GPT OSS 20B is cheaper than DeepSeek V3.1 at $0.02/M vs $0.2/M input tokens.
| Spec | DeepSeek V3.1 | GPT OSS 20B |
|---|---|---|
| Input price | $0.2/M tokens | $0.02/M tokens |
| Output price | $0.8/M tokens | $0.1/M tokens |
| Context window | 164K tokens | 131K tokens |
| Released | Aug 2025 | Aug 2025 |
Not enough votes to call it. On the specs, DeepSeek V3.1 has the edge: bigger model tier.
GPT OSS 20B takes Reasoning. GPT OSS 20B costs 8.0x less per token.
GPT OSS 20B is cheaper on both — 10× input, 8.0× output
GPT OSS 20B uses 4.3x more emoji
GPT OSS 20B is cheaper than DeepSeek V3.1 at $0.02/M vs $0.2/M input tokens.
| Spec | DeepSeek V3.1 | GPT OSS 20B |
|---|---|---|
| Input price | $0.2/M tokens | $0.02/M tokens |
| Output price | $0.8/M tokens | $0.1/M tokens |
| Context window | 164K tokens | 131K tokens |
| Released | Aug 2025 | Aug 2025 |
Not enough votes to call it. On the specs, DeepSeek V3.1 has the edge: bigger model tier.
GPT OSS 20B takes Reasoning. GPT OSS 20B costs 8.0x less per token.
GPT OSS 20B is cheaper on both — 10× input, 8.0× output
GPT OSS 20B uses 4.3x more emoji