gpt-oss-120b is 25.9× cheaper per million tokens (blended). gpt-oss-120b has the larger context window (131,072 vs 32,000 tokens, 4.1×).
Moondream 3 Preview vs gpt-oss-120b
Live catalog fields. Best-in-row is highlighted.
Moondream 3 Previewopen
Moondream · moondream__moondream3-preview
gpt-oss-120bopen
OpenAI · openai__gpt-oss-120b
Identity
| Field | moondream__moondream3-preview | openai__gpt-oss-120b |
|---|---|---|
| Provider | Moondream | OpenAI |
| Slug | moondream__moondream3-preview | openai__gpt-oss-120b |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | moondream/moondream3-preview | openai/gpt-oss-120b |
Quality
| Field | moondream__moondream3-preview | openai__gpt-oss-120b |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | moondream__moondream3-preview | openai__gpt-oss-120b |
|---|---|---|
| Input $ / 1M tokens | $0.30 | $0.02 |
| Cached input $ / 1M | — | $0.02 |
| Output $ / 1M tokens | $2.50 | $0.09 |
Context
| Field | moondream__moondream3-preview | openai__gpt-oss-120b |
|---|---|---|
| Max context tokens | 32,000 | 131,072 |
| Max output tokens | 4,096 | 65,536 |
Modalities
| Field | moondream__moondream3-preview | openai__gpt-oss-120b |
|---|---|---|
| Input | text, image | text |
| Output | text | text |