Gemma 4 31B google/gemma-4-31b-it
Served by 17 providers. Cheapest: Requesty at $0 blended /1M tokens.
| Provider | Type | Input /1M | Output /1M | Cached input | Blended | Context | Notes | Source |
|---|---|---|---|---|---|---|---|---|
| Requesty google/gemma-4-31b-it |
LLM routers | $0 | $0 | — | $0 | 262k | fp4 upstream route google; geo global; 2 other upstream routes listed (input $0.104-$0.13/M); API list price; Requesty's 5% markup on model cost (pricing page) is not included |
✓ src 2026-09-18 |
| OpenRouter google/gemma-4-31b-it |
LLM routers | $0.09 | $0.34 | $0.05 | $0.153 | 262k | api modality text+image+video->text |
✓ src 2026-09-18 |
| CoreWeave google/gemma-4-31B-it |
Inference hosts | $0.10 | $0.34 | — | $0.16 | 262k | Context from docs model table (rounded, e.g. "262k"). |
✓ src src2 2026-09-18 |
| Featherless google/gemma-4-31B-it |
Inference hosts | $0.12 | $0.36 | $0.10 | $0.18 | 33k | Developer-plan per-token rate; model_class gemma4-31b; also usable flat-rate on $25/mo Chat plan (32K ctx, human chat only) |
✓ src src2 src3 2026-09-18 |
| Venice.ai API google-gemma-4-31b-it |
Inference hosts | $0.12 | $0.36 | $0.09 | $0.18 | 256k | fp4 |
✓ src src2 2026-09-18 |
| Chutes google/gemma-4-31B-turbo-TEE |
Inference hosts | $0.12 | $0.37 | $0.012 | $0.182 | 131k | fp4 TEE (confidential compute); upstream weights nvidia/Gemma-4-31B-IT-NVFP4; served as NVFP4 "turbo" build |
✓ src src2 2026-09-18 |
| DeepInfra google/gemma-4-31B-it |
Inference hosts | $0.13 | $0.38 | — | $0.193 | 262k | fp8 Also -turbo (fp4, $0.09/$0.34, cached $0.05) and -Ultra ($0.27/$0.76) variants. |
✓ src src2 2026-09-18 |
| SiliconFlow google/gemma-4-31B-it |
Inference hosts | $0.13 | $0.40 | — | $0.198 | — | context shown on pricing page as "262K" |
✓ src 2026-09-18 |
| Amazon Bedrock google.gemma-4-31b |
Hyperscaler AI platforms | $0.14 | $0.40 | — | $0.205 | 256k | batch −50% bedrock-mantle (OpenAI-compatible) endpoint |
✓ src src2 2026-09-18 |
| Crusoe | Inference hosts | $0.14 | $0.40 | $0.14 | $0.205 | — | cached tokens price listed equal to input |
✓ src 2026-09-18 |
| FriendliAI google/gemma-4-31B-it |
Inference hosts | $0.14 | $0.40 | — | $0.205 | 262k | context from pricing page embedded model data |
✓ src 2026-09-18 |
| GMI Cloud Inference Engine google/gemma-4-31b-it |
Inference hosts | $0.14 | $0.40 | — | $0.205 | — | from GMI console public pricing API (console is client-rendered; docs say prices live in console Model Hub) |
✓ src src2 2026-09-18 |
| Novita AI google/gemma-4-31b-it |
Inference hosts | $0.14 | $0.40 | — | $0.205 | 262k |
✓ src src2 2026-09-18 |
|
| Parasail | Inference hosts | $0.15 | $0.40 | $0.06 | $0.212 | — | special batch price $0.07 in/$0.20 out |
✓ src 2026-09-18 |
| DigitalOcean gemma-4-31B-it |
Inference hosts | $0.18 | $0.50 | $0.036 | $0.26 | 256k | Pricing table lists "Gemma 4"; models page maps it to gemma-4-31B-it. |
✓ src src2 2026-09-18 |
| Together AI | Inference hosts | $0.39 | $0.97 | — | $0.535 | — | Pricing page only; not in docs serverless table |
◐ src 2026-09-18 |
| SambaNova Cloud (SambaCloud) gemma-4-31B-it |
Inference hosts | $0.38 | $1.15 | — | $0.573 | 128k | Preview model; text/image/video input |
✓ src src2 2026-09-18 |
✓ from the provider's own pricing page · ◐ partly confirmed there · 2° third-party source. Router prices may exclude the router's own fees; see each router's page.