StepFun: Step 3.5 Flash 2603
Step 3.5 Flash 2603 is a reasoning model from StepFun released on Apr 2, 2026. It reads text and writes text, with a 256K token context window and up to 256K tokens per reply.
Show moreShow less
It costs $0.10 per million input tokens and $0.30 per million output tokens. Cached input bills at $0.02, 80% less than fresh input.
It supports tool calling, structured JSON output and prompt caching, and its weights are open, so you can host it yourself.
6 providers serve it, including EmpirioLabs AI, NanoGPT and StepFun (Global).
- Modalities
- In / out price
- $0.10 / $0.30 per 1M
- Context
- 256K
- Max output
- 256K
- Released
- Apr 2, 2026
- Knowledge cutoff
- Jan 2025
- Tool calling
- Structured output
- Reasoning
- Prompt caching
- Open weights
- Free to use
Step 3.5 Flash 2603 pricing
USD, as listed on Oct 15, 2026. Most bills are input heavy, so the cached input rate matters as much as the headline price.
| Input | $0.10 / 1M tokens | |
|---|---|---|
| Output | $0.30 / 1M tokens | |
| Cached input (read) | $0.02 / 1M tokens | 80% off input |
Step 3.5 Flash 2603 providers
6 providers serve it, including EmpirioLabs AI, NanoGPT and StepFun (Global). Each host sets its own price and limits, so the cheapest one is not always the one with the longest context.
| Provider | Input /M | Output /M | Cache read /M | Context | Max output |
|---|---|---|---|---|---|
| StepFun (China) First party | $0.10 | $0.30 | $0.02 | 256K | 256K |
| EmpirioLabs AI | $0.10 | $0.30 | $0.02 | 256K | 131K |
| NanoGPT | $0.10 | $0.30 | $0.05 | 262K | 66K |
| StepFun (Global) | $0.10 | $0.30 | $0.02 | 256K | 256K |
| StepFun Step Plan (China) | n/a | n/a | – | 256K | 256K |
| StepFun Step Plan (Global) | n/a | n/a | – | 256K | 256K |
What Step 3.5 Flash 2603 costs per month
Pick a workload close to yours or type your own volumes.
Supported request parameters
What you can set when you call Step 3.5 Flash 2603 through an OpenAI compatible API.
- Tools
tools - Structured outputs
structured_outputs - Reasoning
reasoning - Temperature
temperature
Alternatives to Step 3.5 Flash 2603
Models that take the same inputs and call tools, closest in price, cheaper ones first.
- Index 10
Reads text. Tool calling, structured output, reasoning. Served by 35 providers.
by openaiJun 1, 2024128K context$0.07/M input tokens$0.30/M output tokens35 providers
- 256K context
Reads text. Tool calling, structured output, reasoning. Served by 13 providers.
by stepfunJan 29, 2026$0.10/M input tokens$0.30/M output tokens13 providers
- 262K context
Reads text. Tool calling, reasoning. Served by 2 providers.
by xiaomiDec 16, 2025$0.10/M input tokens$0.30/M output tokens2 providers
- 33K context
Reads text. Tool calling, reasoning.
by qwenMar 31, 2025$0.15/M input tokens$0.15/M output tokens
- 33K context
Reads text. Tool calling, reasoning.
by googleFeb 28, 2025$0.15/M input tokens$0.15/M output tokens
- 256K context
Reads text, images, audio and video. Tool calling, structured output, reasoning. Served by 7 providers.
by nvidiaApr 28, 2026$0.10/M input tokens$0.25/M output tokens7 providers
More from StepFun
- 1M context
Reads text, images and video. Tool calling, structured output, reasoning. Served by 11 providers.
by stepfunSep 16, 2026$0.959/M input tokens$2.74/M output tokens11 providers
- 256K context
Reads text, images and video. Tool calling, structured output, reasoning. Served by 19 providers.
by stepfunMay 29, 2026$0.185/M input tokens$1.11/M output tokens19 providers
StepAudio 2.5 ASR
TranscriptionTurns speech into text. Served by 2 providers.
by stepfunApr 24, 20262 providers
StepAudio 2.5 TTS
SpeechTurns text into spoken audio. Served by 2 providers.
by stepfunApr 16, 20262 providers
Step TTS 2
SpeechTurns text into spoken audio. Served by 2 providers.
by stepfunMar 1, 20262 providers
- 256K context
Reads text. Tool calling, structured output, reasoning. Served by 13 providers.
by stepfunJan 29, 2026$0.10/M input tokens$0.30/M output tokens13 providers
Step 3.5 Flash 2603 questions
How much does the Step 3.5 Flash 2603 API cost?
$0.10 per million input tokens and $0.30 per million output tokens, with cached input at $0.02. The estimator on this page turns that into a monthly bill for your own workload.
What is the context window of Step 3.5 Flash 2603?
256,000 tokens of input, and it can write up to 256,000 tokens in one reply. As a rough guide, a million tokens is around 750,000 English words.
Which providers serve Step 3.5 Flash 2603?
6 providers serve it, including EmpirioLabs AI, NanoGPT and StepFun (Global). Prices differ by host, so the Providers table on this page lists each one with its input and output price.
Does Step 3.5 Flash 2603 support tool calling?
Yes. It accepts tool definitions and can return JSON that matches a schema, which is what an agent needs to call your APIs.
Is Step 3.5 Flash 2603 open source?
Its weights are published, so you can run it on your own hardware or a cloud of your choice. Read the license before commercial use.
When was Step 3.5 Flash 2603 released?
Apr 2, 2026, with training data up to Jan 2025.
Catalog data from models.dev (MIT licensed), refreshed daily, last on Oct 15, 2026. The summary is written from these facts.
Building on Step 3.5 Flash 2603?
I test your real tasks on it and the two closest alternatives, then ship the agent on whichever wins on cost and accuracy.
Book Meeting