# Nemotron 3.5 Super VL vs SWE-2 Flash (slim)

> Nemotron 3.5 Super VL scores 59.3 (C) to SWE-2 Flash's 36.4 (F) for llm inference. Prices, MCP, x402, uptime and agent notes side by side.

- Full: https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-swe-2-flash.md (~6,800 tokens) · this version ~3,530 tokens · JSON https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-swe-2-flash.json · canonical https://www.anchorterminal.com/compare/nemotron-3-5-super-vl-vs-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
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

Nemotron 3.5 Super VL scores 59.3 (C) on agent readiness against SWE-2 Flash's 36.4 (F), and leads in 6 of 7 scored categories. SWE-2 Flash leads on transparency & trust. Both do llm inference.

- Nemotron 3.5 Super VL: C 59.3, rank #635 of 1350 · https://www.anchorterminal.com/tools/nemotron-3-5-super-vl.min.md
- SWE-2 Flash: F 36.4, rank #1243 of 1350 · https://www.anchorterminal.com/tools/swe-2-flash.min.md
- Nemotron 3.5 Super VL, good for Agents that read documents, charts, screenshots and short videos and need tool calls in one open model, prototyped free on NVIDIA's endpoint and moved to a partner host or own GPUs for production. Ahead on Reliability, 58 against 50; Schema & documentation, 74 against 29; Agent ergonomics, 65 against 10; Payments & pricing, 35 against 20; Maintenance & community, 71 against 53. Also A hosted endpoint, with nothing to install; Free to start without a card.
- SWE-2 Flash, good for People already using Devin Desktop or Devin CLI who want a cheaper, faster model for routine coding work such as automations, reviews and small changes, while it is free in November 2026. Ahead on Transparency & trust, 64 against 58.

| Category | Nemotron 3.5 Super VL | SWE-2 Flash |
| --- | --- | --- |
| Reliability (16%) | 58 | 50 |
| Performance (10%) | pending | pending |
| Schema & documentation (13%) | 74 | 29 |
| Agent ergonomics (13%) | 65 | 10 |
| Security & auth (14%) | 54 | 53 |
| Payments & pricing (10%) | 35 | 20 |
| Task success (10%) | pending | pending |
| Maintenance & community (7%) | 71 | 53 |
| Transparency & trust (7%) | 58 | 64 |

| Fact (where they differ) | Nemotron 3.5 Super VL | SWE-2 Flash |
| --- | --- | --- |
| Vendor | NVIDIA | Cognition AI, Inc. |
| Hosted endpoint | `https://integrate.api.nvidia.com/v1` | no (local only) |
| Transports | HTTP |  |
| Auth | API key | OAuth or key |
| Pricing | Free | Freemium |
| Licence | OpenMDW-1.1 for the weights (permissive, not an OSI licence). The hosted trial endpoint is under the NVIDIA API Trial Terms of Service, and the NIM container under the NVIDIA Software Licence Agreement | 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 |
| Last release | 2026-10-15 | 2026-11-04 |
| Terms last updated | not read yet | 2026-06-30 |
| Privacy policy last updated | no date given | 2026-03-09 |
| Customer content may train models | not read yet | yes, with an opt-out |
| Terms restrict automated access | not read yet | not found in the text |
| Terms restrict benchmarking | not read yet | yes |
| Terms or service can change without notice | not read yet | not found in the text |
| Arbitration or class-action waiver | not read yet | yes |
| Agent reviews | 3/5 (4) | none |

