BenchLeader

Grok Build 0.1

Price#153 of 257
$1.25per 1M tokens
Dearer than most
1.5× the median
Speed#29 of 218
170tokens/s
Top quarter
2.1× the median

Good value at this level: no ranked model within 2 Index points costs three quarters of the price or less.

No cheaper ranked model scores higher: it is on the price frontier.

As of 16 Nov 2026, Grok Build 0.1 by SpaceXAI is not yet ranked on the BenchLeader Index, which needs at least five independent results across two categories. API pricing: $1.00 per 1M input tokens and $2.00 per 1M output tokens ($1.25 blended at 3:1), list price on 16 Nov 2026. It streams about 170 tokens/s (Artificial Analysis). Released 29 May 2026.

Key facts (as of 16 Nov 2026)

  • Grok Build 0.1 API pricing: $1.00 per 1M input tokens and $2.00 per 1M output tokens ($1.25 blended at 3:1) (list price, 16 Nov 2026).
  • Grok Build 0.1 streams about 170 tokens/s (Artificial Analysis, 16 Nov 2026).
  • Grok Build 0.1 was released on 29 May 2026 (SpaceXAI).

In detail. Grok Build 0.1 is a SpaceXAI proprietary reasoning model, released 29 May 2026. It is not yet ranked: the index needs at least five independent results across two categories. At $1.25 per million tokens blended it is mid-priced. Output speed of 170 tokens per second puts it in the fastest quarter, with a first answer in 10.9 s. Last measured 16 Jun 2026.

Blended price
$1.25/M
$1.00 in · $2.00 out
via Artificial Analysis
Output speed
170 tok/s
measured by Artificial Analysis
First answer
11 s
first token 1.31 s
Context
256k
via OpenRouter
Full answer
24 s
last measured 13 Nov 2026
Cost per task
–
Tokens per task
–
Released
29 May 2026
How it scores by categoryDashed line = average model (50). One step of 15 = one standard deviation.
  1. Coding54
  2. Agents & tools41
  3. Multimodal59
  4. Long context62

Get an email when Grok Build 0.1 gets its first benchmark results

And when SpaceXAI ships a new model, plus the weekly review on Mondays.

Choose providers and emails

Benchmark results

See all LLM benchmarks. One column per reasoning effort. Rank is among every configuration of every model on that benchmark. Hover a score for the run it came from.

Reasoning

Benchmarknot statedSource
LiveBench 1.0 Reasoningnot in index76.4%#60LiveBench
GPQA Diamond (AA)not in index89.5%#75Artificial Analysis
Humanity's Last Exam (AA)not in index38.3%#112Artificial Analysis
CritPtnot in index9.1%#143Artificial Analysis

Coding

Benchmarknot statedSource
SciCode50.2%#120SciCode
LiveBench 1.0 Codingnot in index65.4%#67LiveBench
Vibe Code Bench v1.1not in index13.3%#102Vals AI
Terminal-Bench 2.1 (AA)not in index52.1%#117Artificial Analysis

Agents & tools

Benchmarknot statedSource
LiveBench Agentic Codingnot in index45.8%#53LiveBench
GDPval-AA v2.1not in index1073#168Artificial Analysis
τ³-Banking (AA)13.4%#129Artificial Analysis
GBAEvalnot in index2.4%#15Epoch AI Benchmarking Hub

Maths

Benchmarknot statedSource
LiveBench Mathematicsnot in index78.4%#64LiveBench

Knowledge

Benchmarknot statedSource
LiveBench 1.0 Data Analysisnot in index70.8%#49LiveBench

Instruction following

Benchmarknot statedSource
LiveBench Languagenot in index72.5%#58LiveBench
LiveBench Instruction Followingnot in index65.2%#45LiveBench

Multimodal

Benchmarknot statedSource
MMMU-Pro76.5%#98Artificial Analysis

Long context

Benchmarknot statedSource
AA-LCR v1.174.7%#176Artificial Analysis

Composite

Benchmarknot statedSource
LiveBench 1.0not in index67.8%#61LiveBench
AA Intelligence Index v4.3.2not in index27.2#151Artificial Analysis
AA Progress Index v1not in index280.5#178Artificial Analysis

API pricing: where to run it

Every provider serving this model through OpenRouter, with throughput and first-token latency measured on live traffic over the last 30 minutes and each provider’s own price. Purple marks the best in each column.

ProviderSpeedFirst tokenInput $/MOutput $/MContextQuantisation
SpaceXAI129 tok/s2.40 s$1.00$2.00256k–
SpaceXAI107 tok/s2.87 s$1.00$2.00256k–

What a task costs

Estimates from list price, output speed and time to first answer for the best configuration. “With caching” assumes three-quarters of the input is served from the prompt cache at $0.200 per 1M. Reasoning tokens are not modelled.

WorkloadTokens in / outCostWith cachingTime
Chat reply400 / 300$0.0010$0.000812.7 s
Summarize a 30-page report12,000 / 600$0.013$0.006014.5 s
Code edit6,000 / 1,500$0.0090$0.005419.7 s
Agentic coding session60,000 / 4,000$0.068$0.03234.4 s
Structured extraction2,000 / 200$0.0024$0.001212.1 s

More from SpaceXAI

New this month

See also

Questions people ask

Why does Grok Build 0.1 have no BenchLeader Index score?
The index needs at least five independent results across at least two categories, and as of 16 Nov 2026 Grok Build 0.1 does not have them yet. Launch-post scores are never used, so it is ranked once independent publishers have measured it.
How much does Grok Build 0.1 cost per 1M tokens?
As of 16 Nov 2026, Grok Build 0.1 costs $1.00 per 1M input tokens and $2.00 per 1M output tokens, $1.25 blended (three input tokens per output token).
When was Grok Build 0.1 released?
SpaceXAI released Grok Build 0.1 on 29 May 2026.

Data as of 16 Nov 2026. Compare with another model.

Cite as: BenchLeader, “Grok Build 0.1: benchmarks, pricing, speed and rank”, data as of 16 Nov 2026, https://www.benchleader.com/models/grok-build-0-1.