Grok 4.5

Tool callingStructured outputReasoningImage input

Website

xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk

Context: 500K
Released: 3mo ago
Input / 1M tokens: $2.00
Output / 1M tokens: $6.00
Cached input / 1M tokens: $0.30

Sources:models.devOpenRouter

Benchmarks

DeepSWE is the primary coding benchmark where an exact model evaluation exists. Other sourced evaluations appear below; missing scores are not zero.

Not evaluated in DeepSWE 1.1 as of 2026-09-22. Results are only shown for exact model versions in the official dataset. Official leaderboard.

Other published benchmarks

Evaluation	Reported score and source
ARC-AGI-2	52.6% Third-party evaluator · grok-4.5_high Reasoning effort: high External evaluation via Epoch AI Original-source terms apply
ARC-AGI-2	33.1% Third-party evaluator · grok-4.5_low Reasoning effort: low External evaluation via Epoch AI Original-source terms apply
ARC-AGI-2	52.6% Third-party evaluator · grok-4.5_medium Reasoning effort: medium External evaluation via Epoch AI Original-source terms apply
FrontierMath-Tier-4-v2-Private	24.4% Epoch AI · grok-4.5_high Reasoning effort: high Epoch AI evaluation
FrontierMath-Tiers-1-3-v2-Private	57.2% Epoch AI · grok-4.5_high Reasoning effort: high Epoch AI evaluation
GPQA diamond	93.4% Epoch AI · grok-4.5_high Reasoning effort: high Epoch AI evaluation
OTIS Mock AIME 2024-2025	97.8% Epoch AI · grok-4.5_high Reasoning effort: high Epoch AI evaluation
SimpleQA Verified	48.3% Epoch AI · grok-4.5_high Reasoning effort: high Epoch AI evaluation

Benchmark compilation: Epoch AI, Capabilities & benchmarking (CC BY attribution). Scores are converted to percentages and model names matched to the Vertical Tabs catalog. Individual evaluations are credited to their original sources. External results may carry separate licences and evaluation configurations; do not interpret scores from different harnesses as directly comparable.

Specifications

Developer: xAI
Model family: Grok
Type: Language model
Predecessor: —
Successor: —
Released: July 8, 2026
Model ID: x-ai/grok-4.5
Openness: Closed
License: —
Input modalities: text, image, file
Output modalities: text
Modality: text+image+file->text
Tokenizer: Grok
Max output tokens: 450K
Hugging Face: —
Source freshness: Metadata synced Oct 8, 2026, 10:17 PM UTC

Additional source evidence

Source model: xai/grok-4.5
Source family: grok
Last updated: 2026-07-08
Model context: 500K
Model output limit: 500K
Open weights: No
File attachments: Yes
Reasoning: Yes
Tool calling: Yes
Structured output: Yes
Temperature control: Yes

Published benchmarks

Benchmark	Score	Evaluation details	Evidence
SWE-Bench Pro	64.7 · resolve rate	2026-07-08	Source
SWE-Bench Multilingual	78 · resolve rate	2026-07-08	Source
Terminal-Bench	83.3 · success rate	2.1 · 2026-07-08	Source
DeepSWE	62 · resolve rate	1.0 · 2026-07-08	Source
DeepSWE	53 · resolve rate	mini-swe-agent · 1.1 · 2026-07-08	Source
SWE Marathon	29 · pass@1	2026-07-08	Source

Complete source record (JSON)

{
  "id": "xai/grok-4.5",
  "name": "Grok 4.5",
  "description": "xAI's Grok model for chat, coding, agentic tools, and lower hallucination risk",
  "family": "grok",
  "last_updated": "2026-07-08",
  "attachment": true,
  "reasoning": true,
  "tool_call": true,
  "structured_output": true,
  "temperature": true,
  "modalities": {
    "input": [
      "text",
      "image"
    ],
    "output": [
      "text"
    ]
  },
  "limit": {
    "context": 500000,
    "output": 500000
  },
  "benchmarks": [
    {
      "name": "SWE-Bench Pro",
      "score": 64.7,
      "source": "https://x.ai/news/grok-4-5",
      "metric": "resolve rate",
      "date": "2026-07-08"
    },
    {
      "name": "SWE-Bench Multilingual",
      "score": 78,
      "source": "https://x.ai/news/grok-4-5",
      "metric": "resolve rate",
      "date": "2026-07-08"
    },
    {
      "name": "Terminal-Bench",
      "score": 83.3,
      "source": "https://x.ai/news/grok-4-5",
      "metric": "success rate",
      "version": "2.1",
      "date": "2026-07-08"
    },
    {
      "name": "DeepSWE",
      "score": 62,
      "source": "https://x.ai/news/grok-4-5",
      "metric": "resolve rate",
      "version": "1.0",
      "date": "2026-07-08"
    },
    {
      "name": "DeepSWE",
      "score": 53,
      "source": "https://x.ai/news/grok-4-5",
      "metric": "resolve rate",
      "harness": "mini-swe-agent",
      "version": "1.1",
      "date": "2026-07-08"
    },
    {
      "name": "SWE Marathon",
      "score": 29,
      "source": "https://x.ai/news/grok-4-5",
      "metric": "pass@1",
      "date": "2026-07-08"
    }
  ],
  "release_date": "2026-07-08",
  "open_weights": false
}

Infrastructure

Provider availability

All providers

Provider	Endpoint	Context	Input /M tokens	Output /M tokens	Cached input /M tokens	Cache write /M tokens	Uptime 1d	Data handling
xAI	xai/zdr	500K	$2.00	$6.00	$0.30	—	100.00%	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
xAI	xai	500K	$2.00	$6.00	$0.30	—	99.65%	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
xAI	xai/zdr/priority	500K	$4.00	$12.00	$0.60	—	—	ZDR: Yes Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15
xAI	xai/priority	500K	$4.00	$12.00	$0.60	—	—	ZDR: No Training: Unknown Prompt logging: Unknown Retention: Unknown ZDR source Privacy policy Checked 2026-10-15

Provider data:OpenRouter