Baseten
99.98%Context131.1K
Max output131.1K
p50 latency255 ms
Throughput253.0 t/s
Input price$0.1
Output price$0.5
Zero retentionNo training
Model directory
Baseer model profileLanguage model
openai/gpt-oss-120b
GPT OSS 120B
Extremely capable general-purpose LLM with strong, controllable reasoning capabilities
Input / 1M tokens$0.1
Output / 1M tokens$0.5
Maximum context131.1K
Inference providers8
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.
Bedrock
99.98%Context128K
Max output8.2K
p50 latency350 ms
Throughput156.5 t/s
Input price$0.15
Output price$0.6
Zero retentionNo training
Cerebras
100.00%Context131.1K
Max output131K
p50 latency—
Throughput—
Input price$0.35
Output price$0.75
Zero retentionNo trainingCaching
Fireworks
100.00%Context128K
Max output128K
p50 latency183 ms
Throughput161.0 t/s
Input price$0.15
Output price$0.6
Zero retentionNo trainingCaching
Groq
100.00%Context131.1K
Max output32.8K
p50 latency172 ms
Throughput—
Input price$0.15
Output price$0.6
Zero retentionNo trainingCaching
Nebius
99.84%Context131K
Max output131K
p50 latency522 ms
Throughput368.0 t/s
Input price$0.15
Output price$0.6
Zero retentionNo training
Parasail
100.00%Context131.1K
Max output131K
p50 latency498 ms
Throughput180.0 t/s
Input price$0.1
Output price$0.75
Zero retentionNo training
Togetherai
96.90%Context128K
Max output128K
p50 latency258 ms
Throughput158.0 t/s
Input price$0.15
Output price$0.6
Zero retentionNo training
| Provider | Maximum context | Max output | p50 latency | p50 throughput | 24h uptime | Input / 1M tokens | Output / 1M tokens | Privacy |
|---|---|---|---|---|---|---|---|---|
Baseten | 131.1K | 131.1K | 255 ms | 253.0 t/s | 99.984% | $0.1 | $0.5 | |
Bedrock | 128K | 8.2K | 350 ms | 156.5 t/s | 99.983% | $0.15 | $0.6 | |
Cerebras | 131.1K | 131K | — | — | 100.000% | $0.35 | $0.75 | |
Fireworks | 128K | 128K | 183 ms | 161.0 t/s | 100.000% | $0.15 | $0.6 | |
Groq | 131.1K | 32.8K | 172 ms | — | 100.000% | $0.15 | $0.6 | |
Nebius | 131K | 131K | 522 ms | 368.0 t/s | 99.835% | $0.15 | $0.6 | |
Parasail | 131.1K | 131K | 498 ms | 180.0 t/s | 100.000% | $0.1 | $0.75 | |
Togetherai | 128K | 128K | 258 ms | 158.0 t/s | 96.900% | $0.15 | $0.6 |
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
- US
- API specifications
- V2, V3, V4
- Temperature control
- Supported
Model identifier
openai/gpt-oss-120bModel profile updated: Sep 12, 2026, 1:46 PM
Related models
More options from the same creator or model category.