# SWE-2 Flash (slim)

> SWE-2 Flash is Cognition's small, fast coding model, mid-trained and reinforcement-trained from Thinking Machines' Inkling-Small (276B total, 12B active parameters). It runs inside Devin Desktop and Devin CLI, with no model API of its own and no public weights.

- Full: https://www.anchorterminal.com/tools/swe-2-flash.md (~9,600 tokens) · this version ~1,830 tokens · JSON https://www.anchorterminal.com/tools/swe-2-flash.json · canonical https://www.anchorterminal.com/tools/swe-2-flash
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-04 · pricing https://www.anchorterminal.com/tools/swe-2-flash#pricing · reviews https://www.anchorterminal.com/tools/swe-2-flash#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**F · 36.4/100 · rank #1243 of 1350 · #33 in Model APIs & inference · not agent-ready · confidence low**


Assessment: A new small coding model from Cognition that anyone can try free in Devin Desktop and Devin CLI until 30 November 2026, with strong vendor-reported coding scores. It has no model API, no published per-token price, context length or model card, and no public weights, so an agent can reach it only by driving Devin's own CLI.

## Facts

- Kind: Model API · vendor: Cognition AI, Inc. · category: Model APIs & inference · legal entity: Cognition AI, Inc. · provenance 72/100
- Auth: OAuth or key · pricing: Freemium · x402: no · licence: Proprietary model, used through Devin Desktop and Devin CLI under Cognition's Platform Terms of Service. The weights are not public; Cognition says it is building a programme to share them with industry partners and researchers
- Probe metrics: not measured yet (probes haven't run)
- Surface graded: The model as Devin Desktop and Devin CLI expose it, read from the launch post, the Devin docs, the pricing page, Cognition's legal pages and the status page on 4 November 2026. No account was made and nothing was run. There is no model API to grade. Devin itself is the separate devin listing
- Model: Mixture of experts, 276B total and 12B active parameters, the size of its base model, Inkling-Small from Thinking Machines Lab (the inkling-small listing). Cognition added a mid-training stage of a few trillion tokens of scientific articles, blogs, code and other sources in three stages, then large-scale reinforcement learning. Context length, output limit, modalities and reasoning levels aren't stated
- Where it runs: Devin Desktop and Devin CLI, per the launch post. Not in the Devin v3 API, whose session agents are `swe-2-medium`, `swe-2-high` and `swe-2-max`, and not yet named on the Devin Desktop or CLI models pages, which list SWE-2, SWE-1.7, SWE-1.7 Lightning, SWE-1.6 and SWE-1.6 Fast
- Weights: Not public. Cognition says it wants enterprises, governments and researchers to be able to host, fine-tune and study the model, but is holding the weights back because the cyber training that raised ExploitBench to 34.8 per cent could also help attackers. It is building a programme to share them with trusted industry partners and research labs, with more 'in a few weeks'
- Cognition's figures: Vendor-reported. Terminal-Bench 4.0 20.0, DeepSWE 1.1 60.1, FrontierCode 2.0 24.0, FrontierCode 1.1 Main 45.5, Terminal-Bench 2.1 89.2, SWE-Atlas QA 50.0, SWE-Bench Pro v2 Hard 89.9 and ExploitBench 34.8, against Inkling-Small, Beam 1.0, Muse Spark Open, GLM 5.3 Flash, DeepSeek V4.1 Flash, GPT-6 Luna, Claude Haiku 5.5 and SWE-2. 200 tokens a second against SWE-2's 60, shown as a simulated replay
- Pricing: Free in Devin Desktop and CLI through 30 November 2026. 'One-fifth the price' of SWE-2 (list $3.00 input, $0.30 cached input, $15.00 output per million tokens), with no SWE-2 Flash figure published. Plan usage is a daily and weekly quota, then extra usage at API pricing
- Data use: Cognition's platform terms of 30 June 2026 let it use customer data for model training unless a paid customer opts out. Enterprise data isn't trained on without written consent (as read for the devin listing)
- Status: www.devinstatus.com (Atlassian Statuspage) has Desktop Agent and Desktop Tab components alongside the cloud ones. In the 90 days to 4 November 2026 its feed lists 'Devin unavailable' for 20 minutes on 13 August with no component named, Devin Cloud unavailable on 13 August, the web app down on 24 September and minor cloud incidents. None names Desktop or the CLI. A scheduled upgrade of Devin Desktop's extension marketplace on 7 August is read as maintenance
- Family: SWE-1 and SWE-1.5 were Windsurf's models; Windsurf is now Devin Desktop, and Cognition publishes the SWE line, SWE-1.5, SWE-1.6, SWE-1.7 and SWE-2 (10 September 2026), on its own blog. None of them is listed

- Scores: Reliability 50, Performance pending, Schema & documentation 29, Agent ergonomics 10, Security & auth 53, Payments & pricing 20, Task success pending, Maintenance & community 53, Transparency & trust 64 · negative events -2 · total over the 7 assessed categories
- Why: Reliability, Model reading, for the surface it runs on, Devin Desktop and Devin CLI. · Schema & documentation, Model reading. · Agent ergonomics, Model reading (tool use, structured output, caching, context, batch, SDKs). · Security & auth, Read as a hosted model reached through Devin's local clients. · Payments & pricing, Published rubric. · Maintenance & community, Model reading. · Transparency & trust, Editorial half.
- Sources: 25, open questions: 8, both in the full twin
- Capabilities: inference.llm
- JSON: https://www.anchorterminal.com/api/v1/tools/swe-2-flash.json
- Verify (for the vendor): the badge `https://www.anchorterminal.com/badges/swe-2-flash.svg` or a link to https://www.anchorterminal.com/tools/swe-2-flash from a page on cognition.com or one of its subdomains, then `POST https://www.anchorterminal.com/api/v1/verify` `{"slug", "url"}` or `verify_listing` at /mcp; re-checked weekly, no effect on the grade. Snippets in the full twin.
- Support: https://devin.ai/support; more in the full twin

## Before you call it

1. There is no endpoint to call. Run Devin CLI single-turn with `devin -p` and pick the model with `--model`; the SWE-2 Flash model ID isn't documented yet, so check `/model` in the CLI first
2. Don't rely on the short name `swe`. The docs say it resolves to the latest model in the family, which may be SWE-2 rather than SWE-2 Flash
3. Plan for billing to start on 1 December 2026. The free period covers Devin Desktop and CLI only, not Devin cloud sessions
4. Treat Cognition's benchmark figures as the vendor's. No independent result for SWE-2 Flash was found
5. Keep `credentials.toml` private. The token in it doesn't expire by default and carries the signed-in user's access

## Connect

```bash
Install Devin CLI or Devin Desktop from https://devin.ai/download, sign in with `devin auth login`, then choose SWE-2 Flash with `/model`
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| OpenAI API | A | 83.9 | inference.llm | https://www.anchorterminal.com/tools/openai-api.min.md |
| BlockRun.AI | A | 78.9 | inference.llm | https://www.anchorterminal.com/tools/blockrun-ai.min.md |
| Claude API | BB | 77.3 | inference.llm | https://www.anchorterminal.com/tools/anthropic-api.min.md |
| GroqCloud | BB | 74.5 | inference.llm | https://www.anchorterminal.com/tools/groq.min.md |
| Fireworks AI Inference | B | 69.3 | inference.llm | https://www.anchorterminal.com/tools/fireworks-inference.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)