Joel WemboMedium article
Aug 5, 2026
Zero Trust Configuration: The 90-Day Hardening Playbook (Every Config File Included)
Every config file. Every command. Every verification test. No hand-waving.
External articleRead on Medium
The Most Advanced Multi-Cloud Platform
Multi-Cloud Infrastructure
Run by AI Agents
One control plane for AWS, Azure, Google Cloud, Oracle and Alibaba. Provision, deploy and optimise from a single workflow — with AI agents doing the repetitive work.
Agentic AI Automation
Multi-Cloud Management
Zero Downtime
Multi-Cloud — Deploy Anywhere
AWS
Azure
GCP
Oracle
Alibaba
Vultr
Terraform
GitHub8+ Integrations Active
99.99% uptimeReal screens
This is the actual product
Not an illustration. These are screenshots of the running dashboard — the same console you get on the free tier.
vxcloud.io/dashboard?tab=monitoring
Every deployment, one control plane
Live operations across AWS, Azure, GCP, Alibaba and bare metal — status, node, resource, session and provider in a single table, with per-resource detail pages you can link a colleague straight to.
Open this console freeAI-Native DevOps · Zero Downtime · Infinite Scale
Ship Faster with
Autonomous Cloud Ops
AI-driven bots that deploy, monitor, and self-heal your infrastructure around the clock — so your team can focus on building, not firefighting.
Integrations & Open Source Stack
Integrate Seamlessly with the
AI & Cloud Tools You Rely On
Our platform connects natively with leading open-source AI frameworks, cloud providers, and developer tools — no glue code required.
& many more — built on open standards, not vendor lock-in.
120+
Teams Using VxCloud
8,500+
Deployments Automated
30+
Cloud Regions Supported
99.99%
Uptime SLA
Platform Pillars
Multi-cloud deployment & management, Observability, Cost, Security
Deploy across AWS, Azure, Google Cloud, Oracle, Alibaba with unified workflows. Gain deep visibility, optimize cloud spend, and enforce enterprise-grade security and compliance.
Multi-cloud deployment
One pipeline to deploy to AWS, Azure, Google Cloud, Oracle, Alibaba and on-prem. Native IaC and GitOps.
Observability
Integrated logs, metrics, traces with alerting. SLO dashboards out of the box.
Cost optimization
Ownership, showback, and recommendations to reduce spend without sacrificing SLAs.
Security & compliance
Policy-as-code, least privilege by default, SOC 2 / ISO 27001 ready.
Features
Everything you need to build
Infrastructure as Code
Define your stack in Terraform, Pulumi, or our visual builder. Every change is versioned, reviewed, and deployed through automated pipelines.
Multi-Region Deployments
Deploy to 30+ cloud regions across AWS, Azure, Google Cloud, Oracle, and Alibaba with built-in traffic routing, failover, and edge caching for global delivery.
Zero Trust Security
Secrets management, network policy enforcement, RBAC, and automated vulnerability scanning baked into every deployment pipeline.
Solutions
Cloud Solutions
Cloud Computing
Auto-scaling compute across providers — VMs, containers, and serverless with unified cost visibility
Data Infrastructure
Managed databases, streaming pipelines, and data warehouses with automated backups and failover
AI/ML Workloads
GPU provisioning, model serving, and experiment tracking integrated into your deployment pipeline
Infrastructure-as-code, in your language
Built for developers & enterprises — no proprietary DSL.
Provision and deploy vxcloud services with our SDKs (Go · Python · TypeScript), the CLI, or a GitHub Action — a few lines, every cloud.
provision.py live
import vxsdk
c = vxsdk.Client.load_from_vxcli()
# Managed Redis — a few lines, any cloud
db = c.cloud.create_redis(
"my-redis", cloud="aws", region="us-east-1",
node_type="cache.t3.micro",
)
print(db["endpoint"])
$ pip install vxsdk && python provision.py
✓ authenticated → node1.vxcloud.io
✓ redis "my-redis" provisioned · us-east-1
→ my-redis.cache.vxcloud.io:6379
CI/CD Pipelines
Enable CI/CD
on your projects
Use our fully managed CI/CD system to deploy your applications and backend services to your favorite cloud provider — automatically, on every push.
↑
01Push Code✓
02Run Tests⚙
03Build Image🚀
04Deploy LiveWorks with your stack
+ 10 more — Flask · Laravel · Spring Boot · Rust · Java · C++ · PHP · Streamlit · Expo · Static
Pick your framework — VxCloud generates the GitHub Actions workflow and runs the matching vxcli deploy over SSH on every push. No DSL, no Terraform provider.
