KymaKyma
xAI

xAI

Grok Build

Grok Build is a text-only, tool-native model optimized for fast, agentic coding workflows. Developers building automated debugging pipelines or multi-step software agents should use it for rapid tool execution and structured reasoning.

Modalities

Text+Image → Text

Below release

Not established

Weights

Not published

Where it sits in the catalogue Kyma measures

Every number against every text model Kyma prices per token — a stated rule, not a chosen line-up.

Price · input#38/59

$1.389

output $2.777 · cached $0.27

median $1.009 · best $0.0494

Price · output#24/59

$2.777

per 1M tokens generated

median $3.528 · best $0.2164

Availability · 30d#36/59

97.71%

393 observations since 2026-05-24

median 98.0% · best 100.0%

Throughput#4/59

124 tok/s

probe median, one fixed prompt

median 40.0 tok/s · best 313.3 tok/s

Response time#30/59

2.25 s

probe median, to a complete answer

median 2.25 s · best 0.84 s

Context

256K

max output 32,768

published by xAI, not measured here

Tick above each rail is this model, below it the other 58. Dashed rule is the field median, solid is its best. Better is left; the axis stops at the 90th percentile, so a few models sit past its right edge.

Usage

How much this model is actually called here.

Rank

#36

of 104 active models

Tokens served

868.9K

all-time

Platform share

0.0%

of all tokens

Pricing

Pay per token. Cached input bills at this model’s own cached rate, listed below.

$1.389 /1M input$2.777 /1M output
Hobby10 req/day · 2K in / 500 out
~$1.25/mo
Production1,000 req/day · 2K in / 500 out
~$125/mo
Scale20,000 req/day · 2K in / 500 out
~$2,500/mo
+ Estimate your workload
1,000
2,000
500
30%

Estimated monthly cost

$105

$3.50 / day on Grok Build

Same workload on:

Grok 4.6$284+170%
Grok 4.20 Multi-Agent$159+52%

Estimates use list pricing with cached input at this model's own cached rate. Actual bills depend on real token counts, and every response includes its exact cost.

When to use Grok Build

Updated 2026-07-31

Where this model earns its cost — and where it doesn't.

Created by xAI, this model specializes in software development tasks. It handles tool calls natively, supports structured outputs, and includes built-in reasoning capabilities. It operates exclusively with text inputs and outputs, with a 256,000-token context window and a 32,768-token maximum output limit.

On Kyma, requests route through an OpenAI-compatible endpoint using a single API key. The platform provides automatic failover if a serving path degrades, and every response returns the exact token cost in usage.cost alongside the X-Kyma-Model header. Prompt caching is supported, billing repeated prefixes at this model's cached input rate. New accounts include a $0.50 credit.

It does not process images, audio, or other non-text modalities. While optimized for speed and tool use, its output length caps at 32,768 tokens, which may require chunking for very long codebase generation or extensive documentation tasks.

Agentic Software Development

Automates multi-step coding tasks by chaining tool calls and reasoning loops.

Rapid Debugging Workflows

Identifies and patches code errors quickly using native tool integration.

Structured API Responses

Generates valid JSON or schema-compliant outputs for downstream system integration.

Fast Chat Interactions

Delivers low-latency conversational responses for developer-focused assistants.

Not ideal for: Do not use this model for tasks requiring image analysis, audio processing, or outputs longer than 32,768 tokens.

How it compares

Against the peers people actually weigh it against.

SpecGrok BuildGrok 4.6Grok 4.20 Multi-Agent
Input /1M$1.389$2.70$1.767
Output /1M$2.777$8.10$3.534
Context256K500K2M
ToolsYesYesNo
ReasoningYesYesYes
Throughput124 tok/s57.8 tok/s313.3 tok/s

Quick start

Up and running in under two minutes.

  1. 1

    Create an API key

    Sign up and grab a key from the dashboard — $0.50 free credit, no card required.

    Get API key →
  2. 2

    Make your first request

    Drop in your key and send a chat completion — fully OpenAI-compatible.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-build",
    "messages": [
      {"role": "user", "content": "Explain prompt caching in one paragraph."}
    ]
  }'
  3. 3

    Stream responses

    Add "stream": true to receive tokens as they arrive.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "grok-build",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

FAQ

Common questions about this model.

What is the context window of Grok Build?

Grok Build has a 256K-token context window — roughly 376 pages of text in a single request.

How much does the Grok Build API cost?

$1.389 per 1M input tokens and $2.777 per 1M output tokens, with cached input at $0.27/1M — 81% off the input rate on repeated prompt prefixes. No subscription; you pay only for what you use.

Does Grok Build support function calling?

Yes — Grok Build supports tool/function calling and structured outputs (JSON mode), so it works with agent frameworks out of the box.

Are the weights for Grok Build publicly available?

No. xAI does not publish Grok Build's weights — it is reachable through an API rather than as a file you can download and run (https://x.ai/news/grok-build-open-source, read 2026-08-14). That is xAI's decision about their own product, not a limitation of Kyma.

Is Grok Build ever served below the precision its creator released it at?

Kyma cannot say, and for this model nobody can. xAI does not publish Grok Build's weights, so there is no released checkpoint whose precision a route could be measured against. We publish "not established" rather than reading a low format as a downgrade: on several models in this catalogue a low format is exactly how the creator ships it.

How do I use Grok Build?

Kyma is OpenAI-compatible: point your SDK's base URL at https://kymaapi.com/v1, use your Kyma API key, and set the model to grok-build. Signing up is free and includes $0.50 of credit — no card required.

Does Grok Build support image inputs?

No, it only accepts and generates text. Use a multimodal model if your workflow requires vision.

How does prompt caching affect my costs?

Repeated prompt prefixes are billed at this model's cached input rate, reducing costs for stable system prompts or long conversation histories.

What happens if the serving endpoint fails during a request?

Kyma automatically reroutes the request to a healthy serving path, and the response includes the exact cost in usage.cost and the active model in the X-Kyma-Model header.

Start with $0.50 free credit — no card required.Create account →

More models by xAI

ModelContextInputOutput
xAIGrok 4.6500K$2.70$8.10
xAIGrok 4.5500K$2.73$8.189
xAIGrok 4.31M$1.92$3.838
xAIGrok 4.202M$1.763$3.528
xAIGrok 4.20 Multi-Agent2M$1.767$3.534