StepFun

stepfun-ai/Step-3.5-Flash

Generally availableOpen weights262K contextReasoning

Summary

stepfun-ai/Step-3.5-Flash is an open-weight language model from StepFun, released on 29 Jan 2026. It accepts text and generates text, with a 262K-token context window and up to 66K output tokens per response. As of 19 Nov 2026, the lowest listed API price is $0.10 per million input tokens and $0.30 per million output tokens (Hugging Face Inference Providers), across 2 providers we track. It is scheduled for retirement on 15 Nov 2026.

StepFun flash model for efficient multimodal reasoning, coding, and tool use

Last verified 19 Nov 2026. Every figure on this page links to its source.

Specifications

DeveloperStepFun
Release date29 Jan 2026 [models.dev]
StatusGenerally available [models.dev]
WeightsOpen weights [Hugging Face]
Licenseapache-2.0 [Hugging Face]
Parameters199B [Hugging Face]
Context window262K (262,000 tokens) [models.dev]
Max output66K tokens [models.dev]
Knowledge cutoffJan 2025 [models.dev]
InputText [models.dev]
OutputText [models.dev]
Reasoning modeYes [models.dev]
Tool callingYes [models.dev]
Structured outputYes [models.dev]
Retirement date15 Nov 2026 [OpenRouter]
Hugging Facestepfun-ai/Step-3.5-Flash [Hugging Face]

stepfun-ai/Step-3.5-Flash API pricing by provider

USD per million tokens. Sorted by input price.

ProviderInputOutputCached inputContextSource
Hugging Face Inference Providers
stepfun-ai/Step-3.5-Flash
$0.10$0.30–262Kmodels.dev, 19 Nov 2026
SiliconFlow
stepfun-ai/Step-3.5-Flash
$0.10$0.30–262Kmodels.dev, 19 Nov 2026

Running stepfun-ai/Step-3.5-Flash locally

Estimated memory, from the parameter count and the architecture in config.json on Hugging Face. Includes about 0.8 GB of runtime overhead.

QuantizationWeightsTotal, 8K contextTotal, 32K context
Q4_K_M (4-bit)121 GB126 GB135 GB
Q8_0 (8-bit)212 GB216 GB226 GB
FP16 / BF16 (16-bit)399 GB403 GB413 GB

At 4-bit with an 8K conversation, stepfun-ai/Step-3.5-Flash needs about 126 GB, more than any single consumer graphics card; it needs a unified-memory machine, a multi-GPU setup or a split between graphics card and system RAM. Check your own hardware, or see Best computer for local AI on our sister site AIPCs.

Frequently asked questions

What is the context window of stepfun-ai/Step-3.5-Flash?

stepfun-ai/Step-3.5-Flash has a context window of 262,000 tokens (262K) and can generate up to 66,000 tokens in a single response, according to models.dev.

How much does the stepfun-ai/Step-3.5-Flash API cost?

stepfun-ai/Step-3.5-Flash is listed from $0.10 per million input tokens and $0.30 per million output tokens (Hugging Face Inference Providers). Prices last verified 19 Nov 2026.

Is stepfun-ai/Step-3.5-Flash open source?

stepfun-ai/Step-3.5-Flash is an open-weight model: its weights are published on Hugging Face as stepfun-ai/Step-3.5-Flash under the apache-2.0 license. Check the license terms before commercial use.

When was stepfun-ai/Step-3.5-Flash released?

StepFun released stepfun-ai/Step-3.5-Flash on 29 Jan 2026, according to models.dev.

Which providers offer stepfun-ai/Step-3.5-Flash?

We track stepfun-ai/Step-3.5-Flash on 2 providers: Hugging Face Inference Providers, SiliconFlow.

How much VRAM does stepfun-ai/Step-3.5-Flash need?

About 126 GB at 4-bit (Q4_K_M) with an 8K-token conversation, and about 216 GB at 8-bit. That is more than any single consumer graphics card holds. These are estimates from the model's published parameter count and architecture.

Similar models from other labs

Comparable on output type, weights, release date, price and context window. Prices are the lowest listed, USD per million tokens.

ModelLabReleasedContextInput $/1MOutput $/1MWeights
Ministral 14BMistral AI2 Dec 2025262K$0.20$0.20Open
Ministral 3 14BMistral AI2 Dec 2025262K$0.20$0.20Open
Nemotron 3 Super 120B A12BNVIDIA11 Mar 2026262K$0.07$0.40Open
Gemma 4 26B A4B ITGoogle DeepMind2 Apr 2026262K$0.07$0.30Open
GLM-4.7-FlashXZhipu AI (Z.ai)19 Jan 2026200K$0.06$0.40Open
GLM-4.7-FlashZhipu AI (Z.ai)19 Jan 2026200K$0.06$0.40Open

Change history

  • Context window changed from 262K to 262K
  • Max output changed from 256K to 66K
  • Name changed from Step 3.5 Flash to stepfun-ai/Step-3.5-Flash
  • Context window changed from 262K to 262K
  • Name changed from stepfun-ai/Step-3.5-Flash to Step 3.5 Flash
  • Max output changed from 66K to 256K
  • No longer listed on openrouter
  • Name changed from Step 3.5 Flash to stepfun-ai/Step-3.5-Flash
  • Context window changed from 262K to 262K
  • Max output changed from 256K to 66K
  • Max output changed from 66K to 256K
  • Name changed from stepfun-ai/Step-3.5-Flash to Step 3.5 Flash
  • Context window changed from 262K to 262K
  • Retirement date changed from none to 15 Nov 2026
  • Name changed from Step 3.5 Flash to stepfun-ai/Step-3.5-Flash
  • Max output changed from 66K to 66K
  • Structured output changed from no to yes
  • Context window changed from 262K to 262K
  • Max output changed from 256K to 66K
  • Structured output changed from yes to no
  • Context window changed from 262K to 262K
  • Max output changed from 66K to 256K
  • Name changed from stepfun-ai/Step-3.5-Flash to Step 3.5 Flash
  • Name changed from Step 3.5 Flash to stepfun-ai/Step-3.5-Flash
  • Context window changed from 262K to 262K

Sources