Tasks and inputs
Mercury Voice is listed for Text generation. It accepts undocumented formats and produces undocumented formats. Use the publisher’s input format and preprocessing for your chosen deployment.
SyncDev model directory · Profile updated Oct 13, 2026
Mercury Voice is Inception’s preview diffusion LLM for voice-agent workflows, with sales-assisted access and separately advertised promotional token rates.
Pricing conditions: The model page lists 50%-off input/output rates of $0.20/$0.75 per million tokens, alongside regular $0.40/$1.50 rates. Access is directed through sales. A universal public API ID, promotion end date and native audio request format have not been established for this profile.
Recorded modality support shows what this model can accept and produce. An undocumented modality is shown as unknown rather than assumed to be unsupported.
Accepts
Not documented in the current source record.
Produces
Not documented in the current source record.
Mercury Voice was previewed with Mercury 2.5 on 8 September 2026. Inception positions it as a diffusion LLM for voice-agent workflows, where delays between reasoning, tool calls and responses affect a conversation. That positioning alone does not establish a speech-recognition or speech-synthesis interface, so this profile does not infer native audio inputs or outputs.
The current model page directs developers to contact sales for access. It advertises reasoning, tools, structured output and a 128K context, but a universal public request ID and exact numeric request limits have not been established here. Keep the actual deployment name, account settings and supported response format with any evaluation.
The publisher displays 50%-off rates of $0.20 per million input tokens and $0.75 per million output tokens, alongside regular rates of $0.40 and $1.50. A promotion end date is not stated. Confirm availability and billing with the offered deployment before estimating a production workload, including any separate speech services used around the language model.
Evaluate the complete conversation pipeline with the deployment that is actually offered. Measure the delay from a user’s completed turn to the first useful response, including tool calls and any speech services. Check interruptions, long tool responses and unfinished actions independently from transcript or speech-generation quality.
Record the exact model identifier, deployment route and request settings with each result. Count complete runs, including rejected outputs, retries and tool calls. When the workflow creates files or code, open the files or execute the existing checks before accepting the result. A plausible first response can hide an incomplete final deliverable.
The specifications describe supported interfaces and request capacity. They do not establish a measured quality ranking or a latency guarantee for your account. SyncDev has not independently benchmarked this model. Choose a deployment after testing the languages, input formats and operating conditions that matter to your users.
Explore inception models, browse model tasks, or compare two models with the same acceptance criteria.
Compare the model on the work you need to complete.
Mercury Voice is listed for Text generation. It accepts undocumented formats and produces undocumented formats. Use the publisher’s input format and preprocessing for your chosen deployment.
The listed route has starting rates of $0.20 input and $0.75 output per million tokens. Measure a completed task using the prompts, documents and tools your application will use. Include reasoning and retries in the result.
Use the model identifier and account requirements for the selected API route. Confirm its request limits and output format with one complete task before connecting a larger workflow.
These records share a directory category. Check the source card, output type and deployment requirements before treating a model as a replacement.
Anthropic
Claude’s small model for high-volume extraction, classification and routing, with adaptive thinking and a 1M-token context window.
Mistral AI
Mistral Large 4 is an open-weight multimodal model released in public preview on the publisher’s announced release, for general reasoning, coding and agent applications.
OpenAI
GPT-6.1 Sol is OpenAI's updated Sol model for coding and professional tasks. It accepts text and images and returns text.
inclusionAI
Ling 3.1 Flash is inclusionAI’s hybrid reasoning model for coding and tool agents, available through a hosted AI Gateway route.
Anthropic
Claude Sonnet 5.5 is an Anthropic language model that accepts text and images and returns text.
MiniMax
MiniMax M3.1 Flash Preview is a multimodal reasoning model for code and agent workflows, accessed through eligible MiniMax plans and tools.