Choose an existing Gemini model to work with a written task, code excerpt or document passage. Explain the intended result, provide the relevant text and set the output controls supported by that task. Vidgo’s current Gemini entries offer Chat Completions and Gemini native formats: use messages for a Chat Completions conversation, or contents and generationConfig for a native request. Review the answer and usage, then continue with clarifications or test feedback.
Gemini is developed by Google. Vidgo provides access to the models. Model names and trademarks belong to their respective owners.The current family includes Flash and Pro Preview entries. Open a card to inspect its protocol options, output settings and current input/output rates, then test the written task you intend to integrate.
Gemini 3.8 Flash handles long-horizon coding, multi-step reasoning, and multimodal analysis with a 1M-token context.
Gemini 3.7 Flash handles agentic coding, multimodal analysis, and long-context knowledge work.
Gemini 3.5 Flash handles coding, long-context analysis, and multimodal understanding.
Gemini 3.1 Pro Preview handles complex reasoning, coding, and multimodal analysis across long contexts.
Gemini 3 Flash Preview handles long-context chat, coding, and multimodal understanding with adjustable reasoning.
In Chat Completions, provide the instruction and source text through messages, and choose the task’s supported max_tokens and sampling settings. In the native format, put each user or model turn in contents with text parts; use systemInstruction for persistent guidance and generationConfig for temperature, maxOutputTokens and topP. Keep the field names of the selected format together when continuing a conversation.
| Model / task | Input and workflow |
|---|---|
| Gemini 3.8 Flash | Gemini 3.8 Flash handles long-horizon coding, multi-step reasoning, and multimodal analysis with a 1M-token context. |
| Gemini 3.7 Flash | Gemini 3.7 Flash handles agentic coding, multimodal analysis, and long-context knowledge work. |
| Gemini 3.5 Flash | Gemini 3.5 Flash handles coding, long-context analysis, and multimodal understanding. |
| Gemini 3.1 Pro Preview | Gemini 3.1 Pro Preview handles complex reasoning, coding, and multimodal analysis across long contexts. |
| Gemini 3 Flash Preview | Gemini 3 Flash Preview handles long-context chat, coding, and multimodal understanding with adjustable reasoning. |
Gemini 3.8 Flash combines software-engineering capabilities with reasoning across specialist subjects. These charts show its DeepSWE v1.1 and HLE-Verified results. Use them to understand the evaluated tasks, then choose an available Gemini model and provide the code, documents or problem statement needed for your own workflow.
DeepSWE v1.1 evaluates software-engineering tasks in real codebases. The chart compares success rate with average task cost in the evaluation environment, helping illustrate the balance between completion quality and resource use. Supply the relevant code, observed behavior and acceptance criteria when requesting an implementation or fix. Vidgo API rates are listed in this page’s pricing section.
HLE-Verified evaluates reasoning across demanding specialist subjects. The chart compares Gemini 3.8 Flash with the listed models under the published methodology. For an analysis task, provide the source material, the question to resolve and any constraints, then ask for an explanation that connects the available evidence to its conclusion.
Provide the relevant text and explain how the answer will be used. Ask for a summary, structured extraction, code review or written draft with explicit requirements. Check the result against the source and use additional context or test feedback when developing the next answer.
Provide the relevant document sections and name the topics, facts and answer length to cover. Review the generated summary against its source before using it in a technical note or implementation discussion.
Supply the code excerpt, expected behavior and observed test result. Ask for an explanation or review, then verify proposed changes and return the results in a follow-up conversation.
Prepare a complete source note and define the required keys, values and units. Validate the returned structure before using the extracted data in an application prototype or content workflow.
Provide the facts, target audience and required sections, then request a complete explanation or reply. Review its meaning, retained details and tone before preparing the final document.
Keep the relevant earlier turns and add the next question with any new text. Review each answer in the context of the material already supplied when developing an analysis or clarifying a requirement.
Prepare the same text task in the format your application uses. Choose messages for Chat Completions or contents for Gemini native requests, then inspect the returned text and usage in the corresponding response format.
The table reads the current starting input-token rate for each Gemini entry per one million tokens. A complete request also includes output-token usage, including the thinking-token treatment documented for the selected model. Gemini 3.8 Flash and 3.7 Flash task pages additionally list cache-read rates. Review the selected model’s full rate table and returned usage, including the conversation context sent with each turn, when planning your application budget.
| Model | Provider | Workflow | Input | API formats | Starting input rate |
|---|---|---|---|---|---|
| Gemini 3.8 Flash | Chat | Text instructions and conversation context | Chat Completions / Gemini Native | $0.6 / 1M tokens | |
| Gemini 3.7 Flash | Chat | Text instructions and conversation context | Chat Completions / Gemini Native | $0.6 / 1M tokens | |
| Gemini 3.5 Flash | Chat | Text instructions and conversation context | Chat Completions / Gemini Native | $0.9 / 1M tokens | |
| Gemini 3.1 Pro Preview | Chat | Text instructions and conversation context | Chat Completions / Gemini Native | $0.8 / 1M tokens | |
| Gemini 3 Flash Preview | Chat | Text instructions and conversation context | Chat Completions / Gemini Native | $0.4 / 1M tokens |
Test a complete text task online, then integrate the selected model and API format.
Open the selected model, provide the task and source text, and choose its available output settings. Submit the conversation, read the complete answer and inspect available token usage. Add clarifications or test feedback when preparing a follow-up.
Use the existing model conversation, current token prices and task documentation to connect a reviewed answer with your application workflow.
Choose one of the existing Gemini entries, inspect its current input/output price and select Chat Completions or the Gemini native format. Prepare the same written task and source material when comparing which workflow fits your application.
Open the selected model, provide the task and source text, and choose its available output settings. Submit the conversation, read the complete answer and inspect available token usage. Add clarifications or test feedback when preparing a follow-up.
The table reads the current starting input-token rate for each Gemini entry per one million tokens. A complete request also includes output-token usage, including the thinking-token treatment documented for the selected model. Gemini 3.8 Flash and 3.7 Flash task pages additionally list cache-read rates. Review the selected model’s full rate table and returned usage, including the conversation context sent with each turn, when planning your application budget.
Use /v1/chat/completions with model and messages for the compatible format. For the native format, use the selected model’s /v1beta/models/{model}:generateContent endpoint with contents and generationConfig; streaming uses streamGenerateContent?alt=sse. Follow the matching documentation for authentication and response fields, then accumulate the returned text and read its usage information.
Use your Vidgo API credentials to authenticate the request to the selected endpoint. Send the exact model identifier, the conversation fields required by that protocol and the supported output settings. Consume the returned response using the same format you selected.
Accumulate streaming text when the selected workflow streams, or read the complete response body when it returns a full reply. Inspect the final answer and returned usage fields, then keep the relevant messages for the next turn. Return to the model conversation when continuing the online task.
Choose an existing Gemini model to work with a written task, code excerpt or document passage. Explain the intended result, provide the relevant text and set the output controls supported by that task. Vidgo’s current Gemini entries offer Chat Completions and Gemini native formats: use messages for a Chat Completions conversation, or contents and generationConfig for a native request. Review the answer and usage, then continue with clarifications or test feedback.
Read language-model introductions, API guides and platform comparisons to understand model selection, conversation inputs, response formats and token costs.
