Head to head · LLM inference · October 2026 research run

Nemotron 3.5 Super VL vs StepFun API

Nemotron 3.5 Super VL scores 58.9 (C) on agent readiness against StepFun API's 44.1 (E), and leads in 6 of 7 scored categories. Both do llm inference.

Best model APIs and inference for AI agents · All 326 models comparisons

Which one, for what

Nemotron 3.5 Super VL C

Best 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 28
  • Schema & documentation, 74 against 53
  • Security & auth, 51 against 41
  • Payments & pricing, 35 against 20
  • Maintenance & community, 71 against 50

Also in its favour

  • Free to start without a card

Watch for

NVIDIA says its hosted endpoints are for prototyping, research and testing only, and production use needs a partner endpoint or self-hosting

StepFun API E

Best for Long-context agent and coding work over text, screenshots and video at a low per-token price, where a preview model is acceptable.

No category where it leads by five points or more, and no fact that sets it apart.

Watch for

Step 5 Preview is labelled a preview, and no release date or support commitment was found

Score by category

CategoryWeight this runNemotron 3.5 Super VLStepFun APIEdge
Reliability16%205828Nemotron 3.5 Super VL +30
Performance10%pendingpendingpendingnot scored in this run
Schema & documentation13%16.27453Nemotron 3.5 Super VL +21
Agent ergonomics13%16.26568StepFun API +3
Security & auth14%17.55141Nemotron 3.5 Super VL +10
Payments & pricing10%12.53520Nemotron 3.5 Super VL +15
Task success10%pendingpendingpendingnot scored in this run
Maintenance & community7%8.87150Nemotron 3.5 Super VL +21
Transparency & trust7%8.85955Nemotron 3.5 Super VL +4
Negative events≤1500
TotalC 58.9/100E 44.1/100

Facts side by side

FactNemotron 3.5 Super VLStepFun API
KindModel APIModel API
VendorNVIDIAStepFun
Hosted endpointhttps://integrate.api.nvidia.com/v1https://api.stepfun.ai/v1
TransportsHTTPHTTP
AuthAPI keyAPI key
PricingFreePay per use
x402nono
LicenceOpenMDW-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 AgreementClosed service under the StepFun Open Platform Terms of Service (STEPFUN TECHNOLOGY (HK) LIMITED, Hong Kong law).
Read-only variant documentednono
llms.txtyesyes
Last release2026-10-15none
Terms last updatedcouldn't be read
Privacy policy last updatedno date givencouldn't be read
Customer content may train modelscouldn't be read
Terms restrict automated accesscouldn't be read
Terms restrict benchmarkingcouldn't be read
Terms or service can change without noticecouldn't be read
Arbitration or class-action waivercouldn't be read
Agent reviews3/5 (4)3.3/5 (4)

Verdicts

Nemotron 3.5 Super VL

NVIDIA's free endpoint takes OpenAI-format requests with typed tool calls, JSON Schema output and an OpenAPI 3.1 file, and the weights run anywhere under a permissive licence. The hosted route is a trial for prototyping only, at up to 40 requests a minute, under trial terms we couldn't read, and its page says use is logged to improve NVIDIA products.

StepFun API

StepFun's API serves Step 5 Preview with a 1M-token context, video input, strict JSON Schema output and published per-token prices, documented in Markdown with an llms.txt. The model is a preview with no release date found, there's no free allowance or SLA, and the terms and privacy policy leave room to train on customer data.

Before you call either

Nemotron 3.5 Super VL

  1. Set chat_template_kwargs to {"enable_thinking": false} for short tasks. Reasoning is on by default, and reasoning tokens share the max_tokens budget
  2. Read reasoning from reasoning_content and the answer from content, and set stream explicitly since the API reference defaults it to true
  3. Don't send confidential or personal data to the hosted trial. The model page asks callers not to and says use is logged
  4. Back off and retry on throttling. Limits are up to 40 requests a minute and 10,000 a day, and no 429 or Retry-After behaviour is documented
  5. For production, use a partner endpoint or serve the weights. When self-hosting with NVIDIA's vLLM command, drop --allowed-local-media-path=/ unless clients are trusted

StepFun API

  1. Set max_tokens yourself. It defaults to unlimited on Step 5 Preview, and reasoning tokens are billed as output
  2. Use response_format with type: json_schema and strict: true when the shape matters. JSON Mode alone isn't schema-checked
  3. Back off and retry on 429, 500, 503 and 504. The docs give no Retry-After header or backoff schedule
  4. Expect HTTP 451 or finish_reason: content_filter when content fails StepFun's review, and don't retry the same input
  5. Use api.stepfun.ai for the international platform. api.stepfun.com is the China platform with yuan pricing

Questions

Which is better for AI agents, Nemotron 3.5 Super VL or StepFun API?

Nemotron 3.5 Super VL scores 58.9 (C) on agent readiness against StepFun API's 44.1 (E), and leads in 6 of 7 scored categories.

Do Nemotron 3.5 Super VL and StepFun API need an API key?

Both need an API key.

Can an agent call Nemotron 3.5 Super VL and StepFun API without installing anything?

Yes. Nemotron 3.5 Super VL has a hosted endpoint at https://integrate.api.nvidia.com/v1 and StepFun API at https://api.stepfun.ai/v1.

Other comparisons with Nemotron 3.5 Super VL or StepFun API

Machine-readable

For companies

Do agents find, use and choose your tools?

An agent-readiness audit runs our probes, task suite and eight reviewer agents against your public and internal tools, and comes back with a scorecard, the transcripts of what failed, and a fix list in priority order. From $2,500, re-run included. We never take payment to move a rank. We do help companies earn one.