Apply your own routing policies, reduce token costs automatically, and see every routing decision in real time with Merge Gateway.
What Dola Seed 2.0 Mini costs to run
| Vendor | Input / 1M tokens | Output / 1M tokens | Zero data retention |
| --- | ---: | ---: | --- |
| BytePlus | $0.1000 | $0.4000 | Yes |
Test Dola Seed 2.0 Mini
with Gateway’s Simulator
See a prompt's output, token spend, latency, and more with Dola Seed 2.0 Mini.
Route requests to Dola Seed 2.0 Mini in minutes
To get started in seconds, add our Gateway Implementation skill to your project, or pick your preferred SDK below. Check out our other quick start skills here.
Install the Merge Gateway SDK
Python
1$ pip install merge-gateway-sdkSend a request
Python
1from merge_gateway import MergeGateway
2
3client = MergeGateway(api_key="YOUR_API_KEY")
4
5response = client.responses.create(
6 model="openai/gpt-5.2",
7 input=[
8 {"type": "message", "role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
9 {"type": "message", "role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
10 ],
11)
12
13print(response.output[0].content[0].text)Try a diffrent model
Swap the model string to route to a different provider. No other code changes needed.
Anthropic
1response = client.responses.create(
2 model="anthropic/claude-sonnet-4-20250514",
3 input=[
4 {"type": "message", "role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
5 {"type": "message", "role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
6 ],
7)Point to Gateway
Python
1from openai import OpenAI
2
3client = OpenAI(
4 api_key="YOUR_API_KEY",
5 base_url="https://api-gateway.merge.dev/v1/openai",
6)Send a request
Use the standard chat.completions.create method. No provider prefix needed on the model name.
Python
1response = client.chat.completions.create(
2 model="gpt-5.2",
3 messages=[
4 {"role": "system", "content": "You are a helpful programming tutor. Explain the concepts clearly with practical examples."},
5 {"role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
6 ],
7)
8
9print(response.choices[0].message.content)Install packages
1npm install merge-gateway-ai-sdk-provider aiCreate the provider
TypeScript
1import { createMergeGateway } from "merge-gateway-ai-sdk-provider";
2
3const gateway = createMergeGateway({
4 apiKey: "YOUR_API_KEY",
5});Send a request
Use generateText to send a request. Model names use the provider/model format.
TypeScript
1import { generateText } from "ai";
2
3const { text } = await generateText({
4 model: gateway("openai/gpt-4o"),
5 prompt: "Explain the concept of recursion in programming with a simple set of examples.",
6});
7
8console.log(text);If you already have @ai-sdk/openai installed, point it at Gateway with a base URL change:
TypeScript
1import { createOpenAI } from "@ai-sdk/openai";
2
3const gateway = createOpenAI({
4 apiKey: "YOUR_API_KEY",
5 baseURL: "https://api-gateway.merge.dev/v1/ai-sdk",
6});
7
8// All generateText/streamText calls work unchangedInstall the Merge Gateway SDK
Anthropic SDK
1from anthropic import Anthropic
2
3client = Anthropic(
4 api_key="YOUR_API_KEY",
5 base_url="https://api-gateway.merge.dev/v1/anthropic",
6)
7
8message = client.messages.create(
9 model="claude-sonnet-4-20250514",
10 max_tokens=1024,
11 messages=[
12 {"role": "user", "content": "Explain the concept of recursion in programming with a simple set of examples."},
13 ],
14)
15
16print(message.content[0].text)Explore other models available in Merge Gateway
Dola Seed 2.0 Mini FAQ
If you have additional questions about Dola Seed 2.0 Mini, we've addressed several more below. Keep in mind that this information was written in June, 2026 and is subject to change.
Heading
What other models does ByteDance offer?