Live pipeline example
deploy-nextjs.ymlRunning
name: Deploy Next.js to vxcloud
on:
push:
branches: [main]
jobs:
deploy:
runs-on: ubuntu-latest
steps:
- uses: prodxcloud/vxcloud-deploy-action@v1
with:
username: ${{ secrets.VXCLOUD_USERNAME }}
api-key: ${{ secrets.VXCLOUD_API_KEY }}
command: deploy nextjs --app-name web --build-mode production
--host ${{ vars.HOST }} --ssh-user ubuntu --key-pair-name VPS1
$ git push origin main
→ Installing vxcli… ✓ v2026.8.14 (checksum verified)
✓ Authenticated as joelwembo → node1.vxcloud.io
🚀 vxcli deploy nextjs --app-name web --build-mode production
· building .next/ · SSR + standalone output
✓ Deployment initiated — exit_code 0
🌐 Next.js live at https://web.vxcloud.online
Integrations
Works with your favorite tools
GitHub
Connect your repositories and automate deployments
Docker
Deploy containerized applications
Kubernetes
Orchestrate containerized applications
Automate Your DevOps with AI
Describe your infrastructure needs and let AI generate production-ready configurations
VMs
Cloud
Databases
CI/CD
Deploy
GitOps
Latest Writing
Latest from VxCloud & Joel Wembo Technologies
What's happening across cloud, AI, DevOps, product launches, and platform engineering right now.
6 latest storiesExplore all articles
Compare
Multi-Cloud Cost Calculator
Estimate monthly spend across 12 cloud providers side-by-side. List prices, no API calls.
Multi-Cloud Cost Calculator
List prices as of 2026-04 · 12 providers · no API calls
24/7 always-on
Approx. $0.10/GB-month SSD across clouds
Approx. $0.09/GB after free tier
Amazon Web Services
$19.00/mo
no plan
Microsoft Azure
$19.00/mo
no plan
Google Cloud Platform
$19.00/mo
no plan
Public on-demand list prices, Linux, no commitments. GPU prices include host compute. Regional prices shown reflect us-east-1 / eastus / us-central1 or closest equivalent. Hetzner/UpCloud bill in EUR with monthly caps; hourly is approximated at ~1.08 FX. Alibaba prices vary 3-8x by region — values shown are Singapore/SG where available. Confirmed against aws-pricing.com, instances.vantage.sh, cloudprice.net, gcloud-compute.com, computeprices.com, sparecores.com, costgoat.com, getdeploying.com, digitalocean.com/pricing, linode.com/pricing. Always verify against the provider's official calculator before procurement.
Benchmark
AI Model Pricing
Compare input/output token prices, context windows, and benchmark scores across leading AI models.
AI Model Pricing
241 models · 34 creators · list prices per 1M tokens, as of 2026-04 · no API calls
Prefix with / for regex, e.g. /^GPT-5/
$0$150
$0$600
Showing 241 of 241 modelsPrices per 1M tokens · USD
| Model | Creator | Input $ | Output $ | Providers | Context | Max Output | Intelligence | Coding |
|---|---|---|---|---|---|---|---|---|
| GPT-5.5 | OpenAI | 5.00 | 30.00 | 1 | 272K | 128K | 60.2 | 59.1 |
| Claude Opus 4.7 | Anthropic | 5.00 | 25.00 | 7 | 1M | 128K | 57.3 | 52.5 |
| Gemini 3.1 Pro Preview | 2.00 | 12.00 | 4 | 1M | 66K | 57.2 | 55.5 | |
| GPT-5.4 | OpenAI | 2.50 | 15.00 | 5 | 1.1M | 128K | 56.8 | 57.3 |
| Kimi K2.6 | Moonshot AI (Kimi) | 0.745 | 4.00 | 4 | 262K | 66K | 53.9 | 47.1 |
