--- title: Gemini 3 Flash | Runware Docs url: https://runware.ai/docs/models/google-gemini-3-flash description: Advanced multimodal text and reasoning model --- # Gemini 3 Flash Gemini 3 Flash is Google’s flagship multimodal language model that processes text alongside images, audio, video, code, and documents. It offers high-performance reasoning, complex instruction following, and deep contextual understanding for a wide range of tasks across language, analysis, and problem solving. - **ID**: `google:gemini@3-flash` - **Status**: live - **Creator**: Google - **Release Date**: December 17, 2025 - **Capabilities**: Text to Text, Image to Text, Video to Text, Audio to Text, Caption ## Pricing - **Input tokens (text, image, video)**: `$0.5 / 1M` - **Input tokens (audio)**: `$1 / 1M` - **Output tokens**: `$3 / 1M` ## Request Parameters **API Options** Platform-level options for task execution and delivery. ### [taskType](https://runware.ai/docs/models/google-gemini-3-flash#request-tasktype) - **Type**: `string` - **Required**: true - **Value**: `textInference` Identifier for the type of task being performed ### [taskUUID](https://runware.ai/docs/models/google-gemini-3-flash#request-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID v4 identifier for tracking tasks and matching async responses. Must be unique per task. ### [webhookURL](https://runware.ai/docs/models/google-gemini-3-flash#request-webhookurl) - **Type**: `string` - **Format**: `URI` Specifies a webhook URL where JSON responses will be sent via HTTP POST when generation tasks complete. For batch requests with multiple results, each completed item triggers a separate webhook call as it becomes available. **Learn more** (1 resource): - [Webhooks](https://runware.ai/docs/platform/webhooks) (platform) ### [deliveryMethod](https://runware.ai/docs/models/google-gemini-3-flash#request-deliverymethod) - **Type**: `string` - **Default**: `sync` Determines how the API delivers task results. **Allowed values**: - `sync` Returns complete results directly in the API response. - `async` Returns an immediate acknowledgment with the task UUID. Poll for results using getResponse. - `stream` Streams results token-by-token as they are generated. **Learn more** (1 resource): - [Task Polling](https://runware.ai/docs/platform/task-polling) (platform) ### [includeCost](https://runware.ai/docs/models/google-gemini-3-flash#request-includecost) - **Type**: `boolean` - **Default**: `false` Include task cost in the response. ### [includeUsage](https://runware.ai/docs/models/google-gemini-3-flash#request-includeusage) - **Type**: `boolean` - **Default**: `false` Include token usage statistics in the response. ### [numberResults](https://runware.ai/docs/models/google-gemini-3-flash#request-numberresults) - **Type**: `integer` - **Min**: `1` - **Max**: `4` - **Default**: `1` Number of results to generate. Each result uses a different seed, producing variations of the same parameters. **Inputs** Input resources for the task (images, audio, etc). These must be nested inside the \`inputs\` object. ### [audios](https://runware.ai/docs/models/google-gemini-3-flash#request-inputs-audios) - **Path**: `inputs.audios` - **Type**: `array of strings` Array of audio inputs (UUID, URL, or Base64). ### [documents](https://runware.ai/docs/models/google-gemini-3-flash#request-inputs-documents) - **Path**: `inputs.documents` - **Type**: `array of strings` Array of document inputs (UUID, URL, or Base64). ### [images](https://runware.ai/docs/models/google-gemini-3-flash#request-inputs-images) - **Path**: `inputs.images` - **Type**: `array of strings` Array of image inputs (UUID, URL, Data URI, or Base64). ### [videos](https://runware.ai/docs/models/google-gemini-3-flash#request-inputs-videos) - **Path**: `inputs.videos` - **Type**: `array of strings` Array of video inputs (UUID, URL, or Base64). **Generation Parameters** Core parameters for controlling the generated content. ### [model](https://runware.ai/docs/models/google-gemini-3-flash#request-model) - **Type**: `string` - **Required**: true - **Value**: `google:gemini@3-flash` Identifier of the model to use for generation. **Learn more** (3 resources): - [Text To Image: Model Selection The Foundation Of Generation](https://runware.ai/docs/guides/text-to-image#model-selection-the-foundation-of-generation) (guide) - [Image Inpainting: Model Specialized Inpainting Models](https://runware.ai/docs/guides/image-inpainting#model-specialized-inpainting-models) (guide) - [Image