Mixtral 8x7B
oah/mixtral-8x7bDeploy Mixtral 8x7B with built-in PII redaction and Hub governance. 8x7B parameters. Available on Managed Credits and BYOK.
GroqTogether.aiDeepInfraMistral AI
Input: $0.20/MOutput: $0.20/M
Why deploy Mistral through AI Security Gateway?
Automatic PII Redaction
Every Mistral request is scanned for 28+ PII entity types — SSNs, credit cards, emails, API keys, and more — before it reaches any provider.
Smart Cost Routing
Mistral is available across 4 providers. Our Smart Router picks the cheapest one per-request. 25% 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 AISG. Full backward compatibility.
Full Observability
Per-request logging of token counts, latency, DLP violations, and cost. Never wonder what your AI spend is again.
Mistral Strengths
- Mixtral MoE: high capability at lower compute cost
- Strong multilingual support (European languages)
- Open-weights variants available for self-hosting
- Codestral: purpose-built for code generation
- Efficient inference even on smaller variants
Available Mistral Models (5)
Mistral Large
oah/mistral-largeDeploy Mistral Large with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Mistral AI
Input: $0.50/MOutput: $1.50/M
Mistral Small
oah/mistral-smallDeploy Mistral Small with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Mistral AI
Input: $0.10/MOutput: $0.30/M
Mistral Medium
oah/mistral-mediumDeploy Mistral Medium with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Mistral AI
Input: $0.40/MOutput: $2.00/M
Codestral
oah/codestralDeploy Codestral with built-in PII redaction and Hub governance. Available on Managed Credits and BYOK.
Mistral AI
Input: $0.30/MOutput: $0.90/M
Mistral Pricing Comparison (per 1M tokens, USD)
Input / Output pricing by provider. Managed Mode adds a 25% managed markup. Pro BYOK = 0% markup.
| Model | Params | Context | Vision | Groq | Together.ai | DeepInfra | Mistral AI |
|---|---|---|---|---|---|---|---|
Mixtral 8x7B oah/mixtral-8x7b | 8x7B | — | No | $0.24/$0.24 | $0.60/$0.60 | $0.20/$0.20 | $0.70/$0.70 |
Mistral Large oah/mistral-large | — | — | No | — | — | — | $0.50/$1.50 |
Mistral Small oah/mistral-small | — | — | No | — | — | — | $0.10/$0.30 |
Mistral Medium oah/mistral-medium | — | — | No | — | — | — | $0.40/$2.00 |
Codestral oah/codestral | — | — | No | — | — | — | $0.30/$0.90 |
Mistral 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 Mistral AI | Provider pricing only | None | None | Manual | None |
| Hub — Managed Mode | Provider + 25% 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
Multilingual customer support (especially European languages)
2
Code generation with Codestral
3
Budget-conscious deployments requiring good multilingual performance
4
MoE deployments for cost/quality tradeoffs
Integration — 2 Lines
from openai import OpenAI
client = OpenAI(
base_url="https://api.aisecuritygateway.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/mixtral-8x7b",
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 Mistral AI (Open / Closed).
Frequently Asked Questions
What is the Mistral API pricing?
Mistral API pricing varies by model and provider. In Managed Mode, we add a 25% markup. With Pro BYOK, pay the provider directly at 0% markup. Check the pricing table above for current rates.
What is the Mixtral cost?
Mixtral cost depends on the provider (Groq, Together.ai, etc.). As a MoE model, it offers strong performance at lower cost than dense models of equivalent quality. See the pricing comparison above.
Mistral vs Llama — which should I use?
Mistral excels at European multilingual tasks and offers Codestral for coding. Llama has wider provider availability and larger model variants. Both run through AISG with identical PII protection and budget enforcement.
Which Mistral model is best for coding?
Codestral is Mistral's dedicated coding model and excels at code generation, completion, and explanation tasks.
Is Mixtral open-source?
Mixtral's open-weights variants are available under permissive licenses. Some newer Mistral models (like Mistral Large) are closed-source.
Deploy Mistral with Enterprise-Grade Security
Get started with 1,000,000 free credits. Every Mistral request is PII-scanned, cost-optimized, and fully logged — zero configuration.
Not ready yet? Get notified about Mistral 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: 2026-04-18T17:41:46.389Z. Pricing shown is the lowest available rate across providers (per 1M tokens, USD). Actual pricing depends on provider and plan.