jishie

Step 3.5 Flash 2603

stepfun-step-plan/step-3.5-flash-2603 · price provider-declared (via models.dev), USD per 1M tokens. Capabilities: toolsreasoningtext.

—Blended $/1M (3:1)
—Input $/1M
—Output $/1M
—1M in + 1M out
—Cache read $/1M
—Cheapest rank
Provider
StepFun Step Plan (China) (stepfun-step-plan)
Context
256,000 tokens
Max output
256,000 tokens
Capabilities
toolsreasoningtext

Same model, other providers

“Step 3.5 Flash 2603” is offered by 5 providers — cheapest-effective first. NanoGPT is the cheapest at $0.15 blended.

ProviderInputOutputBlendedContext
NanoGPT$0.1$0.3$0.15256k
EmpirioLabs AI$0.1$0.3$0.15256k
StepFun (Global)$0.1$0.3$0.15256k
StepFun (China)$0.1$0.3$0.15256k
StepFun Step Plan (China) (this)———256k

Call it

jishie indexes & prices models; it does not proxy inference. Most providers are OpenAI-compatible — point base_url at StepFun Step Plan (China) and pass this model id:

curl $BASE_URL/v1/chat/completions \
  -H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
  -d '{"model":"step-3.5-flash-2603","messages":[{"role":"user","content":"hello"}]}'

Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):