Outpainting: Other Critical Parameters](https://runware.ai/docs/guides/image-outpainting#other-critical-parameters) (guide) ### [seed](https://runware.ai/docs/models/google-gemini-3-flash#request-seed) - **Type**: `integer` - **Min**: `0` - **Max**: `4294967295` Random seed for reproducible generation. When not provided, a random seed is generated in the unsigned 32-bit range. ### [messages](https://runware.ai/docs/models/google-gemini-3-flash#request-messages) - **Path**: `messages.role` - **Type**: `array of objects (2 properties)` - **Required**: true Array of chat messages forming the conversation context. #### [role](https://runware.ai/docs/models/google-gemini-3-flash#request-messages-role) - **Path**: `messages.role` - **Type**: `string` - **Required**: true The role of the message author. **Allowed values**: `user` `assistant` #### [content](https://runware.ai/docs/models/google-gemini-3-flash#request-messages-content) - **Path**: `messages.content` - **Type**: `string` - **Required**: true - **Min**: `1` The text content of the message. **Settings** Technical parameters to fine-tune the inference process. These must be nested inside the \`settings\` object. ### [systemPrompt](https://runware.ai/docs/models/google-gemini-3-flash#request-settings-systemprompt) - **Path**: `settings.systemPrompt` - **Type**: `string` - **Min**: `1` - **Max**: `200000` System-level instruction that guides the model's behavior and output style across the entire generation. ### [temperature](https://runware.ai/docs/models/google-gemini-3-flash#request-settings-temperature) - **Path**: `settings.temperature` - **Type**: `float` - **Min**: `0` - **Max**: `2` - **Step**: `0.01` - **Default**: `1` Controls randomness in generation. Lower values produce more deterministic outputs, higher values increase variation and creativity. ### [topP](https://runware.ai/docs/models/google-gemini-3-flash#request-settings-topp) - **Path**: `settings.topP` - **Type**: `float` - **Min**: `0` - **Max**: `1` - **Step**: `0.01` - **Default**: `0.95` Nucleus sampling parameter that controls diversity by limiting the probability mass. Lower values make outputs more focused, higher values increase diversity. ### [maxTokens](https://runware.ai/docs/models/google-gemini-3-flash#request-settings-maxtokens) - **Path**: `settings.maxTokens` - **Type**: `integer` - **Min**: `1` - **Max**: `65536` - **Default**: `4096` Maximum number of tokens to generate in the response. ### [stopSequences](https://runware.ai/docs/models/google-gemini-3-flash#request-settings-stopsequences) - **Path**: `settings.stopSequences` - **Type**: `array of strings` - **Min**: `1` - **Max**: `50` Array of sequences that will cause the model to stop generating further tokens when encountered. ### [thinkingLevel](https://runware.ai/docs/models/google-gemini-3-flash#request-settings-thinkinglevel) - **Path**: `settings.thinkingLevel` - **Type**: `string` - **Default**: `high` Controls the depth of internal reasoning the model performs before generating a response. **Allowed values**: `minimal` `low` `medium` `high` ## Response Parameters ### [taskType](https://runware.ai/docs/models/google-gemini-3-flash#response-tasktype) - **Type**: `string` - **Required**: true - **Value**: `textInference` Type of the task. ### [taskUUID](https://runware.ai/docs/models/google-gemini-3-flash#response-taskuuid) - **Type**: `string` - **Required**: true - **Format**: `UUID v4` UUID of the task. ### [text](https://runware.ai/docs/models/google-gemini-3-flash#response-text) - **Type**: `string` - **Required**: true Generated text content. ### [cost](https://runware.ai/docs/models/google-gemini-3-flash#response-cost) - **Type**: `float` Task cost in USD. Present when `includeCost` is set to `true` in the request. ### [finishReason](https://runware.ai/docs/models/google-gemini-3-flash#response-finishreason) - **Type**: `string` - **Required**: true The reason why the model stopped generating tokens. **Possible values**: `stop` `length` `content_filter` `unknown` ### [usage](https://runware.ai/docs/models/google-gemini-3-flash#response-usage) - **Path**: `usage.promptTokens` - **Type**: `object (4 properties)` - **Required**: true Token usage statistics for the request. #### [promptTokens](https://runware.ai/docs/models/google-gemini-3-flash#response-usage-prompttokens) - **Path**: `usage.promptTokens` - **Type**: `integer` - **Required**: true - **Min**: `0` Number of tokens in the input