| MiMo V2.5 Pro | Xiaomi | 1.00 | 3.00 | 1 | 1M | 131K | 53.8 | 45.5 |
| GPT-5.3 Codex | OpenAI | 1.75 | 14.00 | 4 | 400K | 128K | 53.6 | 53.1 |
| Qwen3.6 Max Preview | Alibaba | 1.30 | 7.80 | 1 | 240K | 64K | 51.8 | 44.9 |
| GLM-5.1 | Zhipu AI | 1.05 | 3.50 | 3 | 203K | 66K | 51.4 | 43.4 |
| GPT-5.2 | OpenAI | 1.75 | 14.00 | 6 | 410K | 128K | 51.3 | 48.7 |
| Qwen3.6 Plus | Alibaba | 0.325 | 1.95 | 2 | 1M | 66K | 50.0 | 42.9 |
| GLM-5 | Zhipu AI | 0.573 | 2.08 | 9 | 203K | 131K | 49.8 | 44.2 |
| MiniMax M2.7 | MiniMax | 0.300 | 1.20 | 3 | 205K | 131K | 49.6 | 41.9 |
| MiMo V2 Pro | Xiaomi | 1.00 | 3.00 | 2 | 1M | 131K | 49.2 | 41.4 |
| GPT-5.2 Codex | OpenAI | 1.75 | 14.00 | 4 | 400K | 128K | 49.0 | 43.0 |
| GPT-5.4 Mini | OpenAI | 0.750 | 4.50 | 4 | 1.1M | 128K | 48.9 | 51.5 |
| Grok 4.20 | xAI | 2.00 | 6.00 | 3 | 2M | N/A | 48.5 | 40.5 |
| Gemini 3 Pro | 2.00 | 12.00 | 3 | N/A | N/A | 48.4 | 46.5 | |
| GPT-5.1 | OpenAI | 1.25 | 10.00 | 6 | 410K | 128K | 47.7 | 44.7 |
| Kimi K2.5 | Moonshot AI (Kimi) | 0.440 | 2.00 | 11 | 262K | 98K | 46.8 | 39.5 |
| GLM-5 Turbo | Zhipu AI | 1.20 | 4.00 | 2 | 203K | 131K | 46.8 | 36.8 |
| DeepSeek V4 Flash | DeepSeek | 0.140 | 0.280 | 3 | 1M | 384K | 46.5 | 38.7 |
| Claude Opus 4.6 | Anthropic | 5.00 | 25.00 | 7 | 1M | 128K | 46.5 | 47.6 |
| Qwen3.5 397B A17B | Alibaba | 0.390 | 2.34 | 4 | 262K | 66K | 45.0 | 41.3 |
| GPT-5 Codex | OpenAI | 1.25 | 10.00 | 4 | 400K | 128K | 44.6 | 38.9 |
| GPT-5 | OpenAI | 1.25 | 10.00 | 8 | 410K | 128K | 44.6 | 36.0 |
| Claude Sonnet 4.6 | Anthropic | 3.00 | 15.00 | 7 | 1M | 128K | 44.4 | 46.4 |
| GPT-5.4 Nano | OpenAI | 0.200 | 1.25 | 4 | 1.1M | 128K | 44.0 | 43.9 |
| KwaiPilot KAT 2 Pro Coder | KwaiPilot | 0.300 | 1.20 | 2 | 256K | 80K | 43.8 | 45.6 |
| MiMo V2 Omni | Xiaomi | 0.400 | 2.00 | 1 | 262K | 66K | 43.4 | 35.5 |
| GPT-5.1 Codex | OpenAI | 1.25 | 10.00 | 4 | 400K | 128K | 43.1 | 36.6 |
| Claude Opus 4.5 | Anthropic | 5.00 | 25.00 | 9 | 410K | 64K | 43.1 | 42.9 |
| GLM-5V Turbo | Zhipu AI | 1.20 | 4.00 | 2 | 203K | 131K | 42.9 | 36.2 |
| Qwen3.5 27B | Alibaba | 0.195 | 1.56 | 2 | 262K | 66K | 42.1 | 34.9 |
| GLM-4.7 | Zhipu AI | 0.380 | 1.74 | 13 | 205K | 131K | 42.1 | 36.3 |
| MiniMax M2.5 | MiniMax | 0.150 | 1.15 | 7 | 1M | 131K | 41.9 | 37.4 |
| Qwen3.5 122B A10B | Alibaba | 0.260 | 2.08 | 3 | 262K | 66K | 41.6 | 34.7 |
| Grok 4 | xAI | 3.00 | 15.00 | 6 | 256K | N/A | 41.5 | 40.5 |
| GPT-5 Mini | OpenAI | 0.250 | 2.00 | 7 | 400K | 128K | 41.2 | 35.3 |
| Kimi K2 Thinking | Moonshot AI (Kimi) | 0.574 | 1.20 | 13 | 262K | 33K | 40.9 | 34.8 |
| o3 Pro | OpenAI | 20.00 | 80.00 | 4 | 200K | 100K | 40.7 | N/A |
| Qwen3 Max Thinking | Alibaba | 0.780 | 3.90 | 2 | 262K | 66K | 39.9 | 30.5 |
| MiniMax M2.1 | MiniMax | 0.290 | 0.950 | 8 | 1M | 131K | 39.4 | 32.8 |
| Grok 4.1 Reasoning | xAI | 0.200 | 0.500 | 3 | 2M | 30K | 38.6 | 30.9 |
| GPT-5.1 Codex Mini | OpenAI | 0.250 | 2.00 | 4 | 400K | 128K | 38.6 | 36.4 |
| o3 | OpenAI | 2.00 | 8.00 | 5 | 200K | 100K | 38.4 | 38.4 |
| Step 3.5 Flash | StepFun | 0.100 | 0.300 | 1 | 262K | 66K | 37.8 | 31.6 |
| Qwen3.5 35B A3B | Alibaba | 0.163 | 1.30 | 2 | 262K | 66K | 37.1 | 30.3 |
