Author's Description
Seed 1.6 is a general-purpose model released by the ByteDance Seed team. It incorporates multimodal capabilities and adaptive deep thinking with a 256K context window.
Key Specifications
Supported Parameters
This model supports the following parameters:
Features
This model supports the following features:
Performance Summary
ByteDance Seed: Seed 1.6, a general-purpose multimodal model with a 256K context window, demonstrates exceptional reliability, achieving a 100% success rate across all benchmarks. While its speed ranking places it among models with longer response times (15th percentile), its pricing is moderate (24th percentile). The model exhibits outstanding performance in critical areas. It achieved perfect accuracy in both Hallucinations (Baseline) and Reasoning (Baseline) benchmarks, notably being the most accurate model at its price point and speed for these categories. Seed 1.6 also shows strong capabilities in Instruction Following (92nd percentile), Coding (89th percentile), and Mathematics (96th percentile), indicating robust problem-solving and technical proficiency. Its General Knowledge is solid at 99.5% accuracy, and it performs well in Email Classification (98.0%) and Ethics (99.0%). The primary weakness lies in its speed, consistently ranking in the lower percentiles for duration across all tests.
Model Pricing
Current Pricing
| Feature | Price (per 1M tokens) |
|---|---|
| Prompt | $0.25 |
| Completion | $2 |
Price History
Available Endpoints
| Provider | Endpoint Name | Context Length | Pricing (Input) | Pricing (Output) |
|---|---|---|---|---|
|
Seed
|
Seed | bytedance-seed/seed-1.6-20250625 | 262K | $0.25 / 1M tokens | $2 / 1M tokens |
Benchmark Results
| Benchmark | Category | Reasoning | Strategy | Free | Executions | Accuracy | Cost | Duration |
|---|
Other Models by bytedance-seed
|
|
Released | Params | Context |
|
Speed | Ability | Cost |
|---|---|---|---|---|---|---|---|
| ByteDance Seed: Seed 1.6 Flash | Dec 23, 2025 | — | 262K |
Text input
Image input
Video input
Text output
|
★★★ | ★★★★ | $$$ |