GoogleLLM
Gemini 3.5 Flash Lite API
google/gemini-3.5-flash-lite-saverGemini 3.5 Flash-Lite through the Hermes chat model catalog.
- 1.05M context
- 工具
- 视觉
- 音频
- 省钱通道
在 Playground 中运行 Gemini 3.5 Flash Lite
Send a chat request with your account and see the exact token charge. Code needs an API key.
参数
请求预览
{"model": "google/gemini-3.5-flash-lite-saver","messages": [],"stream": true,"max_tokens": 1024}网页 Playground 使用你的登录会话发送此请求体。在代码中请使用 API Key 发送相同内容。
结果
发送一条消息,用你的账号运行 Gemini 3.5 Flash Lite。
收到回复后,这里会显示用量和扣费。
Gemini 3.5 Flash Lite 价格
美元 / 百万 token。按每次请求的提示词长度选择档位。
- Reserve请求被接受时,Hermes 会按估算的提示词长度加上 max_tokens(未设置时为 8,192)预留额度。设置 max_tokens 可以减少预留。
- Settle响应结束后,按模型返回的实际用量结算:提示词 token 按输入价、命中缓存的 token 按缓存读取价、输出 token 按输出价,预留的剩余部分立即释放。
- Failures模型拒绝请求时不收费。流式输出在已生成内容后中断时,会按已生成文本估算并扣费。
Gemini 3.5 Flash Lite 能做什么
Google positions 3.5 Flash-Lite for high-volume, latency-sensitive work and agentic workflows. See the Google documentation for the native model and its limitations. Google-native modalities, thinking controls and hosted tools may differ from the Hermes channel.
The Hermes catalog lists google/gemini-3.5-flash-lite with a 1,048,576-token context, tools and streaming. Vision is listed in the current Hermes catalog. Check the exact channel's other capability flags, price and availability before sending a request; leave room for output within the context limit.
使用场景
Analyze text
Apply the model to documents or questions suited to its scale and latency.
Integrate function tools
Handle tool calls in your application and validate their results.
Evaluate on your data
Compare quality, latency and cost against your actual workload.
用代码调用 Gemini 3.5 Flash Lite
任意 OpenAI SDK 都可用:设置 base URL 和你的 Hermes Key。
- 1
创建 API Key
In the dashboard, with the chat:create scope. API 密钥 - 2
Point your SDK at Hermes
Base URLhttps://api.hermes-ai.net/api/v1 - 3
发送对话补全请求
POST /chat/completionswithgoogle/gemini-3.5-flash-lite-saver
代码示例
Set HERMES_API_KEY in your environment.
export HERMES_API_KEY=your_api_keycurl https://api.hermes-ai.net/api/v1/chat/completions \
-H "Authorization: Bearer $HERMES_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "google/gemini-3.5-flash-lite-saver",
"messages": [{"role": "user", "content": "Say hello in one sentence."}],
"max_tokens": 200
}'请求
POST https://api.hermes-ai.net/api/v1/chat/completions 带 chat:create 权限的 API Key,或已登录会话。
| 字段 | 类型 | 说明 |
|---|---|---|
| model | string | google/gemini-3.5-flash-lite-saver |
| messages | array | OpenAI 对话消息:system、user、assistant、tool 角色;text 和 image_url 内容块。 |
| stream | boolean | SSE 流式输出,最后一个事件包含 usage。 |
| max_tokens | integer | 输出上限,同时决定预留额度。 |
| tools / tool_choice | array / object | 仅支持 function 工具。 |
| response_format | object | 模型支持时可用 JSON 模式和 JSON schema。 |
| temperature, top_p, stop, seed, reasoning_effort | 原样透传。 |
响应
| 字段 | 说明 |
|---|---|
| choices[].message / delta | OpenAI chat completion 结构。 |
| usage | 模型返回的 prompt_tokens、completion_tokens 和 prompt_tokens_details.cached_tokens。 |
| hermes.charged_micros | 精确扣费(微美元,JSON 响应)。流式请求可在 GET /api/v1/chat/requests 查看。 |
| x-hermes-request | 请求 id 响应头,账单流水中使用同一 id。 |
| error.code | 文档中的 Hermes 错误码;请按错误码而非消息文本分支。 |
Gemini 3.5 Flash Lite API 常见问题
Answers built from the model's catalog entry and the Hermes AI API contract.
Can I send the same multimodal inputs as Google's native API?
Not necessarily. Google describes its own platforms; consult the selected Hermes channel's capability flags and request documentation before sending images, audio or video.
What is the Gemini 3.5 Flash Lite API on Hermes AI?
Gemini 3.5 Flash Lite by Google is served through the OpenAI-compatible chat completions endpoint, https://api.hermes-ai.net/api/v1/chat/completions, with the model ID google/gemini-3.5-flash-lite.
What is the context window of Gemini 3.5 Flash Lite?
1,048,576 tokens, shared by the prompt and the output.
Does Gemini 3.5 Flash Lite support vision, tools and JSON output?
Supported: 工具, 视觉, JSON 和 音频. Not supported: 推理. Streaming works with stream: true.
How is Gemini 3.5 Flash Lite billed?
Per token, from prepaid credits. When a request is accepted, credits are reserved for the estimated prompt plus max_tokens of output (8,192 when you set none); when it finishes, the exact charge is taken from the usage the model reports and the rest is released. A rejected request is not charged. Rates are in the pricing table.
Can I use the OpenAI SDK with Gemini 3.5 Flash Lite?
Yes. Set the base URL to https://api.hermes-ai.net/api/v1 and use your Hermes API key; send google/gemini-3.5-flash-lite as the model. Chat completions, streaming, tools and JSON output work unchanged.
What is the Gemini 3.5 Flash Lite saver channel?
The same model on a lower-priority upstream route, with its own model ID (google/gemini-3.5-flash-lite-saver) and its own price. Pick it in the variant switch on this page.
What happens when I hit a rate limit?
Too many requests per minute return 429 RATE_LIMITED and too many in flight return 429 CONCURRENCY_LIMITED. If the model provider rate limits, you get 429 UPSTREAM_RATE_LIMITED and nothing is charged. Retry with backoff.
How do I get an API key for Gemini 3.5 Flash Lite?
Create one under API 密钥 in the dashboard with the chat:create scope, then add credits on the Billing page.