grok-3
oah/grok-3Deploy grok-3 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
Input: $3.00/MOutput: $15.00/M
Why deploy Grok through OpenSourceAIHub?
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.
Zero Code Changes
Change two lines in your OpenAI SDK — base_url and api_key — and every request flows through the Hub. Full backward compatibility.
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 (14)
grok-3-mini
oah/grok-3-miniDeploy grok-3-mini with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
ReasoningInput: $0.30/MOutput: $0.50/M
grok-4-0709
oah/grok-4Deploy grok-4-0709 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
ReasoningInput: $3.00/MOutput: $15.00/M
grok-4-1-fast-non-reasoning
oah/grok-4-1-fast-non-reasoningDeploy grok-4-1-fast-non-reasoning with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
ReasoningInput: $0.20/MOutput: $0.50/M
grok-4-1-fast-reasoning
oah/grok-4-1-fast-reasoningDeploy grok-4-1-fast-reasoning with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
ReasoningInput: $0.20/MOutput: $0.50/M
grok-4-fast-non-reasoning
oah/grok-4-fast-non-reasoningDeploy grok-4-fast-non-reasoning with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
ReasoningInput: $0.20/MOutput: $0.50/M
grok-4-fast-reasoning
oah/grok-4-fast-reasoningDeploy grok-4-fast-reasoning with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
ReasoningInput: $0.20/MOutput: $0.50/M
grok-4.20-0309-non-reasoning
oah/grok-4.20-0309-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
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: Free/MOutput: Free/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-code-fast-1
oah/grok-code-fast-1Deploy grok-code-fast-1 with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
xAI (Grok)
Input: $0.20/MOutput: $1.50/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-pro
oah/grok-imagine-image-proDeploy grok-imagine-image-pro 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 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-3 oah/grok-3 | — | — | No | $3.00/$15.00 |
grok-3-mini oah/grok-3-mini | — | — | No | $0.30/$0.50 |
grok-4-0709 oah/grok-4 | — | — | No | $3.00/$15.00 |
grok-4-1-fast-non-reasoning oah/grok-4-1-fast-non-reasoning | — | — | No | $0.20/$0.50 |
grok-4-1-fast-reasoning oah/grok-4-1-fast-reasoning | — | — | No | $0.20/$0.50 |
grok-4-fast-non-reasoning oah/grok-4-fast-non-reasoning | — | — | No | $0.20/$0.50 |
grok-4-fast-reasoning oah/grok-4-fast-reasoning | — | — | No | $0.20/$0.50 |
grok-4.20-0309-non-reasoning oah/grok-4.20-0309-non-reasoning | — | — | No | — |
grok-4.20-0309-reasoning oah/grok-4.20-0309-reasoning | — | — | No | — |
grok-4.20-multi-agent-0309 oah/grok-4.20-multi-agent | — | — | No | — |
grok-code-fast-1 oah/grok-code-fast-1 | — | — | No | $0.20/$1.50 |
grok-imagine-image oah/grok-imagine-image | — | — | No | — |
grok-imagine-image-pro oah/grok-imagine-image-pro | — | — | No | — |
grok-imagine-video oah/grok-imagine-video | — | — | No | — |
Grok Direct vs OpenSourceAIHub
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
Integration — 2 Lines
from openai import OpenAI
client = OpenAI(
base_url="https://api.opensourceaihub.ai/v1",
api_key="your_hub_api_key"
)
# Use any virtual model name from the pricing table above
response = client.chat.completions.create(
model="oah/grok-3",
messages=[{"role": "user", "content": "Hello!"}]
)Use any virtual model name from the pricing table above (prefixed with oah/). Works with the standard OpenAI SDK. 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 OpenSourceAIHub?
Use the standard OpenAI SDK with model name 'oah/grok-2' and your Hub 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.
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.