| Claude Sonnet 4.5 | Anthropic | 3.00 | 15.00 | 10 | 1M | 64K | 37.1 | 33.5 |
| MiniMax M2 | MiniMax | 0.255 | 1.00 | 9 | 205K | 131K | 36.1 | 29.2 |
| Nemotron Super 3 120B A12B | NVIDIA | 0.090 | 0.450 | 2 | 262K | 32K | 36.0 | 31.2 |
| KwaiPilot KAT 1 Pro Coder | KwaiPilot | 0.030 | 1.20 | 1 | 256K | 32K | 36.0 | 18.3 |
| Claude Opus 4.1 | Anthropic | 15.00 | 75.00 | 7 | 200K | 32K | 36.0 | N/A |
| Grok 4 Reasoning | xAI | 0.200 | 0.500 | 3 | 2M | 256K | 35.1 | 27.4 |
| Gemini 3 Flash | 0.500 | 3.00 | 3 | 1M | 65K | 35.0 | 37.8 | |
| Claude Sonnet 3.7 | Anthropic | 3.00 | 15.00 | 1 | 200K | 64K | 34.7 | 27.6 |
| Gemini 3.1 Flash Lite Preview | 0.250 | 1.50 | 4 | 1M | 66K | 33.5 | 30.1 | |
| GPT OSS 120B | OpenAI | 0.039 | 0.190 | 20 | 131K | 131K | 33.3 | 28.6 |
| o4 Mini | OpenAI | 1.00 | 4.00 | 6 | 200K | 100K | 33.1 | 25.6 |
| Claude Sonnet 4 | Anthropic | 3.00 | 15.00 | 10 | 1M | 64K | 33.0 | 30.6 |
| Claude Opus 4 | Anthropic | 15.00 | 75.00 | 9 | 410K | 32K | 33.0 | N/A |
| Mercury 2 | Inception | 0.250 | 0.750 | 2 | 128K | 50K | 32.8 | 30.6 |
| Qwen3.5 9B | Alibaba | 0.100 | 0.150 | 2 | 262K | N/A | 32.4 | 25.3 |
| DeepSeek V3.2 | DeepSeek | 0.252 | 0.378 | 12 | 164K | 66K | 32.1 | 34.6 |
| Arcee Trinity Large Thinking | Arcee AI | 0.220 | 0.850 | 2 | 262K | 80K | 31.9 | 27.2 |
| Qwen3 Max | Alibaba | 0.359 | 1.43 | 4 | 262K | 66K | 31.4 | 26.4 |
| Claude Haiku 4.5 | Anthropic | 1.00 | 5.00 | 9 | 200K | 64K | 31.1 | 29.6 |
| o1 | OpenAI | 15.00 | 60.00 | 5 | 200K | 100K | 30.8 | 20.5 |
| Claude Sonnet 3.7 (200K) | Anthropic | 3.00 | 15.00 | 10 | 200K | 128K | 30.8 | 26.7 |
| MiMo V2 Flash | Xiaomi | 0.090 | 0.290 | 4 | 262K | 66K | 30.4 | 25.8 |
| GLM-4.6 | Zhipu AI | 0.390 | 1.90 | 10 | 205K | 131K | 30.2 | 30.2 |
| GLM-4.7 Flash | Zhipu AI | 0.060 | 0.400 | 3 | 203K | 131K | 30.1 | 25.9 |
| Gemini 2.5 Pro | 1.25 | 10.00 | 7 | 1M | 66K | 29.5 | 31.9 | |
| DeepSeek V3.2 Speciale | DeepSeek | 0.400 | 1.20 | 2 | 164K | N/A | 29.4 | 37.9 |
| Grok 4.20 Non-Reasoning | xAI | 2.00 | 6.00 | 2 | 2M | N/A | 29.0 | 22.0 |
| Grok 1 Code Fast | xAI | 0.200 | 1.50 | 4 | 256K | 10K | 28.7 | 23.7 |
| DeepSeek V3.1 Terminus | DeepSeek | 0.210 | 0.790 | 6 | 164K | 66K | 28.5 | 31.9 |
| Qwen3 Coder Next | Alibaba | 0.150 | 0.800 | 5 | 262K | 66K | 28.3 | 22.9 |
| DeepSeek V3.1 | DeepSeek | 0.135 | 0.500 | 14 | 164K | 66K | 28.1 | 28.4 |
| GPT-5 Nano | OpenAI | 0.050 | 0.400 | 7 | 400K | 128K | 26.8 | 20.3 |
| GLM-4.5 | Zhipu AI | 0.400 | 1.60 | 8 | 131K | 98K | 26.4 | 26.3 |
| Kimi K2 | Moonshot AI (Kimi) | 0.400 | 2.00 | 4 | 262K | 128K | 26.3 | 22.1 |
| GPT-4.1 | OpenAI | 2.00 | 8.00 | 6 | 1M | 33K | 26.3 | 21.8 |
| Qwen3 Max Preview | Alibaba | 1.20 | 6.00 | 2 | 262K | 66K | 26.1 | 25.5 |
| Solar Pro 3 | Upstage | 0.150 | 0.600 | 1 | 128K | N/A | 25.9 | 13.3 |
| o3 Mini | OpenAI | 1.10 | 4.40 | 5 | 200K | 100K | 25.9 | 17.9 |
| o1 Pro | OpenAI | 150.00 | 600.00 | 3 | 200K | 100K | 25.8 | N/A |
| Gemini 2.5 Flash Preview | 0.300 | 2.50 | 2 | 1M | 66K | 25.7 | 22.1 | |
| o3 Mini High | OpenAI | 1.10 | 4.40 | 1 | 200K | 100K | 25.2 | 17.3 |
| Grok 3 | xAI | 3.00 | 15.00 | 5 | 131K | N/A | 25.2 | 19.8 |
