LLM Reference

Grok-3

Released
2025-02-17
Last refreshed
2026-06-30
Status
Researched 43d ago
DeprecatedProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool use

Grok-3 is a legacy integration reference; evaluate Grok 4.3 before starting new work.

Use it for

  • Teams maintaining an existing integration
  • Workloads that can use a 131k context window
  • Buyers comparing 3 tracked provider routes

Do not use it for

  • New production launches
Specifications
Family
Grok 3
Released
2025-02-17
Context
131k
Knowledge cutoff
2025-04
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Created by

Ethical AI for universal truth-seeking

San Francisco, California, United States
Founded 2023
Website
Pricing
Output / 1M
$2.40
Input / 1M
$0.800

Cheapest of 4 routes · Chutes AI

This model is deprecated. xAI recommends switching to Grok 4.3.

About

Grok-3 is a 2025 xAI model confirmed for May 15, 2026 retirement; use Grok 4.3 for current API work.

Grok-3 is a proprietary model in the Grok 3 family. The structured metadata tracks a 131k-token context window, multimodal input, reasoning, function calling, tool use, and structured outputs. This page tracks provider routes through OpenRouter, xAI Console, Chutes AI, and 1 more, with the cheapest tracked route listed at $0.8 input and $2.4 output per 1M tokens. Headline tracked benchmarks include Aider Polyglot 53.3, Chatbot Arena 1405.0, and Massive Multi-discipline Multimodal Understanding 78.0.

Top use-case fit: coding, agents, and build tasks

Coding

3 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

Included by capability and metadata signals in the decision map.

Provider price ladder

Compare all 4

Compare API pricing across 3 providers for input and output tokens, batch, and cached reads when available.

ProviderInput / 1MOutput / 1MRoute
Chutes AI$0.800$2.40
Serverless
Microsoft Foundry$3.00$15.00
Serverless
OpenRouter$3.00$15.00
Serverless

Available via routers & gateways(6)

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured Outputs

Benchmark peer barsfor Coding

Benchmark scores(8)

Scores are benchmark-specific and are direction-aware: the same numeric gap can mean very different outcomes across suites. Use the leaderboard context and this model's provider route to decide whether the winning margin is meaningful for your workload.
BenchmarkScoreVersionSource
Aider Polyglot53.32026-04https://aider.chat/docs/leaderboards
Chatbot Arena1405.0https://lmarena.ai
Massive Multi-discipline Multimodal Understanding78.0https://mmmu-benchmark.github.io/
MMLU PRO79.9https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
Google-Proof Q&A84.6https://x.ai/blog/grok-3
AIME 202593.3https://x.ai/blog/grok-3
LiveCodeBench79.4https://x.ai/blog/grok-3
HumanEval94.5https://x.ai/blog/grok-3

Migration checks

No linked migration route is available for this model yet.

Compare Grok-3 with other models

Show all 59 popular comparisonssorted by 7-day search impressions
Grok-3 vs Qwen3.6-27B127Grok-3 vs Hunyuan Hy3 Preview124Grok-3 vs GLM-5122Grok-3 vs Gemini 2.5 Pro112Grok-3 vs Qwen3.6-35B-A3B90Grok-3 vs o379Grok-3 vs Claude Opus 4.579Grok-3 vs Llama 3.2 1B72Grok-3 vs o3 Mini70Grok-3 vs Qwen2.5-72B-Instruct68Grok-3 vs DeepSeek V4 Flash64Grok-3 vs Trinity-Large-Thinking61Grok-3 vs Together AI - Llama 3 8B Lite61Grok-3 vs Kimi K2.558Grok-3 vs DeepSeek R1 052858Grok-3 vs Llama 3 70B Instruct52Grok-3 vs Gemini 2.5 Flash46Grok-3 vs Mistral Large 3 675B Instruct45Grok-3 vs Qwen3.5-27B40Grok-3 vs Llama 3 8B Instruct37Grok-3 vs Llama 2 70B Chat37Grok-3 vs Qwen3.5-35B-A3B37Grok-3 vs DeepSeek V336Grok-3 vs Llama 3.1 405B Instruct34Grok-3 vs Claude Opus 4.630Grok-3 vs GPT-5.3-Codex28Grok-3 vs GPT-5.425Grok-3 vs Tencent Hunyuan Turbo S25Grok-3 vs GPT-5.4-Cyber22Grok-3 vs Qwen3.5-122B-A10B20Grok-3 vs Claude Sonnet 4.520Grok-3 vs Phi-3 Mini 4k18Grok-3 vs GPT-5.218Grok-3 vs Llama 3.2 1B Instruct17Grok-3 vs DeepSeek V3.215Grok-3 vs Gemma 7B Instruct14Grok-3 vs DeepSeek R1 Lite14Grok-3 vs Mixtral 8x7B13Grok-3 vs Mixtral 8x22B Instruct v0.313Grok-3 vs Mixtral 8x22B v0.113Grok-3 vs Phi-4 Mini Reasoning13Grok-3 vs Code Cushman 00112Grok-3 vs Qwen3.6 Max Preview11Grok-3 vs o3 Deep Research11Grok-3 vs Together AI Qwen2-7B-Instruct10Grok-3 vs Code Davinci 00110Grok-3 vs Qwen3-Max5Grok-3 vs Qwen3-235B-A22B5Grok-3 vs Gemini 2.5 Flash Live API4Grok-3 vs Code Cushman 0023Grok-3 vs Qwen3.5-397B-A17B3Grok-3 vs Phi-4 Mini Flash Reasoning3Grok-3 vs DeepSeek V3 Base2Grok-3 vs Gemini 2.5 Pro Computer Use Preview2Grok-3 vs Mistral Nemotron2Grok-3 vs Qwen3.5-4B2Grok-3 vs GPT-5.4 Pro1Grok-3 vs Qwen2-7B-Instruct1Grok-3 vs GLM-5V-Turbo1

Frequently asked questions

What is the context window of Grok-3?

Grok-3 has a context window of 131k tokens.

How much does Grok-3 cost?

Grok-3 pricing ranges from $0.8/1M to $3/1M input tokens depending on the provider.

When was Grok-3 released?

Grok-3 was released on 2025-02-17.

Which providers offer Grok-3?

Grok-3 is available from 4 providers: OpenRouter, xAI Console, Chutes AI, Microsoft Foundry.

What benchmarks has Grok-3 been tested on?

Grok-3 has been evaluated on 8 benchmarks, including Aider Polyglot, Chatbot Arena, Massive Multi-discipline Multimodal Understanding, MMLU PRO, Google-Proof Q&A.