Grok 4 Models by xAI
13 models2025–2026Up to 2M ctxFrom $0.2/1M input
About
Grok 4 is a family of 13 AI models by xAI, released between 2025 and 2026.
Current Variants
Use-when guidance is derived from seed capabilities, context, release, and replacement fields.
8 in view5 retired
Grok Build 0.1Current
Use when the workload needs code, 256K context, and reasoning.
2026-05code256K contextreasoning
Grok 4.3Current
Use when the workload needs 1M context, reasoning, and tool use.
2026-051M contextreasoningtool use
Grok 4.20 Multi-AgentCurrent
Use when the workload needs agentic, 2M context, and reasoning.
2026-03agentic2M contextreasoning
Grok 4.20 ReasoningCurrent
Use when the workload needs reasoning, 1M context, and tool use.
2026-03reasoning1M contexttool use
Grok 4.20 Non-ReasoningCurrent
Use when the workload needs 1M context, tool use, and function calling.
2026-031M contexttool usefunction calling
Grok 4.20Current
Use when the workload needs 1M context, reasoning, and tool use.
2026-021M contextreasoningtool use
Grok 4.1Current
Use when the workload needs 131K context, reasoning, and tool use.
2025-11131K contextreasoningtool use
Grok 4 HeavyCurrent
Use when the workload needs 256K context and multimodal inputs.
2025-07256K contextmultimodal inputs
| Model | Use when | Released | Signals | Status |
|---|---|---|---|---|
| Grok Build 0.1 | Use when the workload needs code, 256K context, and reasoning. | 2026-05 | code256K contextreasoning | Current |
| Grok 4.3 | Use when the workload needs 1M context, reasoning, and tool use. | 2026-05 | 1M contextreasoningtool use | Current |
| Grok 4.20 Multi-Agent | Use when the workload needs agentic, 2M context, and reasoning. | 2026-03 | agentic2M contextreasoning | Current |
| Grok 4.20 Reasoning | Use when the workload needs reasoning, 1M context, and tool use. | 2026-03 | reasoning1M contexttool use | Current |
| Grok 4.20 Non-Reasoning | Use when the workload needs 1M context, tool use, and function calling. | 2026-03 | 1M contexttool usefunction calling | Current |
| Grok 4.20 | Use when the workload needs 1M context, reasoning, and tool use. | 2026-02 | 1M contextreasoningtool use | Current |
| Grok 4.1 | Use when the workload needs 131K context, reasoning, and tool use. | 2025-11 | 131K contextreasoningtool use | Current |
| Grok 4 Heavy | Use when the workload needs 256K context and multimodal inputs. | 2025-07 | 256K contextmultimodal inputs | Current |
Release Timeline
7 release groups2026-05
2 current
Grok 4.3
Current1M contextreasoningtool use
Grok Build 0.1
Currentcode256K contextreasoning
2026-03
3 current
Grok 4.20 Multi-Agent
Currentagentic2M contextreasoning
Grok 4.20 Non-Reasoning
Current1M contexttool usefunction calling
Grok 4.20 Reasoning
Currentreasoning1M contexttool use
2026-02
1 current
Grok 4.20
Current1M contextreasoningtool use
2025-11
1 current · 1 retired
Grok 4.1
Current131K contextreasoningtool use
Grok 4.1 Fast
Replaced2M contextreasoningtool use
2025-09
2 retired
Grok 4 Fast Non-Reasoning
Replaced2M contextreasoningmultimodal inputs
Grok 4 Fast Reasoning
Replaced2M contextreasoningmultimodal inputs
2025-08
1 retired
Grok Code Fast 1
Replacedcode262K context314B parameters
2025-07
1 current · 1 retired
Grok 4
Replaced256K contextreasoningtool use
Grok 4 Heavy
Current256K contextmultimodal inputs
Replaced By
Replaced
Keep for legacy integrations; evaluate Grok 4.3 before new work.
Replaced
Keep for legacy integrations; evaluate Grok 4.3 before new work.
Keep for legacy integrations; evaluate Grok 4.3 before new work.