| Qwen3 Coder 480B A35B Instruct | Alibaba | 0.220 | 1.30 | 8 | 262K | 66K | 24.8 | 24.6 |
| Sonar Reasoning Pro | Perplexity | 2.00 | 8.00 | 3 | 128K | 8K | 24.6 | N/A |
| GPT OSS 20B | OpenAI | 0.030 | 0.140 | 16 | 131K | 131K | 24.5 | 18.5 |
| MiniMax M1 80k | MiniMax | 0.100 | 0.100 | 3 | 1M | 40K | 24.4 | 14.5 |
| o1 Preview | OpenAI | 15.00 | 60.00 | 2 | 128K | 33K | 23.7 | 34.0 |
| Grok 4.1 Fast | xAI | 0.200 | 0.500 | 3 | 2M | 30K | 23.6 | 19.5 |
| GLM-4.5 Air | Zhipu AI | 0.130 | 0.850 | 6 | 131K | 98K | 23.2 | 23.8 |
| Grok 4 Fast | xAI | 0.200 | 0.500 | 4 | 2M | 30K | 23.1 | 19.0 |
| GPT-4.1 Mini | OpenAI | 0.400 | 1.60 | 5 | 1M | 33K | 22.9 | 18.5 |
| Mistral Large 3 | Mistral AI | 0.500 | 1.20 | 4 | 262K | 8K | 22.8 | 22.7 |
| DeepSeek V3 324 | DeepSeek | 0.200 | 0.400 | 12 | 164K | 16K | 22.3 | 22.0 |
| INTELLECT-3 | Prime Intellect | 0.200 | 1.10 | 2 | 131K | N/A | 22.2 | 19.1 |
| Devstral 2 | Mistral AI | 0.400 | 2.00 | 1 | 256K | N/A | 22.0 | 23.7 |
| Mistral Medium 3.1 | Mistral AI | 0.400 | 2.00 | 2 | 131K | N/A | 21.3 | 18.3 |
| Qwen3 VL 235B A22B Instruct | Alibaba | 0.200 | 0.880 | 6 | 262K | 33K | 20.8 | 16.5 |
| o1 Mini | OpenAI | 1.10 | 4.40 | 3 | 128K | 66K | 20.4 | N/A |
| Qwen3 Next 80B A3B Instruct | Alibaba | 0.090 | 0.900 | 10 | 262K | 66K | 20.1 | 15.3 |
| Qwen3 Coder 30B A3B Instruct | Alibaba | 0.070 | 0.260 | 5 | 262K | 66K | 20.0 | 19.4 |
| GPT-4.5 | OpenAI | 75.00 | 150.00 | 1 | N/A | N/A | 20.0 | N/A |
| QwQ 32B | Alibaba | 0.150 | 0.200 | 9 | 131K | 16K | 19.7 | N/A |
| Devstral Small 2 | Mistral AI | 0.100 | 0.300 | 1 | 256K | N/A | 19.5 | 20.7 |
| Gemini 2.5 Flash Lite Preview | 0.100 | 0.400 | 3 | 1M | 66K | 19.4 | 14.5 | |
| Nova Premier | Amazon | 2.50 | 12.50 | 3 | 1M | 32K | 19.0 | 13.8 |
| Mistral Medium 3 | Mistral AI | 0.400 | 2.00 | 2 | 131K | 8K | 18.8 | 13.6 |
| Magistral Medium | Mistral AI | 2.00 | 5.00 | 2 | 128K | 64K | 18.8 | 16.0 |
| DeepSeek R1 | DeepSeek | 0.280 | 0.400 | 15 | 164K | 66K | 18.8 | 15.9 |
| Devstral Medium | Mistral AI | 0.400 | 2.00 | 2 | 256K | N/A | 18.7 | 15.9 |
| Claude Haiku 3.5 | Anthropic | 0.800 | 4.00 | 7 | 200K | 8K | 18.7 | 10.7 |
| Gemini 2.0 Flash | 0.100 | 0.400 | 5 | 1M | 8K | 18.5 | 13.6 | |
| Llama 4 Maverick | Meta | 0.150 | 0.600 | 6 | 1M | 16K | 18.4 | 15.6 |
| Nova 2 Lite | Amazon | 0.300 | 2.50 | 3 | 1M | 66K | 18.0 | 12.5 |
| Claude Opus 3 | Anthropic | 15.00 | 75.00 | 5 | 200K | 4K | 18.0 | 19.5 |
| Sonar Reasoning | Perplexity | 1.00 | 5.00 | 2 | 128K | 8K | 17.9 | N/A |
| Gemini 2.5 Flash | 0.150 | 0.600 | 9 | 1M | 66K | 17.8 | 17.8 | |
| Llama 3.1 405B Instruct | Meta | 0.120 | 0.300 | 11 | 131K | 16K | 17.4 | 14.5 |
| Qwen3 VL 32B Instruct | Alibaba | 0.104 | 0.416 | 3 | 131K | 33K | 17.2 | 15.6 |
| DeepSeek R1 Distill Qwen 32B | DeepSeek | 0.150 | 0.150 | 7 | 131K | 32K | 17.2 | N/A |
| GLM-4.6V | Zhipu AI | 0.300 | 0.900 | 4 | 131K | 33K | 17.1 | 11.1 |
| Qwen3 235B A22B Instruct | Alibaba | 0.090 | 0.580 | 9 | 262K | 33K | 17.0 | 14.0 |
| Magistral Small | Mistral AI | 0.500 | 1.50 | 3 | 128K | 64K | 16.8 | 11.1 |
| DeepSeek V3 | DeepSeek | 0.200 | 0.200 | 12 | 164K | 82K | 16.5 | 16.4 |
