LLMx-ai

xAI: Grok Build 0.1

Grok Build 0.1 is xAI’s fast coding model trained specifically for agentic software engineering workflows. It supports text and image inputs with text output, and is optimized for interactive coding...

Anyone in the Space can @-mention xAI: Grok Build 0.1 with the team's shared context — pooled credits, one chat, one memory.

All models

Starter is free forever — 1 Space, 100 credits/month, 1 MCP. No card.

Verdict

Grok Build 0.1 offers a massive 256K context window at aggressive pricing—$1/$2 per Mtok undercuts most frontier models. The lack of public benchmarks makes capability assessment difficult, but the economics favor teams processing long documents or transcripts where cost per token matters more than peak reasoning. Best for workloads where context length is the bottleneck and you can validate output quality yourself.

Best for

  • Long-document analysis under budget constraints
  • Processing multi-hour meeting transcripts
  • Cost-sensitive batch inference jobs
  • Image-text tasks with extended context
  • Prototyping before committing to pricier models

Strengths

The 256K context window handles entire codebases, books, or multi-hour transcripts in one pass. Pricing sits 50-75% below Claude Opus or GPT-4 Turbo on output tokens, making it viable for high-volume summarization or extraction. Vision support adds flexibility for document workflows mixing screenshots and text. The economics work for teams that need reach rather than peak accuracy.

Trade-offs

No public benchmarks means you're flying blind on reasoning quality, code generation accuracy, or instruction-following compared to Claude Sonnet 4.5 or GPT-4o. Early build number suggests rapid iteration—expect API changes or behavior shifts. Without MMLU, HumanEval, or GPQA scores, you'll need to run your own evals before trusting it for critical tasks. The pricing advantage disappears if you need multiple retries to get usable output.

Specifications

Provider
x-ai
Category
llm
Context length
256,000 tokens
Max output
Modalities
text, image
License
proprietary
Released
2026-05-20

Pricing

Input
$1.00/Mtok
Output
$2.00/Mtok
Model ID
x-ai/grok-build-0.1

Per-token prices show what the model costs upstream. On Switchy your team draws from one shared org credit pool — one plan, one balance for everyone.

Team cost calculator

Estimated monthly spend
$22.88
17.6M tokens / month
5 seats · 80 msgs/day

Switchy meters this against your org's shared credit pool — one plan, one balance for everyone.

Providers

ProviderContextInputOutputP50 latencyThroughput30d uptime
x-ai256k$1.00/Mtok$2.00/Mtok

Performance

Performance snapshots are collected daily. Check back after the next ingestion run.

Benchmarks

Public benchmark scores are not available yet for this model. Check back after the next ingestion run.

Works well with

Top MCPs

Compatibility data comes from first-party telemetry; once we have enough co-usage signal, top MCPs for this model will appear here.

How Switchy teams use it

Not enough Spaces have used this model yet to share anonymised team stats. We wait for at least 50 distinct Spaces per week before publishing any aggregate.

Starter prompts

Summarize Long Transcript

Read this entire transcript and produce a structured summary with: (1) key decisions made, (2) action items with owners, (3) unresolved questions. Use timestamps where relevant.
Open in a Space →

Extract Contract Clauses

Review these contracts and extract all clauses related to termination rights, payment terms, and liability caps. Format as a comparison table with document references.
Open in a Space →

Analyze Codebase Structure

Analyze this codebase and describe: (1) main architectural patterns, (2) module dependencies, (3) potential refactoring opportunities. Focus on high-level structure, not line-by-line review.
Open in a Space →

Compare Product Screenshots

Compare these product screenshots and identify: (1) UI changes between versions, (2) new features visible, (3) potential usability concerns. Reference specific screen elements.
Open in a Space →

Synthesize Research Papers

Read these research papers and write a synthesis covering: (1) common methodologies, (2) conflicting findings, (3) gaps in current research. Cite paper titles when referencing specific claims.
Open in a Space →
Data last verified 2 hours ago.Sources aggregated hourly to weekly. See docs/architecture/model-directory.md.