Type
Spec
Rate
Input
per 1M prompt tokens
$0.10
Output
per 1M generated tokens
$0.30
Implicit cache read
per 1M cached input tokens
$0.02
Web Search (Linkup)
per call when invoked
$0.013
Step 3.5 Flash 2603 and Step 3.5 Flash side by side: specs, capabilities, parameters, and live pricing from the EmpirioLabs catalog.
StepFun Text GenerationStep 3.5 Flash 2603 and Step 3.5 Flash are both StepFun models in the Text Generation category, available through the EmpirioLabs API.
| Spec | Step 3.5 Flash 2603 | Step 3.5 Flash |
|---|---|---|
| Model ID | step-3-5-flash-2603 | step-3-5-flash |
| Author | StepFun | StepFun |
| Released | Apr 2, 2026 | Feb 12, 2026 |
| Context window | 256K tokens | 256K tokens |
| Max output | 131,072 tokens | 131,072 tokens |
| Input | Text | Text |
| Output | Text | Text |
| Structured output | Not supported | Not supported |
| Region | International | International |
| Endpoints | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/step-3-5-flash-2603:generateContent | POST /v1/chat/completions POST /v1/responses POST /v1/messages POST /v1beta/models/step-3-5-flash:generateContent |
| Capabilities |
Live rates from the EmpirioLabs catalog for both models. Each rate card always matches what the API charges.
Request parameters each model lists on EmpirioLabs, with the allowed values or range where one applies. A dash marks a parameter the model does not list.
| Parameter | Step 3.5 Flash 2603 | Step 3.5 Flash |
|---|---|---|
| temperature | 0 to 2 Default: 0.5 | 0 to 2 Default: 0.5 |
| top_p | 0.01 to 1 Default: 0.9 | 0.01 to 1 Default: 0.9 |
| max_tokens | 1 to 131072 Default: 4096 | 1 to 131072 Default: 4096 |
| stop | array | array |
| frequency_penalty | -2 to 2 Default: 0 | -2 to 2 Default: 0 |
| reasoning_effort | low, high Default: low | - |
| reasoning_format | general, deepseek-style Default: general | general, deepseek-style Default: general |
| tools | array | array |
| tool_choice | string | string |
| web_search_linkup | boolean Default: false | boolean Default: false |
| disable_formatting | boolean Default: false | boolean Default: false |
Text-only agent model with 256K context, function tools, prompt-cache billing, reasoning_effort low or high, and optional Linkup web search.
Text-only reasoning with 256K context, function tools, prompt-cache billing, and optional Linkup web search.
Step 3.5 Flash 2603 serves the OpenAI-compatible Chat Completions API. Point any OpenAI SDK at https://api.empiriolabs.ai/v1 with your EmpirioLabs API key and use the model id step-3-5-flash-2603. Both models are called through the same endpoint. Set model to step-3-5-flash-2603 or step-3-5-flash. Get an API key from the EmpirioLabs dashboard.
curl https://api.empiriolabs.ai/v1/chat/completions \
-H "Authorization: Bearer $EMPIRIOLABS_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "step-3-5-flash-2603",
"messages": [
{"role": "user", "content": "Write a haiku about the ocean."}
]
}'Step 3.5 Flash 2603 is the newer release (Apr 2, 2026); Step 3.5 Flash was released on Feb 12, 2026. Both models have a context window of 256K tokens. Both models list the same rate for Input (per 1M prompt tokens) and Output (per 1M generated tokens). The specs, rate cards, and parameters on this page come from the live EmpirioLabs catalog.
Step 3.5 Flash 2603 is the newer release (Apr 2, 2026); Step 3.5 Flash was released on Feb 12, 2026.
Both models list the same rate for Input (per 1M prompt tokens) and Output (per 1M generated tokens). Both live rate cards are on this page and always match what the API charges.
Yes. Both models use POST /v1/chat/completions with the same EmpirioLabs API key, so most integrations switch by changing the model value. Check the parameters table on this page first if you rely on a model-specific parameter.
Yes. Open each model in the EmpirioLabs playground and run the same prompt on both, with the parameters the API exposes.
Check out our pricing or reach out if you want your own model deployed on our stack.