StepFun Provider for OpenClaw: Setup, Endpoints, and Models
Learn how to install and configure the StepFun provider plugin for OpenClaw, including endpoint regions, authentication, and available models. Ideal for developers integrating StepFun AI services.
Read this when
- You want StepFun models in OpenClaw
- You need StepFun setup guidance
StepFun is provided as an official external plugin (@openclaw/stepfun-provider) that exposes two provider ids:
stepfun, which targets the standard endpointstepfun-plan, which targets the Step Plan endpoint
Warning
The standard and Step Plan providers are distinct, each with its own endpoints and model ref prefixes (
stepfun/...versusstepfun-plan/...). China keys are meant for the.comendpoints, while global keys belong with the.aiendpoints.
Install plugin
openclaw plugins install @openclaw/stepfun-provider
openclaw gateway restart
Region and endpoint overview
| Endpoint | China (.com) | Global (.ai) |
|---|---|---|
| Standard | https://api.stepfun.com/v1 | https://api.stepfun.ai/v1 |
| Step Plan | https://api.stepfun.com/step_plan/v1 | https://api.stepfun.ai/step_plan/v1 |
The authentication environment variable is STEPFUN_API_KEY.
Built-in catalog
Standard (stepfun):
| Model ref | Context | Max output | Notes |
|---|---|---|---|
stepfun/step-3.5-flash | 262,144 | 65,536 | Default standard model |
stepfun/step-3.7-flash | 262,144 | 262,144 | Multimodal image input support |
Step Plan (stepfun-plan):
| Model ref | Context | Max output | Notes |
|---|---|---|---|
stepfun-plan/step-3.5-flash | 262,144 | 65,536 | Default Step Plan model |
stepfun-plan/step-3.7-flash | 262,144 | 262,144 | Multimodal image input support |
stepfun-plan/step-3.5-flash-2603 | 262,144 | 65,536 | Additional Step Plan model |
Getting started
Standard
This option suits general-purpose workloads routed through the standard StepFun endpoint.
Choose your endpoint region
| Auth choice | Endpoint | Region |
|---|---|---|
stepfun-standard-api-key-intl | https://api.stepfun.ai/v1 | International |
stepfun-standard-api-key-cn | https://api.stepfun.com/v1 | China |
Run onboarding
openclaw onboard --auth-choice stepfun-standard-api-key-intl
For the China endpoint:
openclaw onboard --auth-choice stepfun-standard-api-key-cn
Non-interactive alternative
openclaw onboard --auth-choice stepfun-standard-api-key-intl \
--stepfun-api-key "$STEPFUN_API_KEY"
Verify models are available
openclaw models list --provider stepfun
Default model: stepfun/step-3.5-flash
Alternate model: stepfun/step-3.7-flash
Step Plan
This option suits the Step Plan reasoning endpoint.
Choose your endpoint region
| Auth choice | Endpoint | Region |
|---|---|---|
stepfun-plan-api-key-intl | https://api.stepfun.ai/step_plan/v1 | International |
stepfun-plan-api-key-cn | https://api.stepfun.com/step_plan/v1 | China |
Run onboarding
openclaw onboard --auth-choice stepfun-plan-api-key-intl
For the China endpoint:
openclaw onboard --auth-choice stepfun-plan-api-key-cn
Non-interactive alternative
openclaw onboard --auth-choice stepfun-plan-api-key-intl \
--stepfun-api-key "$STEPFUN_API_KEY"
Verify models are available
openclaw models list --provider stepfun-plan
Default model: stepfun-plan/step-3.5-flash
Alternate models: stepfun-plan/step-3.7-flash, stepfun-plan/step-3.5-flash-2603
A single authentication run writes region-matched profiles for both stepfun and stepfun-plan, meaning both surfaces appear together after one onboarding pass.
Advanced configuration
Full config: Standard provider
{
env: { vars: { STEPFUN_API_KEY: "your-key" } },
agents: { defaults: { model: { primary: "stepfun/step-3.5-flash" } } },
models: {
mode: "merge",
providers: {
stepfun: {
baseUrl: "https://api.stepfun.ai/v1",
api: "openai-completions",
apiKey: "${STEPFUN_API_KEY}",
models: [
{
id: "step-3.7-flash",
name: "Step 3.7 Flash",
reasoning: true,
input: ["text", "image"],
thinkingLevelMap: { off: "low", minimal: "low", xhigh: "high", max: "high" },
cost: { input: 0.2, output: 1.15, cacheRead: 0.04, cacheWrite: 0 },
contextWindow: 262144,
maxTokens: 262144,
},
{
id: "step-3.5-flash",
name: "Step 3.5 Flash",
reasoning: true,
input: ["text"],
cost: { input: 0.1, output: 0.3, cacheRead: 0.02, cacheWrite: 0 },
contextWindow: 262144,
maxTokens: 65536,
},
],
},
},
},
}
Full config: Step Plan provider
{
env: { vars: { STEPFUN_API_KEY: "your-key" } },
agents: { defaults: { model: { primary: "stepfun-plan/step-3.5-flash" } } },
models: {
mode: "merge",
providers: {
"stepfun-plan": {
baseUrl: "https://api.stepfun.ai/step_plan/v1",
api: "openai-completions",
apiKey: "${STEPFUN_API_KEY}",
models: [
{
id: "step-3.7-flash",
name: "Step 3.7 Flash",
reasoning: true,
input: ["text", "image"],
thinkingLevelMap: { off: "low", minimal: "low", xhigh: "high", max: "high" },
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
contextWindow: 262144,
maxTokens: 262144,
},
{
id: "step-3.5-flash",
name: "Step 3.5 Flash",
reasoning: true,
input: ["text"],
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
contextWindow: 262144,
maxTokens: 65536,
},
{
id: "step-3.5-flash-2603",
name: "Step 3.5 Flash 2603",
reasoning: true,
input: ["text"],
cost: { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
contextWindow: 262144,
maxTokens: 65536,
},
],
},
},
},
}
Notes
- Through OpenClaw,
step-3.7-flashhandles both text and image inputs. Video is supported by StepFun's API but is not yet available as a model input type in OpenClaw. - Reasoning effort levels
low,medium, andhighare supported by Step 3.7. Since there is no non-reasoning mode for this model,/think offis treated aslow. - Only
stepfun-plancurrently exposesstep-3.5-flash-2603. - To review or change models, use
openclaw models listandopenclaw models set <provider/model>.
Related
-
Model providers, A summary of every provider, model reference, and failover logic.
-
Configuration reference, The complete configuration schema covering providers, models, and plugins.
-
Models CLI, Instructions for picking and setting up models.
-
StepFun Platform, Managing StepFun API keys and accessing their documentation.