ZMIME
Cognition · Released Nov 4, 2026

SWE-2 Flash

Coding agent model developed from Inkling-Small, with mid-training on scientific and software engineering data.

  • New
  • Proprietary
Capability
—No ECI score yet
Input
—No listed price
Output
—No listed price
Context
—tokens
Pricing

What it costs

No per-token price is published for this model yet.

No per-token price is listed for this model on models.dev.

Capability

Independent benchmarks

Epoch AI has not published a Capabilities Index score for SWE-2 Flash yet.

Specifications

The details

Lab
Cognition
Task
Software engineering
Published capabilities
Coding agent model developed from Inkling-Small, with mid-training on scientific and software engineering data.
Access
Devin Desktop and CLI
Released
Nov 4, 2026
Context window
— tokens
Inputs
Text
Output
Text
Reasoning
Unconfirmed
Tool calling
Unconfirmed
Structured output
Unconfirmed
Weights
Proprietary

Cognition model documentation

Questions

About SWE-2 Flash

How much does SWE-2 Flash cost?

SWE-2 Flash has no published per-token API price on models.dev yet.

How good is SWE-2 Flash?

Epoch AI has not published a Capabilities Index score for SWE-2 Flash yet.

Is SWE-2 Flash open source?

No. SWE-2 Flash is proprietary; you use it through an API or partner platforms.

What inputs does SWE-2 Flash support?

SWE-2 Flash accepts text. Coding agent model developed from Inkling-Small, with mid-training on scientific and software engineering data.

When was SWE-2 Flash released?

Cognition released SWE-2 Flash on Nov 4, 2026.

What are the best alternatives to SWE-2 Flash?

The closest current models from other labs on capability, price and release date are Hy4 (Tencent, $0.834 / $2.50), Ripple-65B Preview (Ricursive Intelligence), GPT-6 Cyber (OpenAI) and ERNIE 5.5 Flash Base (Baidu).