Skip to content

Model Library

StepFunReleased April 2, 2026

Step 3.5 Flash 2603

StepFun · Released April 2, 2026

View public research Browse the library

Intelligence score

26

At a glance

Intelligence
26
Speed
181.8tokens/sec
Latency
1.22stime to first token
Input price
$0.10per 1M tokens
Output price
$0.30per 1M tokens
Context window
260Ktokens
Parameters
—

Summary

Comparison summary

Step 3.5 Flash 2603 scores 26 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other reasoning models in a similar price tier (median: 15). Step 3.5 Flash 2603 generates output at 181.8 tokens per second (based on StepFun's API), which is well above average compared to other reasoning models in a similar price tier (median: 99.0 t/s). Step 3.5 Flash 2603 costs $0.10 per 1M input tokens (very competitive, median: $0.25) and $0.30 per 1M output tokens (very competitive, median: $0.87), based on StepFun's API.

Specifications

Technical specifications

Model nameStep 3.5 Flash 2603
ProviderStepFun
Release dateApril 2, 2026
Intelligence score26
Speed181.8 tokens/sec
Latency (TTFT)1.22s
Input price$0.10 / 1M tokens
Output price$0.30 / 1M tokens
Context window260,000 tokens
Parameters—
ReasoningYes
Input modalitiestext
Output modalities—
Open weightsNo
License—
API availability—
SourceModel Intelligence legacy profile: step-3-5-flash

Pricing

Token prices

Price per 1M tokens

Step 3.5 Flash 2603, as listed in the catalog record

Input $0.10 and output $0.30 per 1M tokens. Missing prices are hatched and marked "Not published".
  1. Input$0.10
  2. Output$0.30

Model Intelligence legacy profile: step-3-5-flash

FAQ · 18

Frequently asked questions

Step 3.5 Flash 2603 was released on April 2, 2026.

Step 3.5 Flash 2603 was created by StepFun.

Step 3.5 Flash 2603 scores 26 (estimated) on the Artificial Analysis Intelligence Index, placing it well above average among other reasoning models in a similar price tier (median: 15).

Step 3.5 Flash 2603 generates output at 181.8 tokens per second (based on StepFun's API), which is well above average compared to other reasoning models in a similar price tier (median: 99.0 t/s).

Step 3.5 Flash 2603 has a time to first token (TTFT) of 1.22s (based on StepFun's API), which is better than average compared to other reasoning models in a similar price tier (median: 1.96s).

Step 3.5 Flash 2603 costs $0.10 per 1M input tokens (very competitive, median: $0.25) and $0.30 per 1M output tokens (very competitive, median: $0.87), based on StepFun's API.

Step 3.5 Flash 2603 costs $0.10 per 1M input tokens and $0.30 per 1M output tokens (based on StepFun's API). For a blended rate (7:2:1 cache hit/input/output ratio), this is $0.06 per 1M tokens. Pricing may vary by provider.

Yes, Step 3.5 Flash 2603 is a reasoning model. It uses extended thinking or chain-of-thought reasoning to work through complex problems before providing an answer.

Step 3.5 Flash 2603 supports text input.

Step 3.5 Flash 2603 supports text output.

No, Step 3.5 Flash 2603 does not support image input. It can only process text.

No, Step 3.5 Flash 2603 is not multimodal. It only supports text input.

Step 3.5 Flash 2603 has a context window of 260k tokens. This determines how much text and conversation history the model can process in a single request.

No, Step 3.5 Flash 2603 is proprietary. The model weights are not publicly available.

Step 3.5 Flash 2603 is a proprietary model and StepFun has not disclosed the model size or parameter count.

Step 3.5 Flash 2603 achieves a score of 26 on the Artificial Analysis Intelligence Index. This composite benchmark evaluates models across reasoning, knowledge, mathematics, and coding.

Yes, Step 3.5 Flash 2603 is available via API through 1 provider.

Step 3.5 Flash 2603 is available through 1 API provider.