Go faster
490.4K tokens$4.47
More tokens, no limits.
Up to 10x more tokens than your Claude or Codex subscription. Never let a subscription limit break your focus and slow you down.
View plansFast open-source models
Fast Inferencefor AI agents
Absurdly fast LLM inference for AI agents. Compatible with Claude, Codex, Cursor, Pi, Hermes, and more. Up to 10x faster than normal.
Go smarter
KIMI-K3-Fast
Opus 5
- SWE7274
- GPQA8183
- tok/s18438
- $/1M0.615
Smart, fast, & affordable.
Fast inference on the top open-source models. Just as smart as Claude and Codex at a fraction of the cost. And did we mention much faster?
View integrationsOne API
open
- kimi-k3-fast
- glm-5.2-fast
- deepseek-v4-fast
closed
- opus-5
- gpt-5.6
- fable-5
All the best models.
One click to switch between the best open-source models and closed-source models like Claude and Codex. Find the right model for you.
Explore modelsCoding agents
Fast inference with any agent.
Route Claude Code, Codex, Grok, OpenCode, Pi, Hermes, OpenClaw, Fx, and Cursor through the Inference.net gateway. One shared key. Native surfaces. Safe reversal.
Claude Code
Native Anthropic /v1/messages. Six model slots for every Claude Code workload.
fast claude onCodex
OpenAI-compatible Responses API with a reversible Codex configuration.
fast codex onGrok
Chat completions with a catalog-backed section for each supported alias.
CLI ADAPTER IN PREVIEWOpenCode
Chat completions with Fast Inference models registered as an OpenCode provider.
fast opencode onPi
Chat completions with model and provider settings written for Pi Agent.
fast pi onHermes
Hermes provider configuration is documented while its CLI adapter is in preview.
CLI ADAPTER IN PREVIEWOpenClaw
OpenClaw provider routing is documented while its CLI adapter is in preview.
CLI ADAPTER IN PREVIEWFx
Fx gateway configuration is documented while its CLI adapter is in preview.
CLI ADAPTER IN PREVIEWCursor
Cursor base URL routing is documented while its CLI adapter is in preview.
CLI ADAPTER IN PREVIEWModels
Fast frontier models.
Kimi, GLM, DeepSeek, Fable, and GPT — routed through Fast Inference. Open the full catalog for every model we serve.
View all modelsModelInputCache readOutput
Loading models
Pricing
Simple, predictable pricing
Operator
$10 monthly allowance$9 / mo
$10 of Gateway credit, renewed each month.
Pay as you go after the credit. Same rates as going direct.
- Claude Code and OpenClaw ready
- Automatic provider failover
- Personal usage meter
- Cancel any time
Studio
$60 monthly allowance$49 / mo
$60 of Gateway credit, renewed each month.
Pay as you go after the credit. Same rates as going direct.
- Everything in Operator
- More monthly Gateway allowance
- Hosted and provider model access
- Cancel any time
Private by default
Your data is
Your data.
Prompts and outputs are never used to train models. Data retention is kept to the minimum needed to operate the service.
01No training
Your data never enters a training set.
02Scoped access
Every key belongs to one project.
03Clear usage
See exactly where tokens and spend go.
04Easy revocation
Disable a credential in one click.
FAQ
Frequently asked questions.
The same endpoint, every model, every provider. No markup. Answers to the questions teams ask before they switch.
faq.sh7 questions
Fast Inference is an OpenAI-compatible API that routes to every model and provider. One key, with no per-request markup.