Terminal-Bench 4.0
grok-build1.0.5
Reasoning effort none
Tested model identity
Grok 4.6xai/grok-4.6Pass rate20.3%
95% CI 17.21%–23.39%
n = 330Checked
x-aiListed Aug 12, 2026
SpaceXAI: Grok 4.6
Grok 4.6 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM. It is succeeded by Grok 4.7.
Context window500K
Max output450K
Provider endpoints8
Benchmark results0
Agent runs1
Measured performance
All leaderboards ↗Benchmark results
No published results in this index yet
Scores appear here when an evaluation matches this exact model.
Model + harness
All agent results ↗Agent runs
grok-build
Access & cost
14 quotesPrices across providers
Your token mix
USD · listed token ratesOpenRouter
Catalog quote- Input
- $2.00
- Output
- $6.00
- Cached input
- $0.50
Experiential
Standard list rate
- Input
- $2.00
- Output
- $6.00
- Cached input
- $0.50
Catalog list rate. Plan allowances and temporary discounts are separate.
- Input
- $2.00
- Output
- $6.00
- Cached input
- $0.50
Web search $0.005/search
- Input
- $4.00
- Output
- $12.00
- Cached input
- $1.00
Web search $0.005/search · A rate applies when all its listed conditions match. Dates and times use UTC.
- Input
- $2.00
- Output
- $6.00
- Cached input
- $0.50
Web search $0.005/search
- Input
- $4.00
- Output
- $12.00
- Cached input
- $1.00
Web search $0.005/search · A rate applies when all its listed conditions match. Dates and times use UTC.
- Input
- $2.20
- Output
- $6.60
- Cached input
- $0.55
Web search $0.005/search
- Input
- $4.40
- Output
- $13.20
- Cached input
- $1.10
Web search $0.005/search · A rate applies when all its listed conditions match. Dates and times use UTC.
- Input
- $2.20
- Output
- $6.60
- Cached input
- $0.55
Cache write $0/M tokens · Web search $0.01/search
Amazon Bedrock
via OpenRouteramazon-bedrock/us-west-2 · prompt over 200000 tokens · rate option 1
Conditional rate- Input
- $4.40
- Output
- $13.20
- Cached input
- $1.10
Cache write $0/M tokens · Web search $0.01/search · A rate applies when all its listed conditions match. Dates and times use UTC.
- Input
- $4.00
- Output
- $12.00
- Cached input
- $1.00
Web search $0.005/search
xAI
via OpenRouterxai/zdr/priority · tier=priority · prompt over 200000 tokens · rate option 1
Conditional rate- Input
- $8.00
- Output
- $24.00
- Cached input
- $2.00
Web search $0.005/search · A rate applies when all its listed conditions match. Dates and times use UTC.
- Input
- $4.00
- Output
- $12.00
- Cached input
- $1.00
Web search $0.005/search
xAI
via OpenRouterxai/priority · tier=priority · prompt over 200000 tokens · rate option 1
Conditional rate- Input
- $8.00
- Output
- $24.00
- Cached input
- $2.00
Web search $0.005/search · A rate applies when all its listed conditions match. Dates and times use UTC.
Model specifications
- Developer
- x-ai
- Modality
- Language
- Context
- 500,000 tokens
- Maximum output
- 450,000 tokens
- Weights
- Not reported
- Provider listed
- Aug 12, 2026
- First discovered
- Oct 16, 2026
Exact identities
- openrouter
x-ai/grok-4.6 - experiential
grok-4.6
Sources
Updated Oct 18, 2026
More from x-ai
View all ↗x-aiListed 26 days ago
SpaceXAI: Grok 4.7
Grok 4.7 is SpaceXAI's flagship model for coding, agentic tasks, and knowledge work, succeeding Grok 4.6. It is particularly strong at long-running software engineering tasks, verifying its own work, and...
500K contextImage inputTool callingNo reported score
No reported score
$2.00in$6.00out/ 1M tokens · USDExperiential · 7 endpointsStandard · fewer than 200,000 input tokens
x-aiListed Jul 23
SpaceXAI: Grok STT 1.0
Grok STT is SpaceXAI's speech-to-text model, available via the REST /v1/stt endpoint. It supports transcription with word-level timestamps, optional speaker diarization, and multichannel audio.
Audio inputNo reported score
No reported score
x-aiListed Jul 8
SpaceXAI: Grok 4.5
Grok 4.5 is a model from SpaceXAI with frontier performance on coding, knowledge work, and STEM.
500K contextImage inputTool callingNo reported score
No reported score
x-aiListed Jul 8
xAI: Grok Latest
This model always redirects to the latest Grok model from xAI.
500K contextImage inputTool callingNo reported score
No reported score