| Qwen3 VL 30B A3B Instruct | Alibaba | 0.130 | 0.520 | 5 | 262K | 33K | 16.1 | 14.3 |
| Ministral 3 14B | Mistral AI | 0.200 | 0.200 | 1 | 262K | N/A | 16.0 | 10.9 |
| DeepSeek R1 Distill Llama 70B | DeepSeek | 0.200 | 0.375 | 11 | 131K | 16K | 16.0 | 11.4 |
| DeepSeek R1 Distill Qwen 14B | DeepSeek | 0.070 | 0.070 | 4 | 131K | 16K | 15.8 | N/A |
| Qwen2.5 72B Instruct | Alibaba | 0.120 | 0.300 | 8 | 131K | 16K | 15.6 | 11.9 |
| Sonar | Perplexity | 1.00 | 1.00 | 3 | 128K | 8K | 15.5 | N/A |
| Sonar Pro | Perplexity | 3.00 | 15.00 | 3 | 200K | 8K | 15.2 | N/A |
| QwQ 32B Preview | Alibaba | 0.287 | 0.861 | 2 | 33K | 16K | 15.2 | N/A |
| Devstral Small | Mistral AI | 0.100 | 0.300 | 4 | 256K | 64K | 15.2 | 12.1 |
| Mistral Small 3.2 | Mistral AI | 0.060 | 0.180 | 1 | 131K | N/A | 15.1 | 13.3 |
| Mistral Large 2 | Mistral AI | 2.00 | 6.00 | 1 | 128K | 8K | 15.1 | 13.8 |
| Qwen3 30B A3B | Alibaba | 0.080 | 0.280 | 7 | 131K | 20K | 15.0 | 14.2 |
| ERNIE 4.5 300B A47B | Baidu | 0.280 | 1.10 | 1 | 123K | 12K | 15.0 | 14.5 |
| Ministral 3 8B | Mistral AI | 0.150 | 0.150 | 1 | 262K | N/A | 14.8 | 10.0 |
| Gemini 2.0 Flash Lite | 0.075 | 0.300 | 4 | 1M | 8K | 14.7 | N/A | |
| Llama 3.3 70B Instruct | Meta | 0.100 | 0.200 | 19 | 131K | 120K | 14.5 | 10.7 |
| GPT-4o | OpenAI | 2.50 | 10.00 | 6 | 131K | 16K | 14.5 | 16.6 |
| Qwen3 VL 8B Instruct | Alibaba | 0.080 | 0.200 | 5 | 131K | 33K | 14.3 | 7.3 |
| Claude Sonnet 3.5 | Anthropic | 3.00 | 15.00 | 6 | 1M | 8K | 14.2 | 26.0 |
| Pixtral Large (25.02) | Mistral AI | 2.00 | 6.00 | 5 | 131K | 4K | 14.0 | N/A |
| Grok 2 | xAI | 2.00 | 10.00 | 2 | 131K | 4K | 13.9 | N/A |
| GPT-4 Turbo | OpenAI | 10.00 | 30.00 | 4 | 128K | 4K | 13.7 | 21.5 |
| Nova Pro | Amazon | 0.800 | 3.20 | 4 | 300K | 10K | 13.5 | 11.0 |
| Llama 4 Scout | Meta | 0.080 | 0.300 | 5 | 328K | 16K | 13.5 | 6.7 |
| Command A | Cohere | 1.56 | 1.56 | 5 | 256K | 8K | 13.5 | 9.9 |
| Llama 3.1 Nemotron 70B Instruct | NVIDIA | 0.600 | 0.600 | 3 | 131K | 16K | 13.4 | 10.8 |
| Grok Beta | xAI | 5.00 | 15.00 | 1 | 131K | N/A | 13.3 | N/A |
| Qwen2.5 32B Instruct | Alibaba | 0.060 | 0.200 | 3 | 131K | 8K | 13.2 | N/A |
| Nemotron Nano 3 30B A3B | NVIDIA | 0.050 | 0.200 | 2 | 262K | N/A | 13.2 | 15.8 |
| Nemotron Nano 2 9B | NVIDIA | 0.040 | 0.160 | 5 | 131K | 8K | 13.2 | 7.5 |
| GPT-4.1 Nano | OpenAI | 0.100 | 0.400 | 5 | 1M | 33K | 13.0 | 11.2 |
| Qwen2.5 Coder 32B Instruct | Alibaba | 0.050 | 0.100 | 8 | 131K | 8K | 12.9 | N/A |
| GPT-4 | OpenAI | 30.00 | 60.00 | 3 | 33K | 8K | 12.8 | 13.1 |
| Nova Lite | Amazon | 0.060 | 0.240 | 4 | 300K | 10K | 12.7 | 5.1 |
| GLM-4.5V | Zhipu AI | 0.600 | 1.20 | 6 | 131K | 32K | 12.7 | 10.8 |
| Gemini 2.5 Flash Lite | 0.075 | 0.300 | 6 | 1M | 66K | 12.7 | 7.4 | |
| GPT-4o mini | OpenAI | 0.150 | 0.600 | 6 | 131K | 16K | 12.6 | N/A |
| Qwen3 4B Instruct | Alibaba | 0.010 | 0.030 | 2 | 262K | 33K | 12.5 | 9.1 |
| Qwen3 30B A3B Instruct | Alibaba | 0.090 | 0.300 | 3 | 262K | 33K | 12.5 | 13.3 |
| Llama 3.1 70B Instruct | Meta | 0.100 | 0.100 | 13 | 131K | 8K | 12.5 | 10.9 |
| DeepSeek V2.5 | DeepSeek | 1.20 | 1.20 | 1 | 33K | N/A | 12.5 | N/A |
| Claude Haiku 3 | Anthropic | 0.250 | 1.25 | 5 | 200K | 4K | 12.3 | 6.7 |
