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.