Llama 3 8B Lunaris is 1.8× cheaper per million tokens (blended). gpt-oss-20b has the larger context window (131,072 vs 8,192 tokens, 16.0×).
gpt-oss-20b vs Llama 3 8B Lunaris
Live catalog fields. Best-in-row is highlighted.
gpt-oss-20bopen
OpenAI · openai__gpt-oss-20b
Llama 3 8B Lunarisopen
Sao10k · sao10k__l3-lunaris-8b
Identity
| Field | openai__gpt-oss-20b | sao10k__l3-lunaris-8b |
|---|---|---|
| Provider | OpenAI | Sao10k |
| Slug | openai__gpt-oss-20b | sao10k__l3-lunaris-8b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | openai/gpt-oss-20b | Sao10K/L3-8B-Lunaris-v1 |
Quality
| Field | openai__gpt-oss-20b | sao10k__l3-lunaris-8b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | openai__gpt-oss-20b | sao10k__l3-lunaris-8b |
|---|---|---|
| Input $ / 1M tokens | $0.03 | $0.04 |
| Cached input $ / 1M | $0.03 | — |
| Output $ / 1M tokens | $0.13 | $0.05 |
Context
| Field | openai__gpt-oss-20b | sao10k__l3-lunaris-8b |
|---|---|---|
| Max context tokens | 131,072 | 8,192 |
| Max output tokens | 117,964 | 7,372 |
Modalities
| Field | openai__gpt-oss-20b | sao10k__l3-lunaris-8b |
|---|---|---|
| Input | text | text |
| Output | text | text |