What is Seed 1.8 API?
ByteDance Seed 1.8 is a large language model with a 256K context window optimized for long-context reasoning and generation.
Technical Specifications
- Supported inputs: Image, Text
- Output: Text
- Context window: 256,000 tokens / Max output: 224,000 tokens
- Endpoint: /chat/completions
Performance Benchmarks
[embed]
Seed 1.8 API Pricing
- Input: $0.325 / 1M tokens
- Output: $2.6 / 1M tokens
Where to Use Seed 1.8
Coding and code review
Generate, debug, and review code across languages, reading whole files or repos in a single prompt.
Agentic and multi-step workflows
Reliable tool-calling and instruction-following suit agent loops that plan, call tools, and iterate.
Long-document analysis
Summarize and extract from contracts, papers, and reports without aggressive chunking.
Code Sample
[embed]
Measured on the AI/ML API gateway across live traffic. Figures are medians unless stated. Last updated 2026-10-12.
Seed 1.8 is documented as suited to information retrieval, where it can gather and reconcile information across several steps. It is also suited to code generation and execution, including tasks where a coding agent generates a script, checks execution results, and revises the code after an error.
It is documented as suited to GUI interaction, where it can interpret screenshots or software interfaces and determine the next permitted action. It is also suited to complex workflows and multi-step task execution, including internal automation systems that coordinate several controlled tools and document workflows that combine long context, visual pages, and follow-up actions.
import requests r = requests.post( "https://api.aimlapi.com/v1/chat/completions", headers={"Authorization": "Bearer " + AIMLAPI_KEY}, json={ "model": "bytedance/seed-1-8", "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/seed-1-8", "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/seed-1-8","messages":[{"role":"user","content":"Hello!"}]}'
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Input | |
| Output | |
| Benchmark | Score | What it measures | Source | Retrieved |
|---|---|---|---|---|
| MMLU | 92.3 | Multi-discipline knowledge across 57 school and professional subjects | Source | September 22, 2026 |
| GPQA Diamond | 83.8 | Google-proof graduate science questions (hardest subset) | Source | September 22, 2026 |
| SWE-bench Verified | 72.9 | Resolving verified real GitHub issues | Source | September 22, 2026 |
| AIME 2025 | 94.6 | Competition mathematics (AIME), 2025 | Source | September 22, 2026 |
| LiveCodeBench | 79.5 | Contamination-free competitive programming problems | Source | September 22, 2026 |
Seed 1.8 has a 256,000 tokens context window and can return up to 224,000 tokens.
Seed 1.8 takes image, text as input and returns text.
Use bytedance/seed-1-8 as the model id. Requests go to https://api.aimlapi.com/v1/chat/completions.
Seed 1.8 is priced at input $0.325 / 1M tokens, output $2.6 / 1M tokens.
Yes, Seed 1.8 can stream responses as they are generated.
Yes, Seed 1.8 accepts image input alongside text.
Seed 1.8 was built by ByteDance.
It supports function calling, streaming, structured outputs, parallel tool calls, and vision input alongside text.