| OLMo 3.1 32B Instruct | Allen AI | 0.200 | 0.600 | 1 | 66K | N/A | 12.2 | 5.6 |
| OLMo 3 32B Think | Allen AI | 0.150 | 0.500 | 1 | 66K | 4K | 12.1 | 10.5 |
| Mistral Saba | Mistral AI | 0.200 | 0.600 | 1 | 33K | N/A | 12.1 | N/A |
| DeepSeek R1 Distill Llama 8B | DeepSeek | 0.025 | 0.025 | 3 | 131K | N/A | 12.1 | N/A |
| Reka Flash | Reka AI | 0.900 | 0.900 | 1 | 100K | 8K | 12.0 | N/A |
| Qwen Turbo | Alibaba | 0.033 | 0.130 | 2 | 1M | 16K | 12.0 | N/A |
| Gemini 1.5 Pro | 1.25 | 5.00 | 2 | N/A | N/A | 12.0 | 19.8 | |
| Llama 3.1 8B Instruct | Meta | 0.020 | 0.030 | 19 | 200K | 128K | 11.8 | 4.9 |
| Qwen2 72B Instruct | Alibaba | 0.900 | 0.900 | 1 | 33K | N/A | 11.7 | N/A |
| Ministral 3 3B | Mistral AI | 0.100 | 0.100 | 1 | 131K | N/A | 11.2 | 4.8 |
| Gemini 1.5 Flash 8B | 0.037 | 0.300 | 2 | N/A | N/A | 11.1 | N/A | |
| Jamba 1.7 Large | AI21 Labs | 2.00 | 8.00 | 2 | 256K | 4K | 10.9 | 7.8 |
| Granite 4 Small H | IBM | 0.060 | 0.250 | 1 | 20K | N/A | 10.8 | 8.5 |
| Qwen3 Omni 30B A3B Instruct | Alibaba | 0.250 | 0.970 | 1 | 66K | 16K | 10.7 | 7.2 |
| Jamba 1.5 Large | AI21 Labs | 2.00 | 2.80 | 4 | 256K | 8K | 10.7 | N/A |
| Jamba 1.6 Large | AI21 Labs | 2.00 | 8.00 | 1 | 256K | N/A | 10.6 | N/A |
| Hermes 3 Llama 3.1 70B | Nous Research | 0.120 | 0.300 | 3 | 131K | N/A | 10.6 | N/A |
| LFM 2 24B A2B | Liquid AI | 0.030 | 0.120 | 1 | 33K | N/A | 10.5 | 3.6 |
| Gemini 1.5 Flash | 0.075 | 0.300 | 2 | 8K | N/A | 10.5 | N/A | |
| Phi-4 | Microsoft | 0.065 | 0.140 | 3 | 16K | 16K | 10.4 | 11.2 |
| Nova Micro | Amazon | 0.035 | 0.140 | 4 | 128K | 10K | 10.3 | 4.1 |
| Claude Sonnet 3 | Anthropic | 3.00 | 15.00 | 2 | 200K | 4K | 10.3 | N/A |
| Nemotron Nano 2 12B VL | NVIDIA | 0.100 | 0.100 | 3 | 131K | 4K | 10.1 | 5.9 |
| Qwen2.5 Coder 7B Instruct | Alibaba | 0.010 | 0.030 | 4 | 131K | 8K | 10.0 | N/A |
| Mistral Large | Mistral AI | 0.500 | 1.50 | 8 | 262K | 16K | 9.9 | N/A |
| Mixtral 8x22B Instruct | Mistral AI | 0.600 | 0.600 | 6 | 66K | 2K | 9.8 | N/A |
| Llama 3.2 3B Instruct | Meta | 0.015 | 0.020 | 9 | 131K | 32K | 9.7 | N/A |
| Llama 2 7B Chat | Meta | 0.050 | 0.150 | 4 | 4K | 4K | 9.7 | N/A |
| Reka Flash 3 | Reka AI | 0.100 | 0.200 | 1 | 66K | N/A | 9.5 | 8.9 |
| DeepSeek R1 Distill Qwen 1.5B | DeepSeek | 0.090 | 0.090 | 3 | 131K | N/A | 9.1 | N/A |
| Claude 2 | Anthropic | 8.00 | 24.00 | 1 | 100K | 8K | 9.1 | 12.9 |
| Mistral Small | Mistral AI | 0.060 | 0.180 | 7 | 262K | 8K | 9.0 | N/A |
| Mistral Medium | Mistral AI | 0.400 | 2.00 | 4 | 131K | 64K | 9.0 | N/A |
| GPT-3.5 Turbo | OpenAI | 0.500 | 1.50 | 4 | 16K | 4K | 9.0 | 10.7 |
| Llama 3 70B Instruct | Meta | 0.120 | 0.300 | 9 | 131K | 8K | 8.9 | 6.8 |
| LFM 40B | Liquid AI | 0.100 | 0.200 | 1 | 131K | N/A | 8.8 | N/A |
| Gemma 3 12B | 0.150 | 0.500 | 1 | 128K | 32K | 8.8 | 6.3 | |
| Gemini 1.0 Pro | 0.500 | 1.50 | 2 | N/A | N/A | 8.5 | N/A | |
| Phi-4 Mini | Microsoft | N/A | N/A | 1 | N/A | N/A | 8.4 | 3.6 |
| Llama 2 70B Chat | Meta | 0.500 | 0.900 | 7 | 4K | 4K | 8.4 | N/A |
| Llama 2 13B Chat | Meta | 0.100 | 0.200 | 4 | 4K | 4K | 8.4 | N/A |
| Command R+ | Cohere | 1.56 | 1.56 | 6 | 128K | 4K | 8.3 | N/A |
