grok-4.20-0309-non-reasoning
oah/grok-4-fast-non-reasoningDeploy grok-4.20-0309-non-reasoning with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
ReasoningInput: Free/MOutput: Free/M
Why deploy Grok through AI Security Gateway?
Automatic PII Redaction
Every Grok request is scanned for 28+ PII entity types — SSNs, credit cards, emails, API keys, and more — before it reaches any provider.
Smart Cost Routing
Grok is available across 1 providers. Our Smart Router picks the cheapest one per-request. 30% managed markup / 0% on Pro BYOK.
Native SDK or OpenAI Compatible
Use the AISG SDK (pip install aisg) for typed metadata and error handling, or change two lines in your OpenAI SDK. Both work.
Full Observability
Per-request logging of token counts, latency, DLP violations, and cost. Never wonder what your AI spend is again.
Grok Strengths
- Competitive with GPT-4 class models
- Strong conversational and knowledge-retrieval performance
- Real-time information awareness
- Competitive pricing in the premium tier
Available Grok Models (9)
grok-4.20-0309-reasoning
oah/grok-4.20-0309-reasoningDeploy grok-4.20-0309-reasoning with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
ReasoningInput: $2.00/MOutput: $6.00/M
grok-4.20-multi-agent-0309
oah/grok-4.20-multi-agentDeploy grok-4.20-multi-agent-0309 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
ReasoningInput: Free/MOutput: Free/M
grok-4.3
oah/grok-4.3Deploy grok-4.3 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
ReasoningInput: $1.25/MOutput: $2.50/M
grok-build-0.1
oah/grok-build-0.1Deploy grok-build-0.1 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
Input: Free/MOutput: Free/M
grok-imagine-image
oah/grok-imagine-imageDeploy grok-imagine-image with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
Input: Free/MOutput: Free/M
grok-imagine-image-quality
oah/grok-imagine-image-qualityDeploy grok-imagine-image-quality with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
Input: Free/MOutput: Free/M
grok-imagine-video
oah/grok-imagine-videoDeploy grok-imagine-video with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
Input: Free/MOutput: Free/M
grok-imagine-video-1.5-preview
oah/grok-imagine-video-1.5-previewDeploy grok-imagine-video-1.5-preview with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
Input: Free/MOutput: Free/M
Grok Pricing Comparison (per 1M tokens, USD)
Input / Output pricing by provider. Managed Mode adds a 30% managed markup. Pro BYOK = 0% markup.
| Model | Params | Context | Vision | xAI (Grok) |
|---|---|---|---|---|
grok-4.20-0309-non-reasoning oah/grok-4-fast-non-reasoning | — | — | No | — |
grok-4.20-0309-reasoning oah/grok-4.20-0309-reasoning | — | — | No | $2.00/$6.00 |
grok-4.20-multi-agent-0309 oah/grok-4.20-multi-agent | — | — | No | — |
grok-4.3 oah/grok-4.3 | — | — | No | $1.25/$2.50 |
grok-build-0.1 oah/grok-build-0.1 | — | — | No | — |
grok-imagine-image oah/grok-imagine-image | — | — | No | — |
grok-imagine-image-quality oah/grok-imagine-image-quality | — | — | No | — |
grok-imagine-video oah/grok-imagine-video | — | — | No | — |
grok-imagine-video-1.5-preview oah/grok-imagine-video-1.5-preview | — | — | No | — |
Grok Direct vs AI Security Gateway
What you get at each pricing tier. Hub adds security, governance, and multi-provider routing on top of raw API access.
| Mode | What You Pay | PII Redaction | Budget Caps | Routing | Audit Trail |
|---|---|---|---|---|---|
| Direct to xAI | Provider pricing only | None | None | Manual | None |
| Hub — Managed Mode | Provider + 30% markup | 28+ PII types | Per-key hard caps | Smart Router | Full compliance log |
| Hub — Pro BYOK ($29/mo) | Direct to provider (0% markup) | 28+ PII types | Per-key hard caps | Smart Router | Full compliance log |
Popular Use Cases
1
Conversational AI with up-to-date knowledge
2
General-purpose assistant applications
3
Alternative to GPT-4 for diversified provider strategy
Quick Integration
# pip install aisg
from aisg import AISG
client = AISG(api_key="your_hub_api_key")
response = client.chat.create(
model="oah/grok-4-fast-non-reasoning",
messages=[{"role": "user", "content": "Hello!"}],
)
print(response.content)
print(response.aisg_metadata.pii_detected)
print(response.aisg_metadata.cost_usd)Use any virtual model name from the pricing table above (prefixed with oah/). Also works with the standard OpenAI SDK — just change base_url. Every request is PII-scanned before reaching xAI (Closed Source).
Frequently Asked Questions
What is the Grok API pricing?
Grok API pricing is set by xAI. In Managed Mode, we add a 30% markup. With Pro BYOK, use your own xAI key at 0% markup. See the pricing table above for current per-token rates.
What is the Grok 2 cost?
Grok 2 cost is competitive in the premium model tier. Check the pricing comparison table above for per-token input/output rates.
How do I access the xAI API through AI Security Gateway?
Use the standard OpenAI SDK with model name 'oah/grok-2' and your AISG API key. All requests are PII-scanned before reaching xAI's servers.
How does Grok compare to GPT-4?
Grok 2 is competitive with GPT-4 class models on many benchmarks. It's a strong alternative for teams seeking provider diversification.
Previous Versions
These models have been retired by the provider. Migrate to a current variant above.
grok-3xai
grok-3-minixai
grok-4-0709xai
grok-4-1-fast-non-reasoningxai
grok-4-1-fast-reasoningxai
grok-4-fast-non-reasoningxai
grok-4-fast-reasoningxai
grok-code-fast-1xai
grok-imagine-image-proxai
Deploy Grok with Enterprise-Grade Security
Get started with 1,000,000 free credits. Every Grok request is PII-scanned, cost-optimized, and fully logged — zero configuration.
Not ready yet? Get notified about Grok updates:
Explore Other Model Families
🦙Llama
Meta's open-weights Llama family is the most widely deployed open-source LLM series. Compare Llama API pricing across Gr…
🧠GPT
OpenAI's GPT family powers the majority of commercial AI applications. Compare GPT-4 API cost and OpenAI API pricing acr…
💎Gemini
Google's Gemini family offers powerful multimodal capabilities with large context windows. Compare Gemini API pricing an…
🤖Claude
Anthropic's Claude family is built with safety and reliability at its core. Compare Claude API pricing and Claude Sonnet…
🔍DeepSeek
DeepSeek has rapidly risen as a leading open-source model family, known for exceptional coding performance and cost effi…
Model registry last updated: . Pricing shown is the lowest available rate across providers (per 1M tokens, USD). Actual pricing depends on provider and plan.