LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Step 3.5 Flash

stepfun·stepfun/step-3.5-flash·GA·Open weights·step series
StepFun flash lane for quick multimodal reasoning and coding assistance

Specs & pricing

Input / output per 1M tokens
Official price·StepFun (China)
$0.10 / $0.31
Blended $0.16 · Cache read $0.021
Lowest paid·CommandCodeGateway
$0.09 / $0.30
Blended $0.14 · 1.2× spread
Context
256,000
Output limit
256,000
Knowledge cutoff
2025-01
Released / updated
2026-01-29 / 2026-02-13
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
Text
Weights
Hugging Face

Step 3.5 Flash by stepfun is offered by 13 providers on this page. Public prices are shown for 10 of them. Its official list price is $0.105 per 1M input tokens and $0.314 per 1M output tokens. Prices vary about 1.2× across the providers that host it. It also has 2 covered by a paid subscription; free tiers usually carry rate limits, and subscription-covered access bills $0 per token only after the subscription fee.

Median output speed is 151 tokens per second, with 3.3s to the first token.

The context window is 256,000 tokens at the reference host, but hosts report different limits, from 64,000 to 262,144, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2025-01.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed151 tok/s
TTFT3.3 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 13 providers10 with public prices · 2 subscription-covered

  • ProviderInput / Output
  • CommandCodeGateway
    stepfun/Step-3.5-Flash
    $0.09 / $0.30
    Cache read $0.02Context 256,000Output limit 256,000
  • Eden AIGateway
    deepinfra/stepfun-ai/Step-3.5-Flash
    $0.09 / $0.30
    Cache read $0.02Context 262,144 ⚠Output limit 256,000
  • StepFun (Global)OfficialFirst-party
    $0.10 / $0.30
    Cache read $0.02Context 256,000Output limit 256,000
  • NanoGPTGateway
    $0.10 / $0.30
    Cache read $0.05Context 262,144 ⚠Output limit 65,536
  • SiliconFlowCloud
    stepfun-ai/Step-3.5-Flash
    $0.10 / $0.30
    Context 262,000 ⚠Output limit 66,000
  • ZenMuxGateway
    $0.10 / $0.30
    Context 256,000Output limit 256,000
  • Hugging FaceCloud
    stepfun-ai/Step-3.5-Flash
    $0.10 / $0.30
    Context 262,144 ⚠Output limit 256,000
  • EmpirioLabs AIGateway
    step-3-5-flash
    $0.10 / $0.30
    Cache read $0.02Context 262,144 ⚠Output limit 131,072
  • StepFun (China)OfficialFirst-party
    $0.10 / $0.31
    Cache read $0.021Context 256,000Output limit 256,000
  • SiliconFlow (China)Cloud
    stepfun-ai/Step-3.5-Flash
    $0.10 / $0.31
    Context 262,000 ⚠Output limit 262,000
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
CommandCode
stepfun/Step-3.5-Flash
Gateway$0.09$0.30$0.02—256,000256,000
Eden AI
deepinfra/stepfun-ai/Step-3.5-Flash
Gateway$0.09$0.30$0.02—262,144 ⚠256,000
StepFun (Global)OfficialFirst-party$0.10$0.30$0.02—256,000256,000
NanoGPTGateway$0.10$0.30$0.05—262,144 ⚠65,536
SiliconFlow
stepfun-ai/Step-3.5-Flash
Cloud$0.10$0.30——262,000 ⚠66,000
ZenMuxGateway$0.10$0.30——256,000256,000
Hugging Face
stepfun-ai/Step-3.5-Flash
Cloud$0.10$0.30——262,144 ⚠256,000
EmpirioLabs AI
step-3-5-flash
Gateway$0.10$0.30$0.02—262,144 ⚠131,072
StepFun (China)OfficialFirst-party$0.10$0.31$0.021—256,000256,000
SiliconFlow (China)
stepfun-ai/Step-3.5-Flash
Cloud$0.10$0.31——262,000 ⚠262,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Reasoning control

effort = loweffort = higheffort = medium

Interleaved thinking (reasoning between tool calls) is declared by 4 of 13 providers.

4 / 13 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1CommandCode$24.60
2Eden AI$24.60
3StepFun (Global) · Official$25.40
4EmpirioLabs AI$25.40
5StepFun (China) · Official$26.57
6NanoGPT$29.00
Switch to CommandCode to save $0.80/mo (3%). The gap is small, so staying on the official channel is fine.
Note: this is a gateway; verify availability and rate limits yourself.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.31$02026-08-052026-10-21
2026-10-21Input list $0.10Output list $0.31Min blended $0.14

Benchmark4 items

NameConditionsScoreMetricSource
Artificial Analysis Coding Index—31.6indexSource ↗
SciCode—40.4percent correctSource ↗
Terminal-Bench Hard—27.3success rateSource ↗
SWE-Bench Verified—74.4resolvedSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

StepAudio 2.5 ASRsame series—StepAudio 2.5 TTSsame series—Step TTS 2same series—Gemma 4 31B ITcheaper alternative$0 / $0Nemotron 3 Ultra 550B A55Bcheaper alternative$0 / $0GLM-4.7-Flashcheaper alternative$0 / $0Hy3cheaper alternative$0 / $0Step 5 Previewsame lab$1.05 / $2.99Step 3.5 Flash 2603same lab$0.10 / $0.31
Data partly from models.dev (MIT) · StepFun (China) official docs ↗