Flash: built to finish fast. Everywhere you work.
Flash is an ultra-fast MoE built specifically for rapid task completion. Run it from Claude, Codex, Pi, Hermes, your IDE, or the API. Up to 1200 tok/s *(at 8 concurrency).
Flash task preview
Ready anywhere

One product. Every way you work.
Bring Flash to your harness, IDE, or API workflow and move from prompt to finished task faster.
Run Flash in Claude, Codex, Pi, Hermes, and compatible harnesses.
Use Flash inside the coding environment you already work in.
Call Flash through the OpenAI-compatible API for full control.

From task to done—faster.
One ultra-fast MoE for your harness, your IDE, and your API workflow.
Flash in every workflow
Bring the same Flash product to your harness, your IDE, or a direct OpenAI-compatible API workflow.
Harnesses: Use Flash in Claude, Codex, Pi, Hermes, and other compatible agent harnesses.
IDEs: Put Flash inside the coding environment where your tasks already live.
API: Call Flash directly through the OpenAI-compatible API when you want full control.
/v1/modelsConfirm Flash and its current product capabilities.
/v1/chat/completionsSend a task to Flash and stream the response.
Bearer <key>Built for rapid task completion
Flash is an ultra-fast MoE focused on moving work from prompt to done without workflow friction.
Purpose-built speed: Spend less time waiting and more time completing the next task.
One product everywhere: Switch surfaces without switching the product behind your work.
Privacy-first content handling: Prompt and response content is not intentionally persisted or used for training.
Prompt and response content is not intentionally persisted or used for training.


Bring Flash to your workflow.
Claude, Codex, Pi, Hermes, your IDE, or the API—Flash is ready wherever you start the task.
See Flash inside the way you work
A browser-only look at one fast product across harnesses, IDEs, and API workflows. No data is sent.


One Flash product. Every work surface.
Claude, Codex, Pi, Hermes, your IDE, and the API all lead to the same fast product.
Claude
Put Flash behind Claude when you want rapid task completion without changing how you work.
Codex
Use Flash in Codex to move quickly from instruction to finished coding task.
Pi
Bring Flash into Pi for a fast, focused agent workflow.
Hermes
Run Flash through Hermes for rapid autonomous task execution.
IDE or API
Use Flash in your IDE or call it directly through the OpenAI-compatible API.
Claude
Put Flash behind Claude when you want rapid task completion without changing how you work.
Codex
Use Flash in Codex to move quickly from instruction to finished coding task.
Pi
Bring Flash into Pi for a fast, focused agent workflow.
Hermes
Run Flash through Hermes for rapid autonomous task execution.
IDE or API
Use Flash in your IDE or call it directly through the OpenAI-compatible API.
Claude
Put Flash behind Claude when you want rapid task completion without changing how you work.
Codex
Use Flash in Codex to move quickly from instruction to finished coding task.
Pi
Bring Flash into Pi for a fast, focused agent workflow.
Hermes
Run Flash through Hermes for rapid autonomous task execution.
IDE or API
Use Flash in your IDE or call it directly through the OpenAI-compatible API.
Claude
Put Flash behind Claude when you want rapid task completion without changing how you work.
Codex
Use Flash in Codex to move quickly from instruction to finished coding task.
Pi
Bring Flash into Pi for a fast, focused agent workflow.
Hermes
Run Flash through Hermes for rapid autonomous task execution.
IDE or API
Use Flash in your IDE or call it directly through the OpenAI-compatible API.

Choose how much work Flash can take on
Every plan includes Flash across harnesses, IDEs, and API workflows. Up to 1200 tok/s *(at 8 concurrency).
Premium
Complete focused tasks with Flash.
Features
Privacy-first processing
Prompts and responses are not used for training
Growth
Most popularComplete more work with Flash.
Features
5x usage
Privacy-first processing
Prompts and responses are not used for training
Scale
Highest capacityPut Flash behind demanding workflows.
Features
20x usage
Privacy-first processing
Prompts and responses are not used for training

Flash plans are monthly USD and limited to the approved cohort while Teralor is at capacity. There is no free trial, no coupon, and no postpaid credit. Join the waitlist for access.
Everything you need to know about Flash
Product, speed, compatibility, access, and API answers in one place.
Ready to work with Flash?
Join the waitlist to bring Flash into your workflow.


Flash goes wherever the task starts.
From agent harnesses to your IDE to direct API calls, Flash stays focused on getting the task done fast.
Use Flash through Claude, Codex, Pi, Hermes, any compatible harness, your IDE, or the API. Up to 1200 tok/s *(at 8 concurrency).
Product
Flash speed
Built for
Works in