Compare models
GPT-4o mini vs Phi-4 vs Whisper large-v3
Every figure below carries the source that reported it and the moment it was observed. Values that failed validation are withheld rather than shown, and a dash means no source we track carries that field for that model.
| Field | GPT-4o mini | Phi-4 | Whisper large-v3 |
|---|---|---|---|
| Downloads, 30 days | — | 624,150Synced from sourceCurrent2h ago | 4,712,143 (highest of the compared values)Synced from sourceCurrent2h ago |
| Likes | — | 2,309Synced from sourceCurrent2h ago | 6,365 (highest of the compared values)Synced from sourceCurrent2h ago |
| Context window | 128,000 (highest of the compared values)Synced from sourceCurrent2h ago | 16,384Synced from sourceCurrent2h ago | — |
| Input, $/M tokens | 0.15Synced from sourceCurrent2h ago | 0.07 (lowest of the compared values)Synced from sourceCurrent2h ago | — |
| Modality | textSeeded, unreviewedwritten 29d ago | textSeeded, unreviewedwritten 29d ago | speechSeeded, unreviewedwritten 29d ago |
| Licence | proprietarySeeded, unreviewedwritten 29d ago | mitSeeded, unreviewedwritten 29d ago | apache-2.0Seeded, unreviewedwritten 29d ago |
| Gated | — | noSynced from sourceCurrent2h ago | noSynced from sourceCurrent2h ago |
| Last updated | — | 2026-07-14Synced from sourceCurrent2h ago | 2024-08-12Synced from sourceCurrent2h ago |
| Library | — | transformersSynced from sourceCurrent2h ago | transformersSynced from sourceCurrent2h ago |
| Task | — | text-generationSynced from sourceCurrent2h ago | automatic-speech-recognitionSynced from sourceCurrent2h ago |
| Hugging Face | — | microsoft/phi-4Synced from sourceCurrent2h ago | openai/whisper-large-v3Synced from sourceCurrent2h ago |
| OpenRouter id | openai/gpt-4o-miniSynced from sourceCurrent2h ago | microsoft/phi-4Synced from sourceCurrent2h ago | — |
| Output, $/M tokens | 0.6Synced from sourceCurrent2h ago | 0.14Synced from sourceCurrent2h ago | — |
| Vendor | OpenAISeeded, unreviewedwritten 29d ago | MicrosoftSeeded, unreviewedwritten 29d ago | OpenAISeeded, unreviewedwritten 29d ago |
Sources: Hugging Face Hub, OpenRouter model catalogue. Most recent observation 2h ago. Where a row is marked, ▲ is the highest of the values shown and ▼ the lowest — arithmetic on the figures above, not a ranking or a recommendation. Rows where neither extreme is meaningful are left unmarked rather than given a direction they do not have.
Change the comparison
Remove one, or open the directory to pick a different set. Up to 3 at a time.