Models available
9
Vendor hub
StepFun models on ChinaAPI
Every model below is reachable with one ChinaAPI key and one OpenAI-compatible base URL. The same key works for every vendor in the catalog, so adding a model is a configuration change rather than a new account.
Availability
Sign-up is the blocker, not the model.
Chinese model providers run their own developer consoles, but registration, invoicing and identity verification are built for mainland-China entities and phone numbers. Developers outside that boundary frequently cannot finish sign-up at all, whatever the model can do.
ChinaAPI puts these models behind one gateway account, so the open questions become price and payload shape instead of eligibility. This page states what is available and what it costs; it makes no quality or ranking claim, because no published benchmark evidence supports one yet.
Model families
StepFun
Base URL
https://api.chinaapi.ai/v1
Account requirement
No mainland-China account or phone number.
Catalog
StepFun models and published USD prices
Rows are generated from the ChinaAPI catalog, not typed by hand. Follow a model link for the full specification, request payload and localized pricing.
| Model | Family | Task type | Context | Price (USD) |
|---|---|---|---|---|
| step-3.5-flash | StepFun | Text | 256K | $0.1/M input, $0.3/M output tokens |
| step-3.5-flash-2603 | StepFun | Text | 256K | $0.1/M input, $0.3/M output tokens |
| step-3.7-flash | StepFun | Text and image input | 256K | $0.2/M input, $1.15/M output tokens |
| step-5-preview | StepFun | Text, image and video input | 1M | $1/M input, $2.7/M output tokens |
| step-tts-2 | StepFun | Text to speech | 1,000 characters/request | $0.4148 per 10k characters |
| stepaudio-2-asr-pro | StepFun | Speech to text | — | $0.2963 per audio hour |
| stepaudio-2.5-asr | StepFun | Speech to text | Streaming audio input | $0.022 per audio hour |
| stepaudio-2.5-chat | StepFun | Audio and text | — | $1.5/M input, $3.5/M output tokens |
| stepaudio-2.5-tts | StepFun | Text to speech | 1,000 characters/request | $0.85 per 10k characters |
Token prices are shown as input and output per one million tokens. Media prices are shown per published billing unit.
Standard model rates follow providers' international list prices at 100%; some models have a separate Paid rate after the first top-up. Live pricing is authoritative.
The displayed media rate may include a service margin covering provider input/output billing, payment processing, chargeback exposure, and operations. Any margin is included in the displayed rate and is not added separately.
Price notes
Some rates above are conditional.
The catalog records a caveat for the models below. The rate in the table is the current published rate, not a permanent one; check live pricing before you depend on it.
step-5-preview
Prompt cache reads are billed at $0.05 per 1M tokens. The standard input and output rates above are the live gateway book prices.
Quickstart
Copy-paste API request.
Swap the model identifier for any row in the table above. Nothing else in the request changes between vendors.
Store the key in an environment variable and keep it out of source control.
curl -X POST https://api.chinaapi.ai/v1/chat/completions \
-H "Authorization: Bearer $CHINAAPI_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "step-3.5-flash",
"messages": [{"role": "user", "content": "Hello from ChinaAPI"}]
}'Other vendor hubs
Same key, same base URL, a different vendor catalog.
Sources and updates
Model list, context values and USD prices on this page are generated from the ChinaAPI model catalog on August 10, 2026. Live pricing in the dashboard is authoritative.