Gemini Deep Research Preview
deep-research-preview-04-2026An agentic model for autonomous multi-step research, synthesis, and cited reports.
Agentic model for autonomous multi-step research, synthesis, and cited reports
1M context1M context
Released2026-04-21
Relays0 sites
reasoningtool uselong context
Model information
- Model ID
- deep-research-preview-04-2026
- Context
- 1M
- Max input
- -
- Max output
- 65.5K
- Knowledge cutoff
- 2025-01
- Open weights
- Not supported
- License
- -
- Release date
- 2026-04-21
Input
Text: SupportedImage: SupportedAudio: SupportedVideo: SupportedPDF: SupportedFile: Supported
Output
Text: SupportedImage: SupportedAudio: Not supportedVideo: Not supported
API capabilities
Reasoning: SupportedTool call: SupportedStructured output: UnknownTemperature: Not supported
Google Official Pricing
CNYUpdated: 2026-10-04T22:55:11.583+08:00
Input
~¥13.379/ 1M tokens
Output
~¥80.272/ 1M tokens
Cache read
~¥1.338/ 1M tokens
Relay Comparison
Compare token, per-request, or per-second pricing by relay channel.
Unit: token prices are ¥ / 1M tokens; per-request and per-second rows use their shown unit
No prices are available for this model yet.
How should Gemini Deep Research Preview relay pricing be compared?
This Gemini Deep Research Preview pricing page compares official pricing with public prices from 0 listed AI gateways. Token prices are shown in CNY per 1M tokens, while per-request, per-second, and per-character rows use the unit shown in the table. Last updated: No clear update time.
- Data sources
- Public price catalogs, official pricing records, and monitoring results.
- Metric definitions
- Uptime means successful probe response rate, fake-rate signals possible model mismatch or abnormal output risk, and latency is average API response time.
- Risk note
- Relay gateways are third-party services. Pricing, billing, privacy, and stability can change; start with a small top-up and verify reliability before continued use.