Stepfun 3.7 Flash
stepfun-3.7-flashStep 3.7 Flash is StepFun's 198B-parameter sparse mixture-of-experts vision-language model (about 11B active parameters) that delivers up to 400 tokens/sec with a 256K context and selectable reasoning depth, purpose-built for high-frequency production agentic workflows spanning perception, search, coding, and document reasoning.
Best for
Characteristics
Modalities
Use cases
Anthropic
Yes
Chat Completions
Responses Api
Yes
Provider
Step
Context Window
262K
Available Access
Prices shown per 1M tokens.
Input
Rp. 724
$0.04 USD
Output
Rp. 4.164
$0.23 USD
Cache
Rp. 145
$0.01 USD
All prices are estimates and subject to change.
Similar Models
Related models selected by the catalog administrator.
muse-spark-1.2-contributorMuse Spark 1.2 Contributor is Meta's Muse Spark 1.2 reasoning model served through the discounted 'contributor' data-contribution tier, giving users lower pricing in exchange for contributing data-development effort.
qwen3.8-flashQwen3.8 Flash is the official fast-tier API version of Alibaba's Qwen3.8 generation, based on the Qwen3.8-Flash-Next architecture (an experimental Qwen4-preview design) and offering low-latency, high-throughput multimodal reasoning with 1M-token context and built-in tools.