GPT-OSS 20B on Together AI
Cheap Together AI hosted GPT-OSS tier for structured outputs, tool use, and high-volume chat.
- Creator
- Together AI
- Lifecycle
- Active
- Context
- 128.0K
- Max output
- —
- Released
- Aug 1, 2025
- Status
- up
- Input
- $0.05 / 1M tokens
- Output
- $0.20 / 1M tokens
- Cached read
- — / 1M tokens
- Cached write
- — / 1M tokens
- Batch discount
- —%
- Source
- GPT-OSS 20B on Together AI pricing
- Verified
- Apr 2, 2026 (High)
Capabilities
- Modalities
- text→text
- Capabilities
- reasoningbatchSupportpromptCachingfunctionCallingstructuredOutputs
- Strengths
- Very cheap hosted reasoning, High-volume friendly
- Tradeoffs
- Lower ceiling than larger hosted open models
Benchmark Coverage
| Benchmark | Version | Score | Date | Source | Notes |
|---|
Release History
| Release | Alias | Lifecycle | Release Date | Deprecation | Shutdown | Summary |
|---|---|---|---|---|---|---|
| GPT-OSS 20B on Together AI | together-gpt-oss-20b | Active | Aug 1, 2025 | — | — | Current published model family snapshot. |
Host Coverage
| Host | Type | Context | Pricing Note | Differences |
|---|---|---|---|---|
| Together AI Serverless | first-party | 128.0K | Hosted model via Together AI serverless catalog. | Serverless hosting |
Migration Guidance
Budget hosted reasoning tier for Together AI workloads.
Replacement models: together-gpt-oss-120b
Change Events
| Date | Type | Title | Description | Source |
|---|---|---|---|---|
| Aug 1, 2025 | family_added | GPT-OSS 20B on Together AI published | Initial public model family launch. | GPT-OSS 20B on Together AI release notes |
Other models from Together AI
DeepSeek V3.1 on Together AI, GLM-5 on Together AI, GPT-OSS 120B on Together AI, Kimi K2.5 on Together AI, Llama 4 Maverick on Together AI, Qwen3 Coder 480B on Together AI, Qwen3.5 397B on Together AI