Dola-Seed 2.0 Mini is a ByteDance model listed on BytePlus as “Dola Seed 2.0 mini,” updated on Feb 14, 2026. AI/ML API documents it as a fast, cost-efficient multimodal model for lightweight tasks.
It is also described as supporting text, image, and video inputs, along with reasoning and agent workflows.
| Developer | ByteDance |
|---|---|
| Model ID | bytedance/dola-seed-2-0-mini |
| Release Date | April 23, 2026 |
| Context Window | 256,000 tokens (~256K) |
| Max Output Tokens | 128,000 tokens |
| Modalities | Image, Text, Video → Text |
| Capabilities | parallel tool calls, reasoning, streaming, structured (JSON schema) output, tool/function calling, vision |
Multimodal input
The model supports text, image, and video inputs.
Reasoning and agents
The model is documented with reasoning and agent workflows.
Lightweight positioning
It is described as fast and cost-efficient for lightweight tasks.
ByteDance family placement
ByteDance’s Seed 2.0 lineup includes Pro, Lite, and Mini model sizes.
Listed by BytePlus
BytePlus lists the model as Dola Seed 2.0 mini.
Lightweight multimodal tasks
Suitable for workloads that combine text, image, and video inputs with a lightweight model profile.
Reasoning workflows
Documented support for reasoning makes it relevant for tasks that need agent-style processing.
General-purpose Seed 2.0 Mini deployment
ByteDance positions the Mini tier within its broader Seed 2.0 model lineup for different deployment scenarios.
Seed 2.0 Mini
ByteDance’s Seed 2.0 lineup includes Pro, Lite, and Mini sizes, indicating adjacent options within the same family.
Sources: https://seed.bytedance.com/en/seed2 · https://docs.aimlapi.com/api-references/text-models-llm/bytedance/dola-seed-2.0-mini · https://llmpricing.dev/m/bytedance/dola-seed-2.0-mini/
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
High-concurrency and batch generation scenarios are documented use cases for Dola-Seed 2.0 Mini, which is described as optimized for inference throughput and deployment density.
It is also documented as suited to lightweight multimodal tasks, handling text, image, and video inputs for fast and cost-efficient use.
Reasoning and agent workflows are listed as supported use cases for this model, with documentation describing it as a fast and cost-efficient multimodal model for those workflows.
General low-cost production workloads are also cited, including batch classification, content moderation, and high-volume chat.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "bytedance/dola-seed-2-0-mini", "messages": [ { "role": "user", "content": "Hello!" } ] }, ) print(r.json())
const r = await fetch("https://api.aimlapi.com/v1/chat/completions", { method: "POST", headers: { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }, body: JSON.stringify({ "model": "bytedance/dola-seed-2-0-mini", "messages": [ { "role": "user", "content": "Hello!" } ] }), }); console.log(await r.json());
curl -X POST https://api.aimlapi.com/v1/chat/completions \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"bytedance/dola-seed-2-0-mini","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Cached input |
The only documented pricing caveat found for Dola-Seed 2.0 Mini is that OpenRouter shows tiered input pricing above 128K context, rising from $0.10 to $0.20 per 1M input tokens.
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Dola-Seed 2.0 Mini This page | Agentic workflows and structured output | |||
| Reasoning + agents | ||||
| Reasoning + agents | ||||
| Reasoning + agents |
Dola-Seed 2.0 Mini has a 256,000 tokens context window and can return up to 128,000 tokens.
Dola-Seed 2.0 Mini takes image, text, video as input and returns text.
Use bytedance/dola-seed-2-0-mini as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Dola-Seed 2.0 Mini became available on April 24, 2026.
Dola-Seed 2.0 Mini is priced at input $0.13 / 1M tokens, output $0.52 / 1M tokens, cached input $0.026 / 1M tokens.
Yes, Dola-Seed 2.0 Mini can stream responses as they are generated.
Yes, Dola-Seed 2.0 Mini accepts image input alongside text.
Dola-Seed 2.0 Mini was built by ByteDance.
It offers reasoning, streaming, vision, and parallel tool calls, so it can handle reasoning tasks, tool-based agent workflows, and lighter multimodal tasks.
Yes, it supports parallel tool calls along with structured output, which allows it to be used in agent-style workflows.