Replaced
Keep for legacy integrations; evaluate Grok Build 0.1 before new work.
Specifications(13 models)
| Model | Released | Context | Parameters | Vision | Multimodal | Reasoning | Fn Calling | Tool Use | Structured Outputs | Code Exec |
|---|---|---|---|---|---|---|---|---|---|---|
| Grok Build 0.1 | 2026-05 | 256K | — | No | No | Yes | Yes | Yes | Yes | No |
| Grok 4.3 | 2026-05 | 1M | ~0.5T | Yes | Yes | Yes | Yes | Yes | Yes | No |
| Grok 4.20 Multi-Agent | 2026-03 | 2M | — | Yes | Yes | Yes | Yes | Yes | Yes | No |
| Grok 4.20 Reasoning | 2026-03 | 1M | — | Yes | Yes | Yes | Yes | Yes | Yes | No |
| Grok 4.20 Non-Reasoning | 2026-03 | 1M | — | Yes | Yes | No | Yes | Yes | Yes | No |
| Grok 4.20 | 2026-02 | 1M | — | Yes | Yes | Yes | Yes | Yes | Yes | No |
| Grok 4.1 | 2025-11 | 131K | — | No | Yes | Yes | Yes | Yes | No | No |
| Grok 4 Heavy | 2025-07 | 256k | — | No | Yes | No | No | No | No | No |
Available From(4 providers)
Pricing
| Model | Provider | Input / 1M | Output / 1M | Type |
|---|---|---|---|---|
| Grok Build 0.1 | xAI Console | $1 | $2 | Serverless |
| Grok 4.20 | xAI Console | $1.25 | $2.5 | Serverless |
| Grok 4.3 | xAI Console | $1.25 | $2.5 | Serverless |
| Grok 4.20 Multi-Agent | xAI Console | $1.25 | $2.5 | Serverless |
| Grok 4.3 | OpenRouter | $1.25 | $2.5 | Serverless |
| Grok 4.20 | OpenRouter | $1.25 | $2.5 | Serverless |
| Grok 4.20 Reasoning | xAI Console | $1.25 | $2.5 | Serverless |
| Grok 4.20 Non-Reasoning | xAI Console | $1.25 | $2.5 | Serverless |
| Grok 4.20 Multi-Agent | OpenRouter | $2 | $6 | Serverless |
Comparisons
- GPT-4o (08-06) vs Grok 4
- o3 vs Grok 4
- Grok 4 Fast Reasoning vs o3
- Claude Sonnet 4.6 vs Grok 4
- Claude Opus 4.6 vs Grok 4
- Grok 4 Fast Reasoning vs Claude Opus 4.6
- DeepSeek V4 Pro vs Grok 4
- DeepSeek R1 vs Grok 4
Frequently Asked Questions
- What is Grok 4 used for?
- Grok 4 is used for code, agentic, and reasoning. The family description and listed model capabilities point to those workloads as the best fit.
- How does Grok 4 compare to Grok 1?
- Grok 4 by xAI is strongest where you need code, while Grok 1 by xAI is the closest related family to check for reasoning. Grok 4 has 13 listed variants and reaches up to 2M context, so compare the specs and pricing tables before choosing a production model.
- Which Grok 4 model should I use?
- For the lowest listed input price, start with Grok 4.1 Fast through OpenRouter at $0.2/1M input tokens. For the most capable/latest local choice, evaluate Grok 4.20 Multi-Agent with 2M context and reasoning, tool use, function calling, structured outputs, and multimodal inputs.
Related Model Families
Models(13)
Grok Build 0.1
2026-05256K1 provider
Reasoning
Grok 4.3
2026-051M~0.5T3 providers
MultimodalReasoning
Grok 4.20 Multi-Agent
2026-032M2 providers
MultimodalReasoning
Grok 4.20 Reasoning
2026-031M1 provider
MultimodalReasoning
Grok 4.20 Non-Reasoning
2026-031M1 provider
Multimodal
Grok 4.20
2026-021M2 providers
MultimodalReasoning
Grok 4.1
2025-11131K
MultimodalReasoning
Grok 4 Heavy
2025-07256k
Multimodal