grok-4.6 supports vision input, tool calling, extended reasoning, prompt caching, web search, structured outputs (JSON schema). You can call it through any OpenAI-compatible client by pointing base_url to Requesty.
How do I use grok-4.6 with the OpenAI SDK?
Install the OpenAI SDK, set base_url to "https://router.requesty.ai/v1", set your API key to your Requesty key, and set the model to "xai/grok-4.6". The quickstart pane shows Python, JavaScript and cURL snippets.
Can I run grok-4.6 through Requesty?
Yes. grok-4.6 runs through Requesty's OpenAI-compatible API, served from xAI Corp.. You do not host the model yourself: point base_url at Requesty, set the model to "xai/grok-4.6", and requests are routed to the upstream provider with automatic failover. The same key gives you 600+ other models too.

more from xai corp. 8

Other xAI Corp. endpoints
endpointctxin /M
grok-4.5500K$2.00
grok-build-0.1256K$1.00
grok-4.31M$1.25
grok-4.2-beta2M$2.00
grok-4-1-fast-reasoning2M$0.20
grok-4-1-fast-non-reasoning2M$0.20
grok-4-fast2M$0.20
grok-4-fast-non-reasoning2M$0.20

call grok-4.6 through one endpoint

One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology

grok-4.6xai corp.in $2.00 /1Mout $6.00 /1Mctx 500Khosted US