Choose an existing GPT model to work with source text, code or a complete task brief. Describe the operation and expected result, then select the API format and output settings available in that task. The family includes GPT 6.1 Sol, GPT 6 Sol, GPT 6 Luna, the three GPT 5.6 entries and GPT 5.5. Their supported formats and request settings differ, so review the selected model’s fields and full token prices before integrating a conversation.
GPT is developed by OpenAI. Vidgo provides access to the models. Model names and trademarks belong to their respective owners.Open a model card to inspect its current context information, API formats, output controls and prices. Prepare a concrete task and the source material you intend to use, then review the returned answer against your acceptance criteria.
GPT-6.1 Sol Chat turns code and document context into implementations and structured analysis, with long-context reasoning and multi-step agent workflows.
GPT-6 Sol handles complex coding, multi-step reasoning, and document analysis with a 1,050,000-token context.
GPT-6 Luna turns text into summaries, classifications, extracted information, and concise rewrites.
OpenAI GPT 5.6 text models: Sol for complex reasoning and agent work, Terra for balanced production workloads, and Luna for high-volume text processing.
OpenAI GPT 5.6 text models: Sol for complex reasoning and agent work, Terra for balanced production workloads, and Luna for high-volume text processing.
OpenAI GPT 5.6 text models: Sol for complex reasoning and agent work, Terra for balanced production workloads, and Luna for high-volume text processing.
GPT-5.5 handles coding, long-context reasoning, and agent workflows with a 1M-token context window.
Use messages for Chat Completions and input for Responses. The current GPT 6 and GPT 5.5 entries offer both formats; GPT 5.6 Sol, Terra and Luna use Responses. Keep the relevant conversation turns and choose the supported output-token fields. For GPT 6 Sol’s Responses workflow, the current settings panel configures max_output_tokens; GPT 5.5’s Responses workflow also provides reasoning.effort.
| Model / task | Input and workflow |
|---|---|
| GPT-6.1 Sol | GPT-6.1 Sol Chat turns code and document context into implementations and structured analysis, with long-context reasoning and multi-step agent workflows. |
| GPT-6 Sol | GPT-6 Sol handles complex coding, multi-step reasoning, and document analysis with a 1,050,000-token context. |
| GPT-6 Luna | GPT-6 Luna turns text into summaries, classifications, extracted information, and concise rewrites. |
| GPT 5.6 Sol | OpenAI GPT 5.6 text models: Sol for complex reasoning and agent work, Terra for balanced production workloads, and Luna for high-volume text processing. |
| GPT 5.6 Terra | OpenAI GPT 5.6 text models: Sol for complex reasoning and agent work, Terra for balanced production workloads, and Luna for high-volume text processing. |
| GPT 5.6 Luna | OpenAI GPT 5.6 text models: Sol for complex reasoning and agent work, Terra for balanced production workloads, and Luna for high-volume text processing. |
| GPT-5.5 | GPT-5.5 handles coding, long-context reasoning, and agent workflows with a 1M-token context window. |
The GPT family offers model choices for coding and technical analysis. These charts focus on GPT 6.1 Sol, showing its research-debugging and kernel-optimization results alongside the named models. Compare the specific versions and evaluation settings, then choose an available GPT model and prepare the code, constraints and tests for your task.
The research-debugging chart compares rubric scores on real experimental faults. GPT 6.1 Sol improves over GPT 6 Sol and approaches Astra on this evaluation. Provide the relevant code, observed failure and diagnostic evidence to request a cause analysis, a proposed correction and a sequence of tests for checking the result.
KernelGen 1P evaluates the ability to understand hardware constraints, correct implementation errors and improve kernel performance. The chart compares the listed GPT versions within the same evaluation. Describe the current implementation and measured bottleneck, then ask for changes that preserve correctness and can be evaluated against your baseline.
Prepare the source material, describe the goal and define the acceptance criteria. Ask for an explanation, structured extraction, draft or proposed software change, then review the result against those requirements. Continue with concrete feedback and test evidence when developing the next answer.
Provide the relevant code, expected behavior and constraints. Request an explanation or proposed implementation, then verify the result with the project’s tests before applying it.
Supply the changed code or draft together with the acceptance criteria. Ask for concrete findings and review the proposed corrections against both the original requirements and observed behavior.
Prepare the source text and define the required fields or categories. Validate the returned values and format before using the result in an application, catalog or content-processing workflow.
Provide the original text, intended reader and details that must be retained. Review the generated summary or rewrite for meaning, necessary information and style before preparing the final content.
Describe the issue, permitted resolutions and information still needed. Generate a complete reply and check its facts, tone and next steps before using it in the business workflow.
Keep relevant conversation context and add new requirements or observed test output. Choose the supported output settings for the selected GPT task, then review each revision against the same completion criteria.
The table reads the current starting input-token rate for each GPT entry per one million tokens. A full request also includes the selected model’s output-token charge and its applicable cache-read or cache-write rates shown on the task page. Sent conversation history contributes to input usage, and generated output contributes to output usage. Review the complete rate table and returned usage when comparing model choices or budgeting several software iterations.
| Model | Provider | Workflow | Input | API formats | Starting input rate |
|---|---|---|---|---|---|
| GPT-6.1 Sol | OpenAI | Chat | Text instructions and conversation context | Chat Completions / Responses | $1.6 / 1M tokens |
| GPT-6 Sol | OpenAI | Chat | Text instructions and conversation context | Chat Completions / Responses | $1.6 / 1M tokens |
| GPT-6 Luna | OpenAI | Chat | Text instructions and conversation context | Chat Completions / Responses | $0.08 / 1M tokens |
| GPT 5.6 Sol | OpenAI | Chat | Text instructions and conversation context | Responses | $1.4 / 1M tokens |
| GPT 5.6 Terra | OpenAI | Chat | Text instructions and conversation context | Responses | $0.56 / 1M tokens |
| GPT 5.6 Luna | OpenAI | Chat | Text instructions and conversation context | Responses | $0.056 / 1M tokens |
| GPT-5.5 | OpenAI | Chat | Text instructions and conversation context | Chat Completions / Responses | $3 / 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 a GPT model by its available format, current output controls and full token rates. GPT 6 and GPT 5.5 tasks offer Chat Completions and Responses, while the GPT 5.6 entries use Responses. Prepare your intended source material and test the task before adopting the workflow.
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 GPT entry per one million tokens. A full request also includes the selected model’s output-token charge and its applicable cache-read or cache-write rates shown on the task page. Sent conversation history contributes to input usage, and generated output contributes to output usage. Review the complete rate table and returned usage when comparing model choices or budgeting several software iterations.
Use /v1/chat/completions with model and messages when that format is offered by the selected task, or /v1/responses with model and input. Follow the selected model’s exact identifier and documented settings, authenticate with Vidgo API credentials and accumulate the returned text. Inspect the completed answer and usage fields before preparing a follow-up.
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 GPT model to work with source text, code or a complete task brief. Describe the operation and expected result, then select the API format and output settings available in that task. The family includes GPT 6.1 Sol, GPT 6 Sol, GPT 6 Luna, the three GPT 5.6 entries and GPT 5.5. Their supported formats and request settings differ, so review the selected model’s fields and full token prices before integrating a conversation.
Read language-model introductions, API guides and platform comparisons to understand model selection, conversation inputs, response formats and token costs.