ByteDance's Seed 2.0 series covers the full spectrum from lightweight, high-throughput inference to frontier-class reasoning and specialized coding. Here are some other models ByteDance supports:
- Dola Seed 2.0 Lite: ByteDance's balanced production workhorse, targeting teams that need multimodal and agentic capabilities without paying flagship prices. It supports a 256K context window and scores 93.0 on AIME 2025 (as of 06/08/2026), making it a strong fit for document processing, image-text understanding, and high-frequency agentic workflows
- Dola Seed 2.0 Pro: ByteDance's flagship general-purpose agent model, built for long-chain reasoning and complex workflows. It achieves 98.3 on AIME 2025, a Codeforces rating of 3020, and 89.5 on VideoMME (as of 06/08/2026), and supports up to 272K context tokens. It's the go-to choice when reasoning depth and multimodal quality are the top priority
- Dola Seed 2.0 Code (preview): A coding-specialized variant fine-tuned on top of the Seed 2.0 base, with a 256K context window. It scores 87.8 on LiveCodeBench v6 and 76.5% on SWE-Bench Verified (as of 06/08/2026) at approximately 35% lower cost than Pro, making it a targeted option for software engineering agents and IDE integrations
- UI-TARS-1.5-7B: ByteDance's 7-billion-parameter vision-language agent optimized for GUI automation across desktop, web, mobile, and game interfaces. It achieves 84.8% on WebVoyager and 46.6 on AndroidWorld (as of 06/08/2026), and is purpose-built for agentic tasks that require interacting with visual interfaces rather than generating text
How does Dola Seed 2.0 Mini differ from ByteDance's other models?
Dola Seed 2.0 Mini sits at the cost and speed end of the Seed 2.0 lineup, optimized for high-throughput, latency-sensitive deployments where budget efficiency matters more than peak reasoning quality.
- Pricing: At $0.10 per million input tokens and $0.40 per million output tokens (as of 06/08/2026), Mini costs approximately 2.5x less on input and 5x less on output than Dola Seed 2.0 Lite ($0.25 input / $2.00 output), and roughly 4.7x less on input than Dola Seed 2.0 Pro ($0.47 input / $2.37 output)
- Context window: Supports up to 256K tokens, matching Lite and nearly matching Pro's 272K ceiling. This is a competitive advantage over many cost-tier models that cap at 32K or 128K
- Benchmark scores: Mini scores 87.0 on AIME 2025, 79.0 on GPQA Diamond, 83.6 on MMLU-Pro, and 1644 on Codeforces (as of 06/08/2026). These are meaningfully lower than Lite (AIME 93.0, GPQA 85.1) and Pro (AIME 98.3, GPQA 88.9), which matters for tasks requiring deep reasoning or competitive-level coding
- Use case fit: Mini supports four reasoning effort modes (minimal, low, medium, high), giving you control over latency and cost per request. It's designed for text classification, sentiment analysis, code completion, and high-concurrency dialogue, not IMO-level math or multi-step agent reasoning chains
Mini is the right call when you're running high request volumes with predictable, structured tasks and want to keep costs in check without sacrificing the 256K context window.
What models should I consider using alongside Dola Seed 2.0 Mini?
No single model is optimal for every task. Here are models worth pairing with Dola Seed 2.0 Mini depending on what your product needs:
- Dola Seed 2.0 Pro When a user query requires multi-step reasoning, mathematical proof-checking, or complex agentic planning, route to Pro. Mini handles the bulk of routine requests while Pro absorbs the high-complexity tail, keeping your average cost low
- Gemini 2.5 Flash For tasks that need fast, low-cost inference with strong multilingual text handling, Gemini 2.5 Flash offers competitive throughput and a 1M-token context window. It's a useful fallback or parallel lane for long-document summarization where Mini's reasoning depth is sufficient but you want provider diversity
- Claude Haiku 3.5 When your pipeline involves structured output extraction, JSON parsing from unstructured inputs, or tight instruction-following on templated prompts, Claude Haiku 3.5 is a strong cost-efficient complement. Its instruction adherence tends to be precise on well-defined schemas
- Mistral Small For European data-residency requirements or workloads where you need a reliable, low-cost text model with strong multilingual coverage, Mistral Small is a natural routing target alongside Mini. Pairing the two gives you geographic and provider redundancy at the budget tier
- UI-TARS-1.5-7B If your product includes any GUI automation, browser-based agents, or mobile interface interaction, UI-TARS-1.5-7B is a specialized complement. Mini handles conversational and text tasks; UI-TARS handles the visual interface layer that Mini isn't built for
What are the challenges of using Dola Seed 2.0 Mini in my product?
