🎁 New Sign up free, 10 calls on us. Up to $1, no card needed.

ByteDance Seed 1.8 Released 2025-12

ByteDance chat tools
Input$0.25/M
Output$2/M
Cache read$0.05/M
Context262K
vs GPT-4o~95% cheaper

Provider list prices: no platform markup, pay-as-you-go. These are official list prices. Logged-in customers may see effective prices including workspace discounts on /console/pricing. Effective input at a 70% cache-hit rate:$0.11/M. Implicit prefix caching is on by default for Seed language models (1,024-token minimum, no storage fee); an explicit context-caching API is also available. Media models (image / ASR) are not cacheable.

Use ByteDance Seed 1.8 in 30 seconds

OpenAI-compatible: swap the base_url, keep your SDK. POST /v1/chat/completions

from openai import OpenAI

client = OpenAI(
    base_url="https://synthorai.io/v1",
    api_key="sk-syn-...",
)

resp = client.chat.completions.create(
    model="ByteDance-Seed-1.8",
    messages=[{"role": "user", "content": "Summarize this diff"}],
)
print(resp.choices[0].message.content)

About ByteDance Seed 1.8

Stronger multimodal understanding and agent capabilities
Text, image, and video input
256K context with 32K chain-of-thought budget

ByteDance-Seed-1.8 is a deep-thinking model on BytePlus ModelArk, currently in beta, that its model page credits with stronger multimodal understanding and agent capabilities and superior performance across a wide range of complex real-world tasks.

  • Release notes add upgraded multimodal understanding and more flexible context management.
  • It accepts text, image, and video input and returns text, with a 256K context window, 224K maximum input, and 64K output including a 32K chain-of-thought budget, plus function calling, structured output, and context caching.
  • Synthorai serves it via its OpenAI-compatible gateway endpoint.

Specs & limits

Max output (vendor spec)65,536
Modalitiestext + image + video → text
Featurestools · structured_output · streaming · vision · batch · reasoning · caching
NotableGeneralized agentic model (search/code/GUI-agent capabilities, native vision); ModelArk id seed-1-8 (version seed-1-8-251228, Beta); 256K context, 64K max output incl. CoT; deep reasoning minimal/low/medium/high; strict-mode function calling.
Prompt cachingautomatic + explicit · min 1,024-token prefix

per ByteDance official docs ↗

FAQ

Is the ByteDance Seed 1.8 API free to try?

Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. At $0.25/M input tokens, that credit alone covers roughly 500 requests of ~8K tokens against ByteDance Seed 1.8.

What is ByteDance Seed 1.8 best at?

Stronger multimodal understanding and agent capabilities, plus text, image, and video input and 256K context with 32K chain-of-thought budget. See the About section for the full picture from the vendor's own release notes.

How much does ByteDance Seed 1.8 cost?

ByteDance Seed 1.8 costs $0.25 per million input tokens and $2 per million output tokens on Synthorai. That is the provider's list price, with no platform markup. Cached input tokens bill at $0.05/M.

Does ByteDance Seed 1.8 support prompt caching?

Yes: automatic caching is on by default, with an explicit mode for guaranteed savings. Cached input tokens bill at $0.05/M vs $0.25/M uncached; prompts need a 1,024-token stable prefix to cache. Prompt caching guide →

How do I get access to ByteDance Seed 1.8?

Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="ByteDance-Seed-1.8", and you're done. One API key covers every model on the gateway.

Related models

Get your free API key Compare your cost →