gemma-4-31b-it
openrouter · 262K ctx · 18 providers · updated 2026-09-19 02:15 UTC
The board shows this model's cheapest measured offer ($0.152/1M); the smaller figure under it is the mean of the 28 offers listed below ($0.291/1M). Add those up and divide — it matches. 24h token volume (55B) is sourced from OpenRouter public rankings — today's only public source of absolute per-model token counts (Vercel AI Gateway publishes share-of-traffic percentages); as more sources come online, the per-router breakdown will sum to this total here.
| Provider | Router / Source | $ in /1M | $ out /1M | TTFT | TPS | Uptime | Evidence |
|---|---|---|---|---|---|---|---|
| openrouter | Pricebook (LiteLLM) ↗ | $0.090 | $0.340 | — | — | — | Official list |
| DeepInfra (turbo) | OpenRouter ↗ | $0.090 | $0.340 | 938ms | 23 | 96.0% | API-measured |
| requesty | Requesty ↗ | $0.104 | $0.304 | — | — | — | API-measured |
| wandb | Pricebook (LiteLLM) ↗ | $0.100 | $0.340 | — | — | — | Official list |
| CoreWeave (fp4) | OpenRouter ↗ | $0.100 | $0.340 | 732ms | 32 | 94.8% | API-measured |
| Venice (fp4) | OpenRouter ↗ | $0.120 | $0.360 | 795ms | 23 | 99.2% | API-measured |
| Chutes (fp4) | OpenRouter ↗ | $0.120 | $0.370 | 3578ms | 12 | 94.1% | API-measured |
| deepinfra | Pricebook (LiteLLM) ↗ | $0.130 | $0.380 | — | — | — | Official list |
| deepinfra | HuggingFace Router ↗ | $0.130 | $0.380 | 450ms | 47 | — | API-measured |
| DeepInfra (fp8) | OpenRouter ↗ | $0.130 | $0.380 | 2044ms | 12 | 88.3% | API-measured |
| aihubmix | Pricebook (LiteLLM) ↗ | $0.140 | $0.400 | — | — | — | Official list |
| friendliai | Pricebook (LiteLLM) ↗ | $0.140 | $0.400 | — | — | — | Official list |
| novita | Pricebook (LiteLLM) ↗ | $0.140 | $0.400 | — | — | — | Official list |
| novita | HuggingFace Router ↗ | $0.140 | $0.400 | 682ms | 38 | — | API-measured |
| novita-ai | Novita AI ↗ | $0.140 | $0.400 | — | — | — | API-measured |
| Crusoe (bf16) | OpenRouter ↗ | $0.140 | $0.400 | 1511ms | 8 | 96.9% | API-measured |
| Friendli | OpenRouter ↗ | $0.140 | $0.400 | 656ms | 77 | 100.0% | API-measured |
| Novita (bf16) | OpenRouter ↗ | $0.140 | $0.400 | 1092ms | 14 | 73.1% | API-measured |
| libertai | Pricebook (LiteLLM) ↗ | $0.150 | $0.400 | — | — | — | Official list |
| Parasail (fp8) | OpenRouter ↗ | $0.150 | $0.400 | 1210ms | 22 | 99.0% | API-measured |
| tensormesh | Pricebook (LiteLLM) ↗ | $0.140 | $0.560 | — | — | — | Official list |
| DeepInfra (ultra) | OpenRouter ↗ | $0.270 | $0.760 | 2298ms | 15 | 98.8% | API-measured |
| together_ai | Pricebook (LiteLLM) ↗ | $0.280 | $0.860 | — | — | — | Official list |
| Together | OpenRouter ↗ | $0.390 | $0.970 | — | — | — | API-measured |
| sambanova | Pricebook (LiteLLM) ↗ | $0.380 | $1.15 | — | — | — | Official list |
| SambaNova | OpenRouter ↗ | $0.380 | $1.15 | 2071ms | 98 | 95.3% | API-measured |
| ModelRun (fp4) | OpenRouter ↗ | $0.750 | $1.00 | 205ms | 80 | 100.0% | API-measured |
| SiliconFlow (fp8) | OpenRouter ↗ | $0.750 | $1.00 | 1513ms | 18 | 82.8% | API-measured |
Volume trend
Last 30 days: 84B → 55B (-35%); range 39B–84B tokens/day. Source: OpenRouter public rankings; refreshed hourly.
Data & method
Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/gemma-4-31b-it.json. Free reuse requires attribution to tkx.org.
About
Gemma 4 31B is an AI model served by multiple inference providers on AI model marketplaces, known for its language understanding capabilities.
AI-generated summary from public information — is this yours?
FAQ
How much does gemma-4-31b-it cost?
Cheapest measured offer right now: $0.09/1M input, $0.34/1M output via openrouter — across 18 tracked providers, refreshed hourly.
Who serves gemma-4-31b-it?
18 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.
How heavily is gemma-4-31b-it used?
gemma-4-31b-it routed 55B tokens in the last 24h. The daily bars above show routed volume over recent days. Source: OpenRouter public rankings — one of the few routers publishing per-model usage; TKX refreshes hourly.