Calling GPT-6.1, Claude and Gemini APIs from mainland China
Use a ModelFold API key and the OpenAI-compatible base URL https://modelfold.ai/v1 to integrate supported GPT-6.1, Claude and Gemini models. Retrieve the exact API model ID before sending a request; curl and Python examples are below. Mainland connectivity varies by network and model availability, and is not an uptime guarantee.
Official sources checked:
Price snapshot updated:
Related guides
Current public prices
Pay as you go with prepaid credits. 200 credits = US$1. Credit charges round up to two decimal places; this is not USD rounding. Failed generations are not charged; a temporary hold may be released after failure. Review the final quote before submitting. Token rates are per one million tokens, input / output; video prices are starting prices for the listed configuration.
| Model | ModelFold USD | Official USD | Unit / configuration |
|---|---|---|---|
| Claude Haiku 5.5 | 0.072 in / 0.36 out | $0.1 / $0.5 (≤100,000 input tokens) | per 1M tokens |
| Claude Opus 5 | 2.40 in / 12.00 out | Not independently verified | per 1M tokens |
| Claude Opus 5.5 | 1.92 in / 9.60 out | $4 / $20 | per 1M tokens |
| Claude Sonnet 5 | 1.02 in / 5.13 out | Not independently verified | per 1M tokens |
| Claude Sonnet 5.5 | 0.96 in / 4.80 out | $2 / $10 | per 1M tokens |
| Gemini 3 Pro | 0.60 in / 4.20 out | Not independently verified | per 1M tokens |
| Gemini 3.1 Pro | 0.60 in / 4.20 out | Not independently verified | per 1M tokens |
| Gemini 3.6 Flash | 0.27 in / 1.35 out | Not independently verified | per 1M tokens |
| Gemini 3.7 Flash | 0.27 in / 1.35 out | Not independently verified | per 1M tokens |
| Gemini 3.8 Flash | 0.27 in / 1.35 out | Not independently verified | per 1M tokens |
| Gemini 4 Argon | 0.96 in / 4.80 out | Not independently verified | per 1M tokens |
| Gemini Omni 1.1 Flash | 0.024 in / 0.024 out | Not independently verified | per 1M tokens |
| GPT 6.1 Sol | 0.72 in / 3.60 out | $2 / $10 | per 1M tokens |
| GPT-6 Astra | 3.36 in / 16.80 out | $10 / $50 | per 1M tokens |
| GPT-6 Sol and Luna | 0.036 in / 0.18 out | $0.1 / $0.5 | per 1M tokens |
| Gemini 4 Carbon | 2.40 in / 12.00 out | Not independently verified | per 1M tokens |
| GPT-6.1 Terra | 1.20 in / 6.00 out | $1 / $5 | per 1M tokens |
| Gemini 3.1 Pro Preview | 2.40 in / 14.40 out | Not independently verified | per 1M tokens |
| Gemini 3.5 Flash Lite | 0.36 in / 3.00 out | Not independently verified | per 1M tokens |
| Gemini 3.1 Flash Lite | 0.30 in / 1.80 out | Not independently verified | per 1M tokens |
| Gemini 3.1 Flash Lite Preview | 0.30 in / 1.80 out | Not independently verified | per 1M tokens |
| Gemini 3 Flash Preview | 0.60 in / 3.60 out | Not independently verified | per 1M tokens |
| Gemini 2.5 Flash | 0.36 in / 3.00 out | Not independently verified | per 1M tokens |
| Gemini 2.5 Flash Lite | 0.12 in / 0.48 out | Not independently verified | per 1M tokens |
| GPT-6 Astra Pro | 12.00 in / 60.00 out | Not independently verified | per 1M tokens |
| GPT-6 Luna Pro | 0.12 in / 0.60 out | Not independently verified | per 1M tokens |
| Gemini 3.1 Pro Preview Custom Tools | 2.40 in / 14.40 out | Not independently verified | per 1M tokens |
| Gemini 4 Hydrogen | 1.80 in / 9.00 out | Not independently verified | per 1M tokens |
| GPT-6.1 Terra Pro | 1.20 in / 6.00 out | Not independently verified | per 1M tokens |
| GPT-6.1 Sol Pro | 2.40 in / 12.00 out | Not independently verified | per 1M tokens |
| GPT-6 Sol Pro | 2.40 in / 12.00 out | Not independently verified | per 1M tokens |
API examples
curl https://modelfold.ai/v1/models -H "Authorization: Bearer $MODELFOLD_API_KEY"curl https://modelfold.ai/v1/chat/completions \
-H "Authorization: Bearer $MODELFOLD_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"claude-haiku-5-5","messages":[{"role":"user","content":"Hello"}]}'import os
from openai import OpenAI
client = OpenAI(api_key=os.environ["MODELFOLD_API_KEY"], base_url="https://modelfold.ai/v1")
response = client.chat.completions.create(
model="claude-haiku-5-5",
messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)Examples are illustrative and were not sent to a paid model. Install the OpenAI Python SDK separately. Video requests are asynchronous; follow the model documentation for polling and required parameters.
Frequently asked questions
Is ModelFold always the cheapest?
No. Compare the same model, context, cache mode and input/output mix. Final quotes and actual usage determine the charge.
Are failed generations charged?
Failed generations are not charged. A temporary reservation is not a final charge; check account logs for settlement.
Where do I find the correct model ID?
Use GET /v1/models and the linked model documentation. A website page slug is not always the API model ID.
