OpenRouter | Google: Gemini 3.5 Flash
Type: MText; Context: 1049K tokens; Max output: 65500 tokens; Latency: 2620 ms; Throughput: 132 qps Google's most cost-effective video generation model, designed for high-volume applications and rapid iteration. Veo 3.1 Lite generates 720p and 1080p video from text or image prompts with native synch It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs.
Google's most cost-effective video generation model, designed for high-volume applications and rapid iteration. Veo 3.1 Lite generates 720p and 1080p video from text or image prompts with native synch
It is highly optimized for coding proficiency and parallel agentic execution loops, supporting text, image, video, audio, and PDF inputs.
Latency
2620ms
Throughput
132 QPS
Total Context
1000K
Max Output
65,500 tokens
Input Price
$0.08333/M
Output Price
$1.5/M
Model Type
MText
Parameter Size
-
Input Modality
text, image, video, file, audio
Output Modality
text
Inference Speed
165 token/s
Success Rate
-
Peak Concurrency
132 QPS
Release Date
5/19/2026
Pricing Mode
-
Free Tier
-
Supported Languages
-
SDK
OpenRouter SDK / OpenAI-compatible API
API Key Acquisition
OpenRouter dashboard API keys
Rate Limit
-
Example Code
import { OpenRouter } from "@openrouter/sdk"; const openrouter = new OpenRouter({ apiKey: "<OPENROUTER_API_KEY>"}); // Stream the response to get reasoning tokens in usageconst stream = await openrouter.chat.send({ model: "google/gemini-3.5-flash", messages: [ { role: "user", content: "How many r's are in the word 'strawberry'?" } ], stream: true}); let response = "";for await (const chunk of stream) { const content = chunk.choices[0]?.delta?.content; if (content) { response += content; process.stdout.write(content); } // Usage information comes in the final chunk if (chunk.usage) { console.log("\nReasoning tokens:", chunk.usage.reasoningTokens); }}User Reviews
0 verified user reviews
Loading reviews...