prompt. #### [completionTokens](https://runware.ai/docs/models/google-gemini-3-flash#response-usage-completiontokens) - **Path**: `usage.completionTokens` - **Type**: `integer` - **Required**: true - **Min**: `0` Number of tokens generated in the response. #### [totalTokens](https://runware.ai/docs/models/google-gemini-3-flash#response-usage-totaltokens) - **Path**: `usage.totalTokens` - **Type**: `integer` - **Required**: true - **Min**: `0` Total number of tokens used (prompt + completion). #### [thinkingTokens](https://runware.ai/docs/models/google-gemini-3-flash#response-usage-thinkingtokens) - **Path**: `usage.thinkingTokens` - **Type**: `integer` - **Min**: `0` Number of tokens used for internal reasoning. Billed separately. ## Examples ### Crimson Night Market Puzzle (Image to Text) **Request**: ```json { "taskType": "textInference", "taskUUID": "dc5de2d2-c9ed-4153-840f-b47ef0ed368b", "model": "google:gemini@3-flash", "seed": 37, "settings": { "temperature": 0.42, "topP": 0.9, "maxTokens": 300, "thinkingLevel": "medium", "systemPrompt": "You are a precise visual reasoning assistant. Ground every conclusion in details visible in the image and avoid inventing facts." }, "inputs": { "images": [ "https://assets.runware.ai/assets/inputs/86f8954c-d52b-483e-8db5-2b5cea99e255.jpg" ] }, "messages": [ { "role": "user", "content": "Analyze the image carefully. First list the key visible clues exactly as seen, including text, numbers, object positions, and the clock time. Then answer this question: which crate is safest to load onto the last ferry, and why? Keep the final answer under 120 words." } ] } ``` **Response**: ```json { "taskType": "textInference", "taskUUID": "dc5de2d2-c9ed-4153-840f-b47ef0ed368b", "text": "Based on the visual evidence:\n\n**Key Clues:**", "seed": 37, "cost": 0.00147, "finishReason": "length", "thoughtSignature": "[REDACTED]" } ``` --- ### Storm-Battered Lighthouse Logbook (Caption) **Request**: ```json { "taskType": "textInference", "taskUUID": "9ce1e395-ed82-4bd2-b224-c1e460e800f4", "model": "google:gemini@3-flash", "seed": 80140, "settings": { "systemPrompt": "You are a precise multimodal captioning assistant. Base the caption only on visible evidence, making careful and plausible inferences without overstating certainty.", "temperature": 0.72, "topP": 0.9, "maxTokens": 220, "thinkingLevel": "medium" }, "inputs": { "images": [ "https://assets.runware.ai/assets/inputs/05589366-3499-45ae-881f-27ce2ca7c8b0.jpg" ] }, "messages": [ { "role": "user", "content": "Write a vivid 2-3 sentence caption for this image as if it were displayed in a maritime museum. Identify the main objects, infer what may have happened recently, and mention at least two visible clues that support the inference." } ] } ``` **Response**: ```json { "taskType": "textInference", "taskUUID": "9ce1e395-ed82-4bd2-b224-c1e460e800f4", "text": "Resting on a weathered wooden sill", "seed": 80140, "cost": 0.00122, "finishReason": "length", "usage": { "promptTokens": 1138, "completionTokens": 216, "totalTokens": 1354, "completionTokensDetails": { "reasoningTokens": 209 }, "costBreakdown": { "tokens": { "prompt": { "modalities": [ { "modality": "TEXT", "tokens": 74, "cost": 0.000037, "costDisplay": "0.000037" }, { "modality": "IMAGE", "tokens": 1064, "cost": 0.000532, "costDisplay": "0.000532" } ], "billableTokens": 1138, "cost": 0.000569, "costDisplay": "0.000569" }, "cache": { "billableTokens": 0, "cost": 0, "costDisplay": "0.000000" }, "completion": { "billableTokens": 216, "textTokens": 7, "reasoningTokens": 209, "cost": 0.000648, "costDisplay": "0.000648" } }, "features": { "search": { "count": 0, "cost": 0, "costDisplay": "0.000000" }, "maps": { "count": 0, "cost": 0, "costDisplay": "0.000000" } }, "total": 0.001217, "totalDisplay": "0.001217" } }, "thoughtSignature": "[REDACTED]" } ``` --- ### Storm-Damaged Harbor Inspection Frame (Video to Text) **Request**: ```json { "taskType": "textInference", "taskUUID": "7b395ae6-9486-4ead-9314-33c45001da27", "model": "google:gemini@3-flash", "seed": 74218, "settings": { "systemPrompt": "You are a meticulous infrastructure inspection assistant. Describe only observable evidence, avoid speculation, and organize findings clearly for operations staff.", "temperature": 0.34, "topP": 0.9, "maxTokens": 900, "thinkingLevel": "medium" }, "inputs": { "videos": [ "https://assets.runware.ai/assets/inputs/7f2503ba-1274-47da-af00-86c07567d2f1.mp4" ] }, "messages": [ { "role": "user", "content": "Analyze this harbor inspection video for emergency