Like any production LLM, Dola Seed 2.0 Mini comes with tradeoffs worth planning for:
- Reasoning ceiling: Mini's GPQA Diamond score of 79.0 and AIME 2025 score of 87.0 (as of 06/08/2026) are noticeably below Lite and Pro. For tasks that require multi-hop reasoning, scientific analysis, or algorithm design, Mini may produce incomplete or lower-quality outputs that require a fallback to a stronger model
- Coding limitations: With a Codeforces rating of 1644 and LiveCodeBench v6 score of 64.1 (as of 06/08/2026), Mini is suited for code completion and boilerplate generation but falls short on complex debugging, refactoring across large codebases, or competitive programming problems. Route those tasks to Dola Seed 2.0 Code or Pro
- Provider dependency: Running all requests through ByteDance's Volcano Engine or BytePlus platform creates a single point of failure. If ByteDance experiences an outage or deprecates the Mini model version, your application has no fallback without prior routing configuration
- Cost at scale: At $0.40 per million output tokens, Mini is already affordable, but at tens of millions of requests per day, output token costs accumulate quickly. Without active budget caps and usage attribution, spend can drift beyond plan without triggering an alert
- Knowledge cutoff: Mini's training data has a cutoff of January 2024. For tasks requiring awareness of recent events, current documentation, or post-cutoff technical releases, you'll need retrieval augmentation or routing to a model with a more recent cutoff
Why should I use Merge Gateway to route LLM requests with Dola Seed 2.0 Mini and every other model?
Using Dola Seed 2.0 Mini through Merge Gateway gives you access to the model itself and the infrastructure layer around it:
- One API, every provider: Access Dola Seed 2.0 Mini and every other major LLM through a single endpoint and API key. Change providers by swapping the model string — no application code changes required
- Intelligent routing and automatic failover: Merge routes around ByteDance outages automatically. Routing policies based on cost, latency, or quality can reduce spend by 40–60% without touching your application code
- Cost governance: Set hard or soft project budgets so Dola Seed 2.0 Mini spend stays within plan. Every request is attributed to a model, project, and tag in a unified billing dashboard across all providers
- Build Your Own Router: Define what "best" means for your traffic by selecting from curated ML benchmarks or adding your own eval scores. The router scores each available model against your weights and picks the winner per request, with a plain-language explanation of every decision
- Security and compliance controls: Apply DLP rules and prompt injection protection before every request reaches ByteDance. Enforce per-project model and region policies without adding that logic to your application
How can I start routing requests to Dola Seed 2.0 Mini via Merge Gateway?
Getting Dola Seed 2.0 Mini running through Merge Gateway takes a few minutes:
1. Create an account and get your API key from the dashboard.
2. Install the Merge Gateway SDK: run pip install merge-gateway-sdk (Python) or npm install merge-gateway-sdk (Node). Alternatively, if you're already using the OpenAI SDK, set base_url = "https://api-gateway.merge.dev/v1/openai" and your existing code works as-is.
3. Make your first request using the provider/model format. For Dola Seed 2.0 Mini, the model string is tencent/dola-seed-2.0-mini. Swap the model string to route to any other provider without changing anything else.
4. Configure a routing policy in the dashboard to set failover behavior, cost limits, and optimization strategy. Your first policy can be as simple as naming Dola Seed 2.0 Mini as primary with one fallback.
Full setup instructions and SDK references are in the Merge Gateway docs.
Try Dola Seed 2.0 Mini through Merge Gateway
Route, observe, and control AI requests across providers from one API.
