GPT-5.6 is here ๐ŸŽ‰ 20% off all GPT ๐ŸŽ‰ All July ๐Ÿ”ฅLearn more
Doubao

Doubao Seed 1.6 Flash

Chat
volcengine/doubao-seed-1-6-flash
CompareGet Started

Doubao Seed 1.6 Flash is ByteDance's fast-inference variant of Doubao Seed 1.6, served through Volcengine and optimized for high-throughput, low-latency applications. It keeps the same long context window as the base model and supports tool use (function calling) plus prompt caching, so repeated system prompts in high-traffic pipelines are billed at the lower cache rate of $0.0043/M tokens. With input at $0.03/M tokens and output at $0.22/M, it is the most affordable member of the Doubao Seed 1.6 family on Ofox and fits cost-sensitive, high-concurrency deployments. Context: 256K tokens, output: 32K. Released 2025-08-28. Accessible via the OpenAI-compatible protocol.

Context Window
256K
Max Output Tokens
32K
Released
2025-08-28
Capabilities
Function CallingPrompt Caching
Available Providers
VolcengineVolcengine
Supported Protocols
OpenAIopenai

Providers

VolcengineVolcengine
Input Tokens
$0.03/M
Output Tokens
$0.22/M
Cache Read
$0.0043/M
Protocols
OpenAIopenai/v1/chat/completions/v1/responses

Code Examples

from openai import OpenAI
client = OpenAI(
base_url="https://api.ofox.ai/v1",
api_key="YOUR_OFOX_API_KEY",
)
response = client.chat.completions.create(
model="volcengine/doubao-seed-1-6-flash",
messages=[
{"role": "user", "content": "Hello!"}
],
)
print(response.choices[0].message.content)

Frequently Asked Questions

Doubao Seed 1.6 Flash on Ofox.ai costs $0.03/M per million input tokens and $0.22/M per million output tokens. Pay-as-you-go, no monthly fees.