response planning. Provide: 1) a concise scene summary, 2) a bullet list of visible damage, 3) immediate safety hazards, 4) the top 3 repair priorities in order, and 5) a final severity rating from Low, Moderate, High, or Critical. Base your answer only on what is visible in the video and note any uncertainty clearly." } ] } ``` **Response**: ```json { "taskType": "textInference", "taskUUID": "7b395ae6-9486-4ead-9314-33c45001da27", "text": "This harbor inspection report is based on the provided video footage:\n\n### 1. Scene Summary\nThe scene depicts a small, weathered harbor during overcast, choppy conditions. The infrastructure includes a wooden pier, a small utility shed, and a red cylindrical lighthouse. A fishing boat is docked at the end of the pier, where two workers in high-visibility rain gear are assessing the situation.\n\n### 2. Visible Damage\n* **Fishing Boat:** A large structural breach is visible on the starboard side of the hull/deck area.\n* **Pier Walkway:** Multiple wooden planks are missing or broken, creating significant gaps in the walking surface.\n* **Pier Railings:** Safety railings are missing or have been removed along large sections of the pier.\n* **General Weathering:** Significant corrosion is visible on the lighthouse exterior and the metal siding of the utility shed.\n* **Debris:** Loose crates and coiled ropes are scattered across the pier, potentially obstructing movement.\n\n### 3. Immediate Safety Hazards\n* **Fall Hazard:** Missing planks on the pier walkway present a high risk of injury or falling into the water.\n* **Drowning Risk:** The lack of perimeter railings combined with wet, slippery surfaces increases the risk of personnel falling overboard.\n* **Vessel Sinking:** The large hole in the boat's hull poses an immediate risk of the vessel taking on water and sinking (confirmed by dialogue regarding the need for pumps).\n\n### 4. Top 3 Repair Priorities\n1. **Vessel Stabilization:** Patch the hull breach", "seed": 74218, "cost": 0.00308, "finishReason": "length", "usage": { "promptTokens": 644, "completionTokens": 895, "totalTokens": 1539, "completionTokensDetails": { "reasoningTokens": 570 }, "costBreakdown": { "tokens": { "prompt": { "modalities": [ { "modality": "AUDIO", "tokens": 152, "cost": 0.000152, "costDisplay": "0.000152" }, { "modality": "TEXT", "tokens": 108, "cost": 0.000054, "costDisplay": "0.000054" }, { "modality": "VIDEO", "tokens": 384, "cost": 0.000192, "costDisplay": "0.000192" } ], "billableTokens": 644, "cost": 0.000398, "costDisplay": "0.000398" }, "cache": { "billableTokens": 0, "cost": 0, "costDisplay": "0.000000" }, "completion": { "billableTokens": 895, "textTokens": 325, "reasoningTokens": 570, "cost": 0.002685, "costDisplay": "0.002685" } }, "features": { "search": { "count": 0, "cost": 0, "costDisplay": "0.000000" }, "maps": { "count": 0, "cost": 0, "costDisplay": "0.000000" } }, "total": 0.003083, "totalDisplay": "0.003083" } }, "thoughtSignature": "[REDACTED]" } ``` --- ### Rainy Night Market Analysis (Image to Text) **Request**: ```json { "taskType": "textInference", "taskUUID": "474e2fda-f280-4785-a9af-021b3b984c65", "model": "google:gemini@3-flash", "seed": 49334, "settings": { "temperature": 0.67, "topP": 0.9, "maxTokens": 1200, "thinkingLevel": "medium", "systemPrompt": "You are a precise multimodal analyst. Describe only what is visible or clearly inferable from the image, and separate observation from interpretation." }, "messages": [ { "role": "user", "content": "Analyze the provided image in a structured way. Return: 1) a one-sentence scene summary, 2) the 8 most important visible elements, 3) any readable or partially readable text, 4) inferred location/style clues, 5) what is happening in the scene, 6) mood and lighting analysis, and 7) two plausible stories that could explain this moment. Be specific and ground every claim in visible evidence." } ], "inputs": { "images": [ "https://assets.runware.ai/assets/inputs/947004f0-67f0-4b93-82ff-20610bab46e1.jpg" ] } } ``` **Response**: ```json { "taskType": "textInference", "taskUUID": "474e2fda-f280-4785-a9af-021b3b984c65", "text": "This analysis is based on the visual evidence provided in the image.\n\n### 1. Scene Summary\nA street vendor prepares hot drinks at a small cart in a narrow, rain-slicked alleyway illuminated by glowing lanterns and decorated with hanging fish streamers.\n\n### 2. The 8 Most", "seed": 49334, "cost": 0.00419, "finishReason": "length", "thoughtSignature": "[REDACTED]" } ```