This model is deprecated. We only continue performance benchmarking for the default 10k input token workload. Results for other workloads are historical and no longer updated.
ByteDance Seed has launched a newer model, Doubao Seed Code. We suggest considering it instead.
For more information, see comparison of Doubao Seed Code to other models and API provider benchmarks for Doubao Seed Code.
ByteDance Seed
Open weights model
•Released August 2025
Seed-OSS-36B-Instruct API Provider Benchmarking & Analysis
This analysis is intended to support you in choosing the best API provider of Seed-OSS-36B-Instruct for your use-case.
Fastest
SiliconFlowOutput speed
Total 1 provider
Lowest Latency
SiliconFlowTime to first answer token
Total 1 provider
Lowest Price
SiliconFlowBlended price (per 1M tokens)
Total 1 provider
Seed-OSS-36B-Instruct is available through SiliconFlow.
Highlights
Pricing
Pricing: Cache Hit, Input, and Output
Pricing: Blended Price
Output Speed vs. Price
Speed
Measured by Output Speed (tokens per second)
Output Speed: Seed-OSS-36B-Instruct
Latency vs. Output Speed
Latency
Measured by Time (seconds) to First Token
Time to First Answer Token
End-to-End Response Time
Seconds to output 500 tokens, calculated based on time to first token, 'thinking' time for reasoning models, and output speed
End-to-End Response Time
Key Comparison Metrics & API Features
| SiliconFlow | 262k | Open | -- | 40 | 3.10 | 65.00 | 49.52 | ||
Frequently Asked Questions
Common questions about Seed-OSS-36B-Instruct providers
Seed-OSS-36B-Instruct is available through 1 API provider: SiliconFlow. Each provider offers different performance characteristics and pricing.
Seed-OSS-36B-Instruct is currently available through 1 API provider that we benchmark and track.
The fastest provider for Seed-OSS-36B-Instruct by output speed is SiliconFlow (40.4 t/s). Output speed measures how quickly tokens are generated after the model starts responding.
The provider with the lowest time to first answer token for Seed-OSS-36B-Instruct is SiliconFlow (52.62s). Lower latency means faster initial response time.
The most affordable provider for Seed-OSS-36B-Instruct by blended price is SiliconFlow ($0.25 per 1M tokens). Blended price uses a 7:2:1 cache hit/input/output token ratio.
The provider with the lowest input token pricing for Seed-OSS-36B-Instruct is SiliconFlow ($0.21 per 1M input tokens).
The provider with the lowest output token pricing for Seed-OSS-36B-Instruct is SiliconFlow ($0.57 per 1M output tokens).
The only provider of Seed-OSS-36B-Instruct supports JSON mode for structured output.
The only provider of Seed-OSS-36B-Instruct supports function calling (tool use).
SiliconFlow leads across all key metrics for Seed-OSS-36B-Instruct, offering the fastest speed, lowest latency, and most competitive pricing.
When choosing a provider for Seed-OSS-36B-Instruct, consider: output speed (for throughput-intensive tasks), latency (for interactive applications requiring quick first responses), pricing (for cost-sensitive workloads), and API features like JSON mode or function calling.
Yes, provider performance can vary over time due to infrastructure changes, load balancing, and updates. We continuously benchmark all providers and display historical performance trends in the "Over Time" charts.
For information about Seed-OSS-36B-Instruct's intelligence, capabilities, modalities, and how it compares to other models, see the model overview page. View model overview