Gemini 3.8 Flash API pricing and integration guide
Review Gemini 3.8 Flash's 5x reference rate, documented 1M context and image support for frequent coding and agent tasks.
Current prices and model reference
- Model ID
gemini-3.8-flash- Documented context
- 1M
- Documented image input
- Supported
Live pricing or availability cannot be confirmed right now. Check the model catalog before making a request.
Prices are in CNY. A 1× multiplier equals CNY 0.4 per million input tokens. Output and cache charges follow the billing configuration; your usage record is authoritative.
View the full live pricing catalogWhen to consider this model
Compare code changes, screenshot understanding and tool results on the same tasks. Measure acceptance, latency and total cost against fixed criteria.
How to evaluate it
Use the exact ID gemini-3.8-flash. Confirm live discovery exposes it before testing short text, one image and multi-turn tool tasks.
What to check before integration
The new Feishu table lists 5x, or CNY 2 per million input tokens, with 1M context and image support. Check this exact ID in live discovery; a reference listing does not establish availability or equivalence to another Gemini version.
Client configuration
In a client supporting a custom API endpoint, enter this base URL and model ID with your own API key. Select the protocol described in the client tutorial and validate a short request first.
Base URL: https://api.llm-token.cn/v1
Model ID: gemini-3.8-flash