Step 3.5 Flash 2603

Optimized from Step 3.5 Flash for high-frequency agent workloads. It preserves flagship reasoning and tool calling while improving token efficiency and inference speed, adds a low-reasoning mode to r…

stepFun/step-3.5-flash-2603

Optimized from Step 3.5 Flash for high-frequency agent workloads. It preserves flagship reasoning and tool calling while improving token efficiency and inference speed, adds a low-reasoning mode to reduce consumption, and improves compatibility with coding tools and agent frameworks.

Specifications & capabilities

Input
text
Output
text
Context window · tokens
256000
Published model ID
step-3.5-flash-2603
Capabilities
promptCaching, reasoning, streaming, structuredOutputs, toolCalling

Published prices

1–3 / 3

step-3.5-flash-2603 ↗

$0.02

Inference provider
stepFun
Platform
StepFun
Unit
cache_read_tokens_per_million
Currency
USD
Billing conditions
Billing label
Cached input / 1M tokens

step-3.5-flash-2603 ↗

$0.10

Inference provider
stepFun
Platform
StepFun
Unit
input_tokens_per_million
Currency
USD
Billing conditions
Billing label
Input / 1M tokens (cache miss)

step-3.5-flash-2603 ↗

$0.30

Inference provider
stepFun
Platform
StepFun
Unit
output_tokens_per_million
Currency
USD
Billing conditions
Billing label
Output / 1M tokens

Provider specifications & access

1–1 / 1

Step 3.5 Flash 2603 ↗

source model id
step-3.5-flash-2603
hosting
stepfun-global-hosted
platforms
  • StepFun
context length
256000
architecture
input_modalities
  • text
output_modalities
  • text
capabilities
  • promptCaching
  • reasoning
  • streaming
  • structuredOutputs
  • toolCalling

Source specification observations

1–1 / 1

stepFun ↗

field
context_length
value
256000
normalized value
256000
scope
source-model
source id
stepFun
confidence
1

Original sources

1–2 / 2

StepFun · Model documentation ↗

StepFun · Catalog ↗

Source links

1–1 / 1

Explore more models

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace