Step 5 Preview
stepfun-ai/step-5-preview · in: text, image, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image video.
$1.43
Blended $/1M (3:1)
$1
Input $/1M
$2.7
Output $/1M
$3.70
1M in + 1M out
$0.1 −90%
Cache read $/1M
#4959 of 8,511
Cheapest rank
- Provider
- StepFun (Global) (
stepfun-ai) - Kind
- text (outputs text)
- Context
- 1,024,000 tokens
- Max output
- 65,536 tokens
- Capabilities
- tools reasoning text image video
Same model, other providers
“Step 5 Preview” is offered by 16 providers — cheapest-effective first. Nvidia is the cheapest at $0.00 blended.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| Nvidia | free | free | $0.00 | 1M |
| StepFun (Global) (this) | $1 | $2.7 | $1.43 | 1M |
| Deep Infra | $1 | $2.7 | $1.43 | 1M |
| Vercel AI Gateway | $1 | $2.7 | $1.43 | 1M |
| Requesty | $1 | $2.7 | $1.43 | 1M |
| Novita AI | $1 | $2.7 | $1.43 | 1M |
| EmpirioLabs AI | $1 | $2.7 | $1.43 | 1M |
| CommandCode | $1 | $2.7 | $1.43 | 1M |
| OpenCode Go | $1 | $2.7 | $1.43 | 1M |
| Kilo Gateway | $1 | $2.7 | $1.43 | 1M |
| DevPass (LLM Gateway) | $1 | $2.7 | $1.43 | 1M |
| OpenRouter | $1 | $2.7 | $1.43 | 1M |
| NanoGPT | $1 | $2.7 | $1.43 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at StepFun (Global) and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"step-5-preview","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):