VENICE ATLAS · MODEL DOSSIER · GROK 4.7

Model overview

Grok 4.7

Name: Grok 4.7
Brand: venice.ai
Price: 2.2700 USD
Availability: InStock

Grok 4.7 is xAI's multimodal chat and reasoning model with function calling, structured outputs, adjustable reasoning effort (low/medium/high/xhigh), and a 500K-token context window.

grok-4-7 · venice.ai

Text · Venice catalog$2.27 per 1M tokensPrice on Venice AI

ModalityTextOn Venice AI

Primary price$2.27 per 1M tokensper 1M tokens

Context window500KMax tokens

Benchmarks23Benchmark results

Benchmark results

See the tests behind each score. They use the benchmark’s original scoring scale.

Agents#2533.79 rating Coding#2334.84 rating General intelligence#2846.57 rating Knowledge#517.35 rating Productivity#98.68 rating Safety#1311.32 rating

Agents1 result

AA-Briefcase v1.1aa-briefcase-1.1 · agents

55.2%

ReportedOct 2026

Coding7 results

CathedralBenchcathedralbench · code

29.0%

ReportedOct 2026

CursorBench 4.0cursorbench-4.0 · code

46.3%

ReportedOct 2026

CVE-Benchcve-bench · code

36.6%

ReportedOct 2026

CyberGymcybergym · code

80.3%

ReportedOct 2026

DeepSWE 1.1deepswe-1.1 · code

71.0%

ReportedOct 2026

FrontierSWE V2frontierswe-v2 · code

29.0%

ReportedOct 2026

SWE-Marathonswe-marathon · code

46.0%

ReportedOct 2026

Engineering2 results

CADGenBenchcadgenbench · engineering

44.4%

ReportedOct 2026

EEBencheebench · engineering

66.0%

ReportedOct 2026

General intelligence1 result

GDPval (Elo)gdpval-elo · general

56.5%

ReportedOct 2026

Healthcare1 result

HealthBench Professionalhealthbench-professional · healthcare

56.7%

ReportedOct 2026

Knowledge1 result

Harvey LAB (Vals)harvey-lab · knowledge

19.6%

ReportedOct 2026

Legal1 result

Harvey's Legal Agent Benchmarkharveys-legal-agent-benchmark · legal

19.6%

ReportedSep 2026

Reasoning2 results

BixBench MCQbixbench-mcq · reasoning

88.4%

ReportedOct 2026

Terminal-Bench 4.0terminal-bench-4.0 · reasoning

38.0%

ReportedOct 2026

Safety5 results

ProtocolQA Open-Endedprotocolqa-open-ended · safety

70.4%

ReportedOct 2026

Virology Capabilities Testvct · safety

63.0%

ReportedOct 2026

WMDP-Biowmdp-bio · safety

88.1%

ReportedOct 2026

WMDP-Chemwmdp-chem · safety

84.9%

ReportedOct 2026

WMDP-Cyberwmdp-cyber · safety

88.1%

ReportedOct 2026

Science2 results

LAB-Bench Practicallab-bench-practical · science

76.8%

ReportedOct 2026

LatchBio Capabilities v1.0latchbio-capabilities · science

44.5%

ReportedOct 2026

Learn what each benchmark measures ↗

Pricing detail

Input price per 1M tokens: $2.27
Output price per 1M tokens: $6.80
Cache read price per 1M tokens: $0.57
Blended price per 1M tokens (50/50): $4.54

Prices are published by Venice AI. Venice model page ↗

Capabilities

ReasoningFunction callingVisionWeb search

Endpoint metadata

Privacy: private
Quantization: not-available
Maximum completion tokens: 200K
Uncensored: No
Beta: No
Mapping confidence: 100.0%

View model source ↗

All capabilities

Max Images: 10
Quantization: not-available
Supports E2 E E: No
Supports Vision: Yes
Supports X Search: Yes
Optimized For Code: Yes
Supports Log Probs: No
Supports Reasoning: Yes
Supports Web Search: Yes
Supports Audio Input: No
Supports Video Input: No
Default Reasoning Effort: high
Reasoning Effort Options: low, medium, high, xhigh
Supports Multiple Images: Yes
Supports Response Schema: Yes
Supports Tee Attestation: No
Supports Function Calling: Yes
Supports Reasoning Effort: Yes

Traits

most_intelligent

Related models

Grok 4.7

Benchmark results

More from xai