Pricing, context window, capabilities, and release date — pulled from each provider's public docs. Both are available via the same AIgateway OpenAI-compatible endpoint; flip the model string to switch.
Both models stream in parallel through your own AIgateway key. Tokens, latency, and cost update as they arrive.
| Seedream 4.5 bytedance/seedream-4.5 | Seedream 5 Lite bytedance/seedream-5-lite | |
|---|---|---|
| Provider | ByteDance | ByteDance |
| Family | Seedream | Seedream |
| Modality | image | image |
| Context window | — | — |
| Max output | — | — |
| Released | 2026-04-08 | 2026-04-08 |
| Input price | $0.040 /img | $0.035 /img |
| Output price | — | — |
| Cache read | — | — |
| Tools | — | — |
| Streaming | — | — |
| Vision | — | — |
| JSON mode | — | — |
| Reasoning | — | — |
| Prompt caching | — | — |
Seedream 4.5 builds on 4.0 with multi-reference image support, batch generation, and sequential image generation.
Seedream 5 Lite is a lighter, faster version of the Seedream 5 family with multi-reference and batch generation support.
# pip install aigateway-py openai
# aigateway-py: sub-accounts, evals, replays, jobs, webhook verify.
# openai SDK: chat/embeddings/images/audio — drop-in compat per our SDK's own guidance.
from openai import OpenAI
client = OpenAI(
base_url="https://api.aigateway.sh/v1",
api_key="sk-aig-...",
)
# Try Seedream 4.5
client.chat.completions.create(
model="bytedance/seedream-4.5",
messages=[{"role":"user","content":"hello"}],
)
# Try Seedream 5 Lite — same client, same key
client.chat.completions.create(
model="bytedance/seedream-5-lite",
messages=[{"role":"user","content":"hello"}],
)