Why the edge:
- Agent ergonomics, Nemotron 3.5 Super VL +55: Nemotron 3.5 Super VL 65 (Model reading of the checklist (tool use, structured output, caching, context, batch, SDKs, errors). OpenAI-format tools, `tool_choice` auto, none, required or a named function, and parallel calls on by default (20 of 20). `response_format` with `json_schema` and `strict` in the OpenAPI file. Not tested by us (12 of 15). The card describes prefix caching for self-hosted serving, but no caching on the hosted endpoint is documented (2 of 10). 1M tokens in the weights, but the hosted page lists 262K, and completions are capped at 131,072 tokens (12 of 15). No batch mode (0 of 10). Any OpenAI SDK works with the base URL, and NVIDIA maintains `langchain-nvidia-ai-endpoints`. Only `messages` is required, but reasoning defaults to on at high effort and the reference defaults `stream` to true (10 of 15). Errors carry a message, type and request id, with no 429 or rate-limit body documented (9 of 15). 65.); SWE-2 Flash 10 (Model reading (tool use, structured output, caching, context, batch, SDKs). Tool use is Devin's harness, not something a caller configures; no context length, output limit or cache price is published for SWE-2 Flash (5 of 25). No documented output-size or reasoning controls for this model; SWE-2's effort levels aren't stated for Flash (0 of 20). No model-level error documentation (0 of 20). No idempotency or retry guidance (0 of 20). One flag or picker selects it and `devin -p` runs a single turn and prints to stdout, but there is no SDK or direct endpoint (5 of 15). 5 + 0 + 0 + 0 + 5 = 10.)
- Schema & documentation, Nemotron 3.5 Super VL +45: Nemotron 3.5 Super VL 74 (Model reading. An OpenAPI 3.1 file for this model's `/chat/completions` on docs.api.nvidia.com, with typed request and response schemas (25). build.nvidia.com/llms.txt, a Markdown copy of the model page and a Markdown copy of the API reference (10). The card and NIM page state intended uses, deployment geography, hardware per checkpoint and reasoning modes, but say little on when not to use the model, and the docs disagree on the medium reasoning switch (`medium_effort` on the card, `low_effort` in the API snippets) (13 of 20). Enums for `reasoning_effort`, `tool_choice` and `response_format`, ranges for `temperature`, `top_p` and `max_tokens`, and `messages` required with at least one item. `chat_template_kwargs` is a free-form object and is the switch the snippets use (12 of 15). Python, LangChain, Node and curl examples with responses, and 400, 422 and 500 error schemas with examples. No 429 (11 of 15). No changelog for the catalogue or the model. The OpenAPI version is 1.0.0, its licence field names the NVIDIA Nemotron Open Model Licence where the card says OpenMDW-1.1, and card revisions are visible only in the Hugging Face commit history (3 of 15). 74.); SWE-2 Flash 29 (Model reading. No model API, so no OpenAPI entry; the Devin v3 OpenAPI file lists SWE-2 agents only, and no model card was found (0). docs.devin.ai serves llms.txt and Markdown copies of every page (10). The launch post says what it is for (automations, code review, feature development, documentation) and the CLI docs say when to pick a SWE model, but the models pages don't list SWE-2 Flash yet (6 of 20). No documented model ID, reasoning settings, context or output limits to type (0 of 15). The CLI pages show `--model` and `/model` examples, with no model-specific errors (3 of 15). Named, dated model versions on Cognition's blog and public release notes, but no release note for SWE-2 Flash yet; the newest is 2 November (10 of 15). 0 + 10 + 6 + 0 + 3 + 10 = 29.)
- Maintenance & community, Nemotron 3.5 Super VL +18: Nemotron 3.5 Super VL 71 (Released on 15 October 2026. The Hugging Face commit lists, re-read on 4 November, show a processor-config and video-forward fix in the BF16 repository on 22 October and a hardware support matrix update in the NVFP4 repository on 23 October, 12 days before this check (30). NVIDIA released three Nemotron 3.5 models in the 90 days (Lightning in August, Content Safety and Super VL), but publishes no deprecation notice periods for catalogue models, so churn can't be judged (10 of 20). On Hugging Face two pull requests on SGLang instructions were merged within a day, and two others were open when read. Support for the free tier is the developer forum (15 of 25). NVIDIA maintains `langchain-nvidia-ai-endpoints` (1.5.0 tagged 14 October, repository commits to 26 October), and the endpoint takes OpenAI SDKs (10 of 15). Day-one recipes for vLLM 0.32.0, SGLang, TensorRT-LLM and a NIM container, though the card's vLLM command also names a nightly image (6 of 10). 30+10+15+10+6 = 71.); SWE-2 Flash 53 (Model reading. Released 4 November 2026 (30). Churn and notice in place of release counts: SWE-1.6, SWE-1.7, SWE-1.7 Lightning, SWE-2 (10 September) and now SWE-2 Flash in a few months, with no model deprecation notice period found and short names that move to the newest model (10 of 20). Public release notes and a support address, no public tracker (10 of 25). No official SDK for the model (0 of 15). The docs are kept current but don't yet cover this model (3 of 10). 30 + 10 + 10 + 0 + 3 = 53.)
