Gemini 3 Pro Preview
qihang-ai/gemini-3-pro-preview · family gemini-pro · in: text, image, audio, video → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image audio video.
$1.29
Blended $/1M (3:1)
$0.57
Input $/1M
$3.43
Output $/1M
$4.00
1M in + 1M out
—
Cache read $/1M
#4454 of 7,714
Cheapest rank
- Provider
- QiHang (
qihang-ai) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 65,000 tokens
- Capabilities
- tools reasoning text image audio video
Same model, other providers
“Gemini 3 Pro Preview” is offered by 4 providers — cheapest-effective first. This one (QiHang) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| QiHang (this) | $0.57 | $3.43 | $1.29 | 1M |
| Databricks | $2 | $12 | $4.50 | 1M |
| Merge Gateway | $2 | $12 | $4.50 | 1M |
| AnyAPI | — | — | — | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at QiHang and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"gemini-3-pro-preview","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):