Grok 4
Grok 4 Fast is an xAI Grok model for reasoning, coding, vision, and general conversational tasks.
- Input / output price
- $3.00 / $15.00 per 1M
- Context
- 262K tokens
- Released
- Jul 9, 2025
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
One provider serves this model, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Azure Foundry azure_foundry/grok-4 | $3.00/M | $15.00/M |
Pricing
USD per 1M tokens on Azure Foundry, after gateway discounts.
- Input
- $3.00 per 1M
- Output
- $15.00 per 1M
Cost by volume
Total cost from 0 to 1T tokens.
Benchmarks
The Respan Index plus 18 published scores from 8 sources, each linked to where it was published.
27.6/ 100
Respan Index#100 of 175
- 100Grok 427.6
- 101Gemini 3.1 Flash-Lite26.9
- 101MiniMax M2.726.9
Published scores
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LiveCodeBench (Jan - May)xAI | 79% | xAI | Jul 9, 2025 |
| WeirdMLHåvard Tveit Ihle | 45.7% | Håvard Tveit Ihle | Oct 5, 2026 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| GPQA (no tools)xAI | 87.5% | xAI | Jul 9, 2025 |
| GPQA DiamondEpoch AI | 87% | Epoch AI | Oct 5, 2026 |
| SimpleBenchSimpleBench | 60.5% | SimpleBench | Oct 5, 2026 |
| Humanity's Last Exam (with tools)xAI | 38.6% | xAI | Jul 9, 2025 |
| Chess PuzzlesEpoch AI | 28% | Epoch AI | Oct 5, 2026 |
| Humanity's Last Exam (no tools)xAI | 25.4% | xAI | Jul 9, 2025 |
| ARC-AGI-2xAI | 15.9% | xAI | Jul 9, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| AIME 2025MathArena | 92.5% | MathArena | Oct 13, 2026 |
| AIME 2025 (no tools)xAI | 91.7% | xAI | Jul 9, 2025 |
| HMMT 2025 (no tools)xAI | 90% | xAI | Jul 9, 2025 |
| OTIS Mock AIME 2024-2025Epoch AI | 84% | Epoch AI | Oct 5, 2026 |
| USAMO 2025 (no tools)xAI | 37.5% | xAI | Jul 9, 2025 |
| Benchmark | Score | Source | Published |
|---|---|---|---|
| LMArena EloLMArena | 1411 Elo · #111 of 187 | LMArena | Oct 8, 2026 |
| LMArena VisionLMArena | 1184 Elo · #78 of 89 | LMArena | Oct 9, 2026 |
How Grok compares: Claude vs Grok, Gemini vs Grok, DeepSeek vs Grok
Compare Grok 4: Grok 4 vs Grok 4.3, Grok 4 vs Grok 4.6, Grok 4 vs Grok 4.7, Grok 4 vs Grok 4.5, Grok 4 vs Grok 4.1 Fast Reasoning, Grok 4 vs Grok Build 0.1
Apps
Use Grok 4 in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Grok 4 FAQ
Short answers, built from the data on this page.
Grok 4 is a model from xAI, released on Jul 9, 2025. Grok 4 Fast is an xAI Grok model for reasoning, coding, vision, and general conversational tasks.
On the Respan gateway, Grok 4 costs $3.00 per 1M input tokens and $15.00 per 1M output tokens on Azure Foundry, after gateway discounts.
Grok 4 is served by Azure Foundry.
Grok 4 accepts up to 262K tokens of context.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "grok-4". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Grok 4 scores 27.6 out of 100 on the Respan Index v1.1, ranking #100 of 175 models. By category: Coding 7.1, Agents 33.6, Reasoning 31.7, Knowledge & language 26.6 (estimated), and Human preference 45.4. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.
Grok 4 has 18 published benchmark scores, including LiveCodeBench (Jan - May) 79%, BALROG 43.6%, and GPQA (no tools) 87.5%. Each score links to where it was published; the data is collected by Respan.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.