- Payments & pricing, Nemotron 3.5 Super VL +15: Nemotron 3.5 Super VL 35 (No x402, MPP or L402 (0). The hosted endpoint is free and says so without a login, and the production routes are priced in public (AI Enterprise at $4,500 a GPU a year, partner hosts per million tokens), but the free endpoint can't be used in production and has no per-call price of its own (15 of 20). Free with no card per build.nvidia.com/llms.txt (20). A person signs in at build.nvidia.com, which uses SMS verification per the status page, to generate a key. No keyless or programmatic route (0). 35.); SWE-2 Flash 20 (Published rubric. No payment protocol (0). Plan prices are public, but no per-token price for SWE-2 Flash is on a readable page; the docs' cost table loads in the browser and the post gives only 'one-fifth the price' of SWE-2 (10). Free through 30 November 2026 on Devin Desktop and CLI, but the docs say Free tier users only have SWE-1.6, so whether the Free plan reaches it, and without a card, isn't confirmed; the in-between value used on the devin listing (10). A person signs in through a browser (0). 0 + 10 + 10 + 0 = 20.)
- Reliability, Nemotron 3.5 Super VL +8: Nemotron 3.5 Super VL 58 (Hosted reading, for NVIDIA's trial endpoint. status.ngc.nvidia.com is a Statuspage site with NVIDIA Build and Cloud Functions components and a readable history (20). In the 90 days to 4 November, re-read from history.atom, two incidents, both minor for an API caller, and none posted since 29 September. SMS verification for NVIDIA Build was unavailable in China from 23 to 29 September, which affects sign-up, and on 10 August new Cloud Functions deployments failed for about three hours while existing deployments kept running (20). build.nvidia.com gives limits of up to 40 requests a minute and 10,000 a day, and says they vary by model and with other users' traffic (12 of 15). The OpenAPI file documents a 202 pending result with an `NVCF-REQID` to poll, but no 429, Retry-After or backoff guidance, and NVIDIA's FAQ says to expect long waits under load (3 of 15). No SLA for the trial. NVIDIA's SLAs come with AI Enterprise for self-hosted software (0). The card says v1.0 GA, but the hosted page calls the model early access and NVIDIA calls the catalogue a trial for prototyping only (3 of 10). The model page re-read on 4 November still says early access, with a free endpoint marked available and 40 rpm. 20+20+12+3+0+3 = 58.); SWE-2 Flash 50 (Model reading, for the surface it runs on, Devin Desktop and Devin CLI. Status page at www.devinstatus.com (Atlassian Statuspage) with Desktop Agent and Desktop Tab components besides the cloud ones, read on 4 November 2026 (20). The history feed for the 90 days from 6 August lists 'Devin unavailable' for 20 minutes on 13 August with no component named, read as across the board and a major as on the devin listing; Devin Cloud unavailable on 13 August and the web app down on 24 September name cloud surfaces this model doesn't use; the rest are degraded-performance incidents (new sessions on 3 September, 'multiple services' on 17 September, Ask Devin on 26 October, automation triggers on 4 November) and session queuing on 10 and 11 August, read as minor and a scheduled Devin Desktop extension marketplace upgrade on 7 August, read as maintenance. One major (10). No rate limit figures for the model or the CLI; usage is a daily and weekly quota with no numbers (0). No 429, backoff or retry guidance for this surface (0). Cognition publishes an SLA (25 February 2026) with uptime and response times that applies when included in an order form, read as a contractual SLA on Enterprise, as on other listings (10). The launch post makes it available today with no preview or beta label (10). 20 + 10 + 0 + 0 + 10 + 10 = 50.)
- Transparency & trust, SWE-2 Flash +6: Nemotron 3.5 Super VL 58 (Weights under OpenMDW-1.1, a short permissive licence from the Linux Foundation with no field-of-use limits, but not an OSI licence. Datasets and training recipes are released. The hosted trial is under terms we couldn't read, and the OpenAPI file names a different model licence and the AI Enterprise EULA (22 of 30). NVIDIA's privacy policy (22 September 2025) doesn't address API prompts. The model page says use is logged for security and to improve NVIDIA products, with improvement data not linked to identity, and gives no retention period. The trial terms that may say more were unread (8 of 30). No deprecation policy or dated notices for catalogue models. The page carries an `isDeprecated` flag only (3 of 20). The quickstart says hosted endpoints run on NVIDIA DGX Cloud, but no subprocessors or data locations for the catalogue were found (5 of 20). `langchain-nvidia-ai-endpoints`, the listing's package, sends aggregate usage counts to NVIDIA by default for hosted endpoints, disclosed in its README with `NVIDIA_USAGE_TELEMETRY_ENABLED=false` as the opt-out, and its envelope sets user, device and session fields to "undefined", as the README says. Disclosed, so no term. 22+8+3+5 = 38.); SWE-2 Flash 64 (Editorial half. Closed model under Cognition's platform terms; the weights aren't public and the sharing programme isn't described yet (15). Terms, privacy policy, security page and DPA agree, with training on self-serve data by default and no retention periods, as read for the devin listing (18). The API versioning policy covers API endpoints, not models, and no model deprecation notice was found (5 of 20). Sub-processors listed with purpose and country, per the devin listing's 8 October check (18). 15 + 18 + 5 + 18 = 56.)