InferX Endpoints
Access production-ready open models through OpenAI-compatible APIs. InferX manages the infrastructure, scaling, and runtime.
- Start with an API key
- Pay per token
- No infrastructure to manage
Built by the team that solved sub-second cold starts for large language models.View benchmark
Inference infrastructure for production AI.
Run AI models in production without paying for idle GPUs.
True serverless inferenceSub-second cold startsOpenAI-compatible APIs
A request enters the OpenAI-compatible API, the scheduler restores initialized model state, GPU capacity attaches while tokens stream, and resources return to the pool when serving completes.
INFERX RUNTIMEOPENAI-COMPATIBLE API
SNAPSHOT READYRESOURCE LAYERCAPACITY IDLE
Snapshot PoolInitialized model state
GPU PoolGPU slicing enabled0 SLICES
Secure RuntimeIsolated container
Scale to ZeroCapacity released
Compatible with your favorite AI tools
OpenAILangChainOpenCodeHermesOpenClawContinueLlamaIndexVercel AI SDKDify
PROVEN ON PRODUCTION HARDWARE
- MODEL
- Qwen3.6-35B-A3B
- PRECISION
- FP16
- MODEL SIZE
- ~70 GB
- HARDWARE
- NVIDIA H100
TRADITIONAL STARTUPLoad Model Weights≈35s
INFERX STARTUPGPU Snapshot Restore<1s
HOW THE STARTUP PATH CHANGES
TRADITIONAL STARTUP
- Request
- Reserve GPU
- Load model weights
- Initialize runtime
- Serve
- GPU stays allocated
INFERX STARTUP
- Request
- Scheduler
- GPU Snapshot Restore
- Allocate GPU resources
- Serve
- Scale to zero
MONTHLY ACCESS
An easy way to try InferX.
Beta offer: $10/month, includes $50 in usage credits.
MONTHLY ACCESS$20 / month $10 / month
INCLUDED USAGE CREDITS$50 every billing cycle
AFTER INCLUDED CREDITSPay per usage
Production-ready endpoints
Popular models ready now.
Start with hosted endpoints, or deploy more models from the InferX catalog.
Ready now
DeepSeek V4 Flash
FREE TO USE UNTIL AUG 12DeepSeek
- Input
- $0.07 / 1M50% off
- Cached input
- $0.01 / 1M
- Output
- $0.11 / 1M61% off
Cached input supported.
Use endpointReady now
Mimo v2.5
Xiaomi
- Input
- $0.08 / 1M43% off
- Cached input
- $0.008 / 1M
- Output
- $0.18 / 1M36% off
Cached input supported.
Use endpointReady now
GLM 5.2
Zhipu AI
- Input
- $0.18 / 1M87% off
- Cached input
- $0.018 / 1M
- Output
- $1.90 / 1M57% off
Cached input supported.
Use endpointComing soon
Kimi K3
Moonshot AI
Coming soonPricing will be published before availability.
Deployment options
Choose how to build on InferX.
The same runtime. Two deployment models.
Endpoints
ServerlessRun frontier open models instantly.
OpenAI-compatible APIs for production AI workloads with pay-per-token pricing.
- Pay per token
- OpenAI compatible
- Frontier open models
- Streaming responses
- Long context
- Tool calling
Sovereign Endpoints™
DedicatedYour infrastructure. Your performance.
Dedicated inference infrastructure powered by the InferX runtime.
- Dedicated GPUs
- Sub-second cold starts
- Private networking
- Predictable latency
- Kubernetes
- On-prem deployment
InferX Runtime
Inside the InferX Runtime
A model-ready runtime, restored on demand.
A request enters the OpenAI-compatible API, the scheduler restores initialized model state, GPU capacity attaches while tokens stream, and resources return to the pool when serving completes.
INFERX RUNTIMEOPENAI-COMPATIBLE API
SNAPSHOT READYRESOURCE LAYERCAPACITY IDLE
Snapshot PoolInitialized model state
GPU PoolGPU slicing enabled0 SLICES
Secure RuntimeIsolated container
Scale to ZeroCapacity released
- 01Request
- 02Scheduler
- 03GPU Snapshot Restore
- 04Allocate GPU Resources
- 05Stream Tokens
- 06Scale to Zero
- 07Runtime Snapshot Ready
OpenAI compatible
Change one line. Keep your OpenAI code.
Keep the OpenAI Python SDK and request shape. Point your existing client at InferX to serve open models in production.
Verified SDK compatibilityinference.py
PYTHON 3.12
import osfrom openai import OpenAIclient = OpenAI( api_key=os.environ["OPENAI_API_KEY"], base_url="https://model.inferx.net/v1",)stream = client.chat.completions.create( model="Qwen/Qwen3.6-35B-A3B", messages=[{"role": "user", "content": "Hello, InferX."}], stream=True,)for chunk in stream: print(chunk.choices[0].delta.content or "", end="")