Gemma 4 31B
google/gemma-4-31b-it
Input
$0.20
per 1M token
Output
$0.40
per 1M token
Input ter-cache
—
per 1M token
Varian gratis dengan pembatasan kuota (rate-limit) juga tersedia.
Gemma 4 31B Instruct is Google DeepMind's 30.7B dense multimodal model supporting text and image input with text output. Features a 256K token context window, configurable thinking/reasoning mode, native function...
Deskripsi di bawah ini disediakan oleh OpenRouter dalam bahasa Inggris.
- Dirilis
- Context window
- 262K token
- Output maksimal
- 16K token
- Input
- gambar, teks, video
- Output
- teks
- Penalaran
- Ya
Riwayat harga
- input $0.10 → $0.20 +100% · output $0.34 → $0.40 +18%
- input $0.20 → $0.10 -50% · output $0.40 → $0.34 -15%
Penyedia di OpenRouter
16 endpoint menyediakan model ini. Uptime menunjukkan rasio permintaan berhasil di OpenRouter; harga per 1M token.
| Penyedia | Input | Output | Context window | Uptime 30 mnt | Uptime 24 jam |
|---|---|---|---|---|---|
| DeepInfrafp8 · flextingkat diskon/prioritas | $0.16 | $0.32 | 262K | — | 96.4% |
| CoreWeavefp4 | $0.10 | $0.34 | 262K | 100% | 100% |
| Venicefp4 | $0.12 | $0.36 | 256K | 100% | 100% |
| Chutesfp4 | $0.12 | $0.37 | 131K | 100% | 99.51% |
| Crusoebf16 | $0.14 | $0.40 | 262K | 100% | 100% |
| Friendli | $0.14 | $0.40 | 262K | 100% | 100% |
| DekaLLM | $0.14 | $0.40 | 262K | 100% | 99.79% |
| Novitabf16 | $0.14 | $0.40 | 262K | 100% | 93.2% |
| Parasailfp8 | $0.15 | $0.40 | 262K | 100% | 100% |
| DeepInfrafp8 | $0.20 | $0.40 | 262K | 100% | 100% |
| DeepInfraturbo | $0.135 | $0.51 | 262K | 100% | 100% |
| DeepInfrafp8 · prioritytingkat diskon/prioritas | $0.30 | $0.60 | 262K | 100% | 99.86% |
| ModelRunfp4 | $0.75 | $1.00 | 262K | 100% | 100% |
| SiliconFlowfp8 | $0.75 | $1.00 | 262K | 100% | 99.91% |
| Io Net | $0.361 | $1.09 | 262K | 100% | 98.9% |
| SambaNova | $0.38 | $1.15 | 131K | 100% | 93.8% |