GoogleLLM
Gemini 3.5 Flash API
google/gemini-3.5-flashGemini 3.5 Flash multimodal reasoning model through the Hermes chat API.
- 1.05M context
- Tools
- Vision
- JSON
- Audio
Run Gemini 3.5 Flash in the playground
Send a chat request with your account and see the exact token charge. Code needs an API key.
Parameters
Request preview
{"model": "google/gemini-3.5-flash","messages": [],"stream": true,"max_tokens": 1024}The web playground sends this body with your signed-in session. From code, send the same body with an API key.
Result
Send a message to run Gemini 3.5 Flash with your account.
Usage and charge appear here after a reply.
Gemini 3.5 Flash pricing
USD per 1M tokens. The tier is chosen by the prompt size of each request.
- ReserveWhen a request is accepted, Hermes reserves credits for the estimated prompt plus max_tokens of output (8,192 when you set none). Set max_tokens to keep the reservation small.
- SettleWhen the response finishes, the reservation is replaced by the exact charge from the usage the model reports: prompt tokens at the input rate, cached prompt tokens at the cache-read rate, completion tokens at the output rate. The remainder is released immediately.
- FailuresIf the model rejects the request nothing is charged. If a stream is interrupted after tokens were generated, the generated text is estimated and charged.
What Gemini 3.5 Flash can do
Google's model card describes Gemini 3.5 Flash as a multimodal model based on Gemini 3 Flash, with thinking levels that balance quality, cost and latency. Google describes text, image, audio and video input on its own platform; those native input types and controls should not be assumed to work identically through Hermes.
The Hermes catalog lists google/gemini-3.5-flash with a 1,048,576-token context, tools, vision, audio, streaming and structured outputs. It does not list a reasoning control for this route. Check the current API documentation, model status and price before relying on a specific input or setting.
Use cases
Analyze visual material
Pair a question with a supported image input.
Extract structured information
Request structured output and validate the returned data.
Work with long text
Analyze documents within the listed context while allowing space for the response.
Call Gemini 3.5 Flash from code
Any OpenAI SDK works: set the base URL and your Hermes key.
- 1
Create an API key
In the dashboard, with the chat:create scope. API keys - 2
Point your SDK at Hermes
Base URLhttps://api.hermes-ai.net/api/v1 - 3
Send a chat completion
POST /chat/completionswithgoogle/gemini-3.5-flash
Code examples
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",
"messages": [{"role": "user", "content": "Say hello in one sentence."}],
"max_tokens": 200
}'Request
POST https://api.hermes-ai.net/api/v1/chat/completions API key with the chat:create scope, or your signed-in session.
| Field | Type | Notes |
|---|---|---|
| model | string | google/gemini-3.5-flash |
| messages | array | OpenAI chat messages: system, user, assistant and tool roles; text and image_url parts. |
| stream | boolean | Server-sent events with a final usage chunk. |
| max_tokens | integer | Output cap; also sizes the credit reservation. |
| tools / tool_choice | array / object | Function tools only. |
| response_format | object | JSON mode and JSON schema where the model supports it. |
| temperature, top_p, stop, seed, reasoning_effort | Passed through unchanged. |
Response
| Field | Notes |
|---|---|
| choices[].message / delta | The OpenAI chat completion shape. |
| usage | prompt_tokens, completion_tokens and prompt_tokens_details.cached_tokens as reported by the model. |
| hermes.charged_micros | Exact charge in USD micro-units (JSON responses). Streams expose it on GET /api/v1/chat/requests. |
| x-hermes-request | Request id header, also used in the billing ledger. |
| error.code | Documented Hermes error code; branch on it, not on the message. |
Gemini 3.5 Flash API FAQ
Answers built from the model's catalog entry and the Hermes AI API contract.
Are all Google-native capabilities available here?
Not necessarily. The manufacturer model card covers Google's platforms; the Hermes catalog and API documentation define this route's supported inputs and controls.
What is the Gemini 3.5 Flash API on Hermes AI?
Gemini 3.5 Flash 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.
What is the context window of Gemini 3.5 Flash?
1,048,576 tokens, shared by the prompt and the output.
Does Gemini 3.5 Flash support vision, tools and JSON output?
Supported: Tools, Vision, JSON and Audio. Not supported: Reasoning. Streaming works with stream: true.
How is Gemini 3.5 Flash 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?
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 as the model. Chat completions, streaming, tools and JSON output work unchanged.
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?
Create one under API keys in the dashboard with the chat:create scope, then add credits on the Billing page.