| Jamba 1.7 Mini | AI21 Labs | 0.200 | 0.400 | 1 | 256K | N/A | 8.1 | 3.1 |
| Jamba 1.5 Mini | AI21 Labs | 0.200 | 0.200 | 4 | 256K | 8K | 8.0 | N/A |
| Jamba 1.6 Mini | AI21 Labs | 0.200 | 0.400 | 1 | 256K | N/A | 7.9 | N/A |
| Mixtral 8x7B Instruct | Mistral AI | 0.070 | 0.150 | 10 | 33K | 16K | 7.7 | N/A |
| Mistral 7B Instruct | Mistral AI | 0.010 | 0.100 | 9 | 127K | 16K | 7.4 | N/A |
| Command R | Cohere | 0.150 | 0.150 | 5 | 128K | 4K | 7.4 | N/A |
| Granite 3.3 8B Instruct | IBM | 0.030 | 0.200 | 2 | 8K | 8K | 7.0 | 3.4 |
| Llama 3 8B Instruct | Meta | 0.030 | 0.040 | 9 | 32K | 8K | 6.4 | 4.0 |
| Llama 3.2 1B Instruct | Meta | 0.027 | 0.080 | 5 | 128K | 16K | 6.3 | 0.6 |
| Gemma 3 4B | 0.030 | 0.080 | 1 | 128K | 8K | 6.3 | 2.9 | |
| Ada | OpenAI | 0.100 | N/A | 1 | 8K | N/A | N/A | N/A |
| Aion 1 | Aion Labs | 4.00 | 8.00 | 1 | 131K | 33K | N/A | N/A |
| Aion 1 Mini | Aion Labs | 0.700 | 1.40 | 1 | 131K | 33K | N/A | N/A |
| Aion 2 | Aion Labs | 0.800 | 1.60 | 1 | 131K | 33K | N/A | N/A |
| Aion Llama 3.1 RP 8B | Aion Labs | 0.800 | 1.60 | 1 | 33K | N/A | N/A | N/A |
| Allam 1 13B Instruct | SDAIA | 1.80 | 1.80 | 1 | 8K | 8K | N/A | N/A |
| Apply 3 | Relace | 0.850 | 1.25 | 1 | 256K | 128K | N/A | N/A |
| Arcee Coder Large | Arcee AI | 0.500 | 0.800 | 1 | 33K | N/A | N/A | N/A |
| Arcee Maestro Reasoning | Arcee AI | 0.900 | 3.30 | 1 | 131K | 32K | N/A | N/A |
| Arcee Spotlight | Arcee AI | 0.180 | 0.180 | 1 | 131K | 66K | N/A | N/A |
| Arcee Trinity Large Preview | Arcee AI | 0.150 | 0.450 | 2 | 131K | N/A | N/A | N/A |
| Arcee Trinity Mini | Arcee AI | 0.045 | 0.150 | 2 | 131K | N/A | N/A | N/A |
| Arcee Virtuoso Large | Arcee AI | 0.750 | 1.20 | 1 | 131K | 64K | N/A | N/A |
| Arctic | Snowflake | 1.68 | 1.68 | 1 | 4K | N/A | N/A | N/A |
| Arctic 1.5 Embed M | Snowflake | 0.060 | 0.060 | 1 | N/A | N/A | N/A | N/A |
| Arctic 2 Embed L | Snowflake | 0.100 | 0.100 | 1 | N/A | N/A | N/A | N/A |
Public list prices per 1M tokens (input/output) for LLM API inference. Intelligence & Coding scores reflect public benchmarks; higher is better. 'providers' is the count of inference providers offering the model. Prices vary over time and by region/tier — verify against the provider's pricing page before procurement.
Watch
Platform demos & industry talks
Learn how teams ship faster on multi-cloud and build robust observability practices.
Explore VxCloud for enterprises →
Trusted by leading companies worldwide
Built for AI-scale infrastructure
Power demanding AI workloads with confidence
What our customers say
A
Alex Kimura
Platform Engineer at NovaBridge
"VxCloud completely streamlined our release workflow. We went from manual weekend deployments to fully automated pipelines shipping multiple times a day."
R
Rachel Okonkwo
CTO at Luminary Labs
"The managed infrastructure on VxCloud just works. We scaled from a small prototype to handling millions of requests without ever worrying about uptime."
J
James Petrov
Head of Security at Crestfield IO
"Security was non-negotiable for us. VxCloud gave us enterprise-grade compliance controls out of the box, so our team could focus on building instead of auditing."