Gemini 3 Pro Preview
gemini-3-pro-preview
Gemini 3 Pro Preview is a text model from Google. The snapshot records a release date of 2025-11-18. Context window: 1.04858M tokens. Maximum output: 65.536K tokens. Input: text, images, audio, video, PDF. Output: text. Capabilities recorded: reasoning, tool calls.
Directory snapshot 2026-10-26 · Chinese dossier: 完整中文页
Official list price
CNY / 1M TOKENSThe snapshot does not record an official list price for this model. We do not estimate one. Ask the provider or read the relay's own pricing page before budgeting.
Relay coverage
24 SITES24 sites in our public directory listed this model ID in the 2026-10-26 snapshot. Listed relay price range: ¥0.08–¥37.5 per 1M input tokens. A listing means the model appeared on the site's public model list; it is not proof that the site serves the genuine model.
| Site | Domain | Relay price / 1M | Verification |
|---|---|---|---|
| 小瑞API | xiaoruiapi.cc | ¥0.08 | — |
| LinoRoute | linoroute.com | ¥0.29412–¥1.05884 | personal |
| 元初AI | ai.yuanc.icu | ¥0.4 | enterprise |
| SpiderMan-API | spiderman-api.com | ¥0.5 | — |
| API快连 | apikl.ai | ¥0.6–¥1.2 | enterprise |
| luchikey | sub2api.luchikey.com | ¥0.7 | enterprise |
| token2u | token2u.ai | ¥0.798 | enterprise |
| UniLink | api.unilink.work | ¥0.8–¥2 | personal |
| AutoRouter | autorouter.net | ¥0.8 | personal |
| JBB金贝贝 | jbbt.cc | ¥1–¥37.5 | enterprise |
| Super API | superapi.buzz | ¥1.1–¥2.8 | — |
| Volt | voltapi.ai | ¥1.2 | personal |
| AIGC Token | aigc-token.com | ¥2–¥6 | enterprise |
| VovoKey｜启界 | vovokey.com | ¥2–¥2.1 | enterprise |
| RPG8 | api.rpg8.cn | ¥2 | — |
| 像素群岛 | api.shiyutv.cn | ¥2 | — |
| A6api | a6api.com | ¥2.31066 | enterprise |
| niccom | niccom.com.cn | ¥2.34 | enterprise |
| OmniaKey | omniakey.com | ¥2.48 | enterprise |
| xAIx | api.xaix.me | ¥3–¥11.2 | — |
| RunAPI | runapi.host | ¥5.805–¥8.7075 | enterprise |
| PackyCode | packyapi.ai | ¥6 | enterprise |
| Modelsell | modelsell.com | ¥6.8–¥9.52 | — |
| ePhone AI | ephone.ai | ¥7.42–¥14 | — |
How to verify this model on a relay
THREE STEPS- Send a short request to the relay and read the
modelfield in the response. It must match the ID you sent; a different ID is a mapping, not necessarily a substitution. - Run the same prompt against a known-good endpoint and compare prompt-token counts. A large, repeatable gap points at a different tokenizer or a different backend.
- Run the seven checks. Billing, context retention, error shape, parameter compliance, tools, and streaming each produce evidence you can quote.
Same publisher
GoogleQuestions
FAQWhat is the context window of Gemini 3 Pro Preview?
The snapshot records 1,048,576 tokens.
How much does Gemini 3 Pro Preview cost?
The snapshot records no official price. 24 relay sites listed the model, but relay prices are not official prices.
Is a relay really serving Gemini 3 Pro Preview?
A model ID in a response is not proof. The seven-check detection compares tokenizer ratios, billing, error shape, parameter compliance, tools, and streaming against the advertised family. Run it on a key you can afford to spend, and treat one run as a spot check, not 24/7 monitoring.
Specifications and prices come from the 2026-10-26 public directory snapshot. We do not publish IQ scores or structured-output claims for models where we have no reliable data.