Bedrock
99.95%Context128K
Max output8.2K
p50 latency346 ms
Throughput197.0 t/s
Input price$0.07
Output price$0.3
Zero retentionNo training
Model directory
Baseer model profileLanguage model
openai/gpt-oss-20b
GPT OSS 20B
A compact, open-weight language model optimized for low-latency and resource-constrained environments, including local and edge deployments.
Input / 1M tokens$0.03
Output / 1M tokens$0.14
Maximum context131.1K
Inference providers6
Price comparison
USD per one million tokens, using current provider data.
Provider latency
Last-hour p50 in milliseconds; lower is better.
Provider uptime
Reported availability over the last 24 hours; not a contractual SLA.
Inference providers
Compare current pricing, performance, and privacy across every available provider.
Deepinfra
100.00%Context131.1K
Max output8.2K
p50 latency226 ms
Throughput108.0 t/s
Input price$0.03
Output price$0.14
Zero retentionNo training
Groq
100.00%Context131.1K
Max output32.8K
p50 latency304 ms
Throughput915.0 t/s
Input price$0.075
Output price$0.3
Zero retentionNo trainingCaching
Novita
100.00%Context131.1K
Max output32.8K
p50 latency441 ms
Throughput283.0 t/s
Input price$0.04
Output price$0.15
No training
Parasail
100.00%Context131.1K
Max output8.2K
p50 latency594 ms
Throughput160.0 t/s
Input price$0.04
Output price$0.2
Zero retentionNo training
Togetherai
99.83%Context131.1K
Max output8.2K
p50 latency341 ms
Throughput113.0 t/s
Input price$0.05
Output price$0.2
Zero retentionNo training
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Bedrock | 128K | 8.2K | 346 ms | 197.0 t/s | 99.948% | $0.07 | $0.3 | |
Deepinfra | 131.1K | 8.2K | 226 ms | 108.0 t/s | 100.000% | $0.03 | $0.14 | |
Groq | 131.1K | 32.8K | 304 ms | 915.0 t/s | 100.000% | $0.075 | $0.3 | |
Novita | 131.1K | 32.8K | 441 ms | 283.0 t/s | 100.000% | $0.04 | $0.15 | |
Parasail | 131.1K | 8.2K | 594 ms | 160.0 t/s | 100.000% | $0.04 | $0.2 | |
Togetherai | 131.1K | 8.2K | 341 ms | 113.0 t/s | 99.826% | $0.05 | $0.2 |
What can this model do?
Available modalities and capabilities across inference providers.
TextAdvanced reasoningTool useAutomatic cachingTools
Reasoning options
LowMediumHigh
Technical profile
- Model type
- Language model
- Release date
- Aug 5, 2025
- Knowledge cutoff
- 2024-10
- Regions
- —
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
openai/gpt-oss-20bModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.