Model prices / Google / Gemma 4 31B IT
Gemma 4 31B ITOpen weights
Google · released 2026-04-02
No price from the maker itself is on record for Gemma 4 31B IT. The lowest of 46 providers is DevPass (LLM Gateway): $0.1 per 1M input tokens and $0.25 per 1M output tokens (as of 2026-11-12). Context window: 262K tokens, up to 32.8K output tokens per request.
Price by providerUSD per 1M tokens
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
| GoogleOfficialgemma-4-31b-it | — | — | — | Official | Official docs |
 DevPass (LLM Gateway)Lowestgemma-4-31b-it | $0.1 | $0.25 | $0.01 | Lowest | Official docs |
LLLM Gatewayconsensusprotocol/ | $0.1 | $0.25 | $0.01 | Official docs | |
LLLM Gatewayrunware/ | $0.102 | $0.297 | $0.012 | Official docs | |
FFastRoutergoogle/ | $0.1 | $0.3 | — | Official docs | |
KKilo Gatewaygoogle/ | $0.1 | $0.34 | $0.1 | Official docs | |
NNanoGPTgoogle/ | $0.1 | $0.34 | $0.1 | Official docs | |
 CoreWeavegoogle/ | $0.1 | $0.34 | $0.1 | Official docs | |
 Venice AIgoogle-gemma-4-31b-it | $0.12 | $0.36 | $0.09 | Official docs | |
 Chutesgoogle/ | $0.12 | $0.37 | $0.012 | Official docs | |
NNanoGPTTEE/ | $0.12 | $0.37 | $0.012 | Official docs | |
NNanoGPTTEE/ | $0.12 | $0.37 | $0.012 | Official docs |
42 more listings
| Provider | Input | Output | Cached | Notes | |
|---|---|---|---|---|---|
KKenarigemma-4-31b-it | $0.102857 | $0.405714 | $0.041143 | Official docs | |
OOrcaRoutergoogle/ | $0.13 | $0.38 | $0.02 | Official docs | |
AAbacusgoogle/ | $0.14 | $0.4 | — | Official docs | |
 Amazon Bedrockgoogle. | $0.14 | $0.4 | — | Official docs | |
 Crusoegoogle/ | $0.14 | $0.4 | $0.14 | Official docs | |
 Friendligoogle/ | $0.14 | $0.4 | — | Official docs | |
 Hugging Facegoogle/ | $0.14 | $0.4 | — | Official docs | |
LLLM Gatewaynovita/ | $0.14 | $0.4 | — | Official docs | |
MMerge Gatewaygoogle/ | $0.14 | $0.4 | — | Official docs | |
NNanoGPTgoogle/ | $0.14 | $0.4 | $0.05 | Official docs | |
 Novita AIgoogle/ | $0.14 | $0.4 | — | Official docs | |
 Ollama Cloudgemma4: | $0.14 | $0.4 | $0.05 | Official docs | |
 Vercel AI Gatewaygoogle/ | $0.14 | $0.4 | — | Official docs | |
NNeuralwattgemma-4-31b | $0.144 | $0.42 | $0.0144 | Official docs | |
 Deep Infragoogle/ | $0.2 | $0.4 | — | Official docs | |
LLLM Gatewaydeepinfra/ | $0.2 | $0.4 | — | Official docs | |
 OpenRoutergoogle/ | $0.2 | $0.4 | — | Official docs | |
NNanoGPTTEE/ | $0.15 | $0.46 | $0.075 | Official docs | |
CCortecsgemma-4-31b-it | $0.223 | $0.39 | — | Official docs | |
 DigitalOceangemma-4-31B-it | $0.18 | $0.5 | $0.036 | Official docs | |
Aai&google/ | $0.2 | $0.5 | $0.05 | Official docs | |
IInfomaniakgoogle/ | $0.25 | $0.5 | — | Official docs | |
BBerget.AIgoogle/ | $0.280375 | $0.56075 | — | Official docs | |
MModulargoogle/ | $0.25 | $0.65 | $0.08 | Official docs | |
TTinfoilgemma4-31b | $0.4 | $1 | — | Official docs | |
 SambaNovagemma-4-31B-it | $0.38 | $1.15 | — | Official docs | |
 SiliconFlowgoogle/ | $0.75 | $1 | $0.25 | Official docs | |
 AI/ML APIgoogle/ | $1.04742 | $1.57642 | $1.04742 | Official docs | |
RRegolo AIgemma4-31b | $0.46 | $2.42 | — | Official docs | |
OOppergemma-4-31b-it | $0.46488 | $2.44062 | — | Official docs | |
LLLMTRgemma-4 | $2 | $5 | $0.5 | Official docs | |
LLilacDeprecatedgoogle/ | $0.11 | $0.35 | — | Deprecated | Official docs |
AAMDGemma-4-31B-IT | $0 | $0 | $0 | Official docs | |
BBothubgemma-4-31b-it: | $0 | $0 | — | Official docs | |
IInferXgemma-4-31B-it-fp8 | $0 | $0 | — | Official docs | |
 Nvidiagoogle/ | $0 | $0 | — | Official docs | |
| OpenRoutergoogle/ | $0 | $0 | — | Official docs | |
 Poegoogle/ | $0 | $0 | — | Official docs | |
QQVACgemma4-31b | $0 | $0 | — | Official docs | |
RRequestygemma-4-31b-it | $0 | $0 | — | Official docs | |
UUnoRoutergemma-4-31b-it: | $0 | $0 | — | Official docs | |
TTempr Gatewaygoogle/ | — | — | — | Official docs |
Providers are those listed by models.dev. This site has not vetted them one by one; each provider's own page has the binding price.
About
Largest Gemma 4 instruction model for open, self-hosted chat and reasoning
Description from models.dev.
Specs
- Type
- Text
- Context
- 262K
- Max output
- 32.8K
- Input
- Text, Image
- Output
- Text
- Reasoning
- Yes
- Tool calling
- Yes
- Structured output
- Yes
- Knowledge cutoff
- 2025-01
- Open weights
- Yes
- Released
- 2026-04-02
Source
Prices and specs come from models.dev (MIT licence), updated 2026-11-12. Each provider's name links to its official docs. A provider priced at 0 usually includes the model in a subscription; it is not necessarily a free API.