LLM Reference

Grok 4

Released
2025-07-09
Last refreshed
2026-06-15
Status
Researched 25d ago
DeprecatedProprietaryCommercial use: conditionalMultimodalCodingRAGAgentsLong contextVisionClassificationJSON / Tool use

Grok 4 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 256k context window
  • Buyers comparing 3 tracked provider routes

Do not use it for

  • New production launches
Specifications
Family
Grok 4
Released
2025-07-09
Context
256k
Architecture
Decoder Only
Specialization
general
Openness
Proprietary
License
ProprietaryCommercial use: conditional
Training
Pretrained
Created by

Ethical AI for universal truth-seeking

San Francisco, California, United States
Founded 2023
Website
Pricing
Output / 1M
$15.00
Input / 1M
$3.00

Cheapest of 4 routes · OpenRouter

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

About

Original Grok 4 API model (grok-4-0709) with 256K context, reasoning, text and image input, function calling, structured outputs, live browsing, and code execution support. xAI lists May 15, 2026 as the API retirement date for this model; new integrations should use Grok 4.3.

Grok 4 is a proprietary model. The structured metadata tracks a 256k-token context window, multimodal input, reasoning, function calling, tool use, structured outputs, and code execution. This page tracks provider routes through Microsoft Foundry, OpenRouter, Replicate API, and 1 more, with the cheapest tracked route listed at $1.25 input and $2.5 output per 1M tokens. Headline tracked benchmarks include Aider Polyglot 79.6, MMLU PRO 87.0, and SWE-bench Verified 76.7.

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

Coding

2 relevant benchmarks in the decision map.

RAG

Included by capability and metadata signals in the decision map.

Agents

2 relevant benchmarks 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
OpenRouter$3.00$15.00
Serverless
Replicate API$7.20$36.00
Serverless
Microsoft Foundry--
ServerlessProvisionedPartial

Available via routers & gateways(6)

Capabilities

VisionMultimodalReasoningFunction CallingTool UseStructured OutputsCode ExecutionPrompt Caching

Benchmark peer barsfor Coding

Benchmark scores(4)

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 Polyglot79.62026-04 (high)https://aider.chat/docs/leaderboards
MMLU PRO87.0https://huggingface.co/spaces/TIGER-Lab/MMLU-Pro
SWE-bench Verified76.7SWE-bench Verifiedhttps://www.swebench.com/verified.html
τ-bench78.9τ-benchhttps://taubench.com/

Migration checks

No linked migration route is available for this model yet.

API versions

grok-4-0709grok-4
Show all 69 popular comparisonssorted by 7-day search impressions
Grok 4 vs Gemini 2.5 Flash4KGrok 4 vs Gemini 2.5 Pro4KGrok 4 vs Grok 3 Mini3KGrok 4 vs DeepSeek V3.13KGrok 4 vs Grok-32KGrok 4 vs Qwen3-Max2KGrok 4 vs DeepSeek V32KGrok 4 vs Claude Mythos Preview1KGrok 4 vs GPT-5.51KGrok 4 vs o3 Mini841Grok 4 vs DeepSeek V3.2777Grok 4 vs Composer 2.5712Grok 4 vs Gemini 3.5 Flash689Grok 4 vs Kimi K2 Thinking616Grok 4 vs Qwen3.6-27B499Grok 4 vs GPT-5.5 Pro488Grok 4 vs GPT-5.4469Grok 4 vs GLM-5.1433Grok 4 vs DeepSeek R1 0528275Grok 4 vs Kimi K2.5236Grok 4 vs Step 3.5 Flash233Grok 4 vs Claude 3.7 Sonnet219Grok 4 vs Llama 3.1 70B Instruct211Grok 4 vs Qwen3.6-35B-A3B205Grok 4 vs Mistral Large 2202Grok 4 vs Claude Opus 4.5186Grok 4 vs GLM-5182Grok 4 vs Composer 2166Grok 4 vs Llama 2 13B Chat164Grok 4 vs Qwen2.5-72B159Grok 4 vs Claude Sonnet 4.5134Grok 4 vs Llama 3 70B Instruct126Grok 4 vs Trinity-Large-Thinking120Grok 4 vs Ling-2.6-1T119Grok 4 vs Hunyuan Hy3 Preview113Grok 4 vs Qwen3-235B-A22B105Grok 4 vs Together AI - Llama 3 8B Lite96Grok 4 vs Xiaomi MiMo-V2.5-TTS-Series93Grok 4 vs GLM-5V-Turbo92Grok 4 vs Nano Banana (Gemini 2.5 Flash Image)80Grok 4 vs Llama 3 8B Instruct74Grok 4 vs Qwen2.5-72B-Instruct69Grok 4 vs Qwen3.5-27B63Grok 4 vs DeepSeek R1 Distill Llama 70B60Grok 4 vs Xiaomi MiMo-V2.548Grok 4 vs Qwen3.5-35B-A3B48Grok 4 vs GLM-5 Turbo45Grok 4 vs Gemini 2.5 Pro Preview 06-0535Grok 4 vs Llama Guard 3 1B32Grok 4 vs Phi-3 Mini 4k30Grok 4 vs Qwen2.5-7B-Instruct28Grok 4 vs Llama 3.2 1B Instruct27Grok 4 vs Trinity-Large-Preview25Grok 4 vs Phi-4 Mini Flash Reasoning25Grok 4 vs Qwen3.5-397B-A17B24Grok 4 vs Gemma 7B Instruct23Grok 4 vs Kimi K2 Thinking Turbo23Grok 4 vs GLM-5 9B22Grok 4 vs Qwen3.5-122B-A10B20Grok 4 vs Llama 4 Scout 17B-16E Instruct19Grok 4 vs Mistral Nemotron18Grok 4 vs Mixtral 8x7B12Grok 4 vs Code Cushman 00210Grok 4 vs ShieldGemma 9B10Grok 4 vs Code Davinci 0017Grok 4 vs Gemini 2.5 Pro Preview 05-066Grok 4 vs Mixtral 8x22B Instruct v0.35Grok 4 vs Qwen2-7B-Instruct3Grok 4 vs Qwen3.6 Max Preview3