Gemma 4 31B
GoogleGemma 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...
In
$0.20
Out
$0.40
Blended
$0.25
Where to buy this model
15 access routes| Route | In | Out | Blended | vs |
|---|---|---|---|---|
| ● CoreWeave cheapestfp4 | $0.10 | $0.34 | $0.16 | - |
| ● Venice fp4 | $0.12 | $0.36 | $0.18 | +12% |
| ● Chutes fp4 | $0.12 | $0.37 | $0.18 | +12% |
| $0.16 | $0.32 | $0.20 | +25% | |
| ● DekaLLM | $0.14 | $0.40 | $0.21 | +31% |
| ● Crusoe bf16 | $0.14 | $0.40 | $0.21 | +31% |
| ● Friendli | $0.14 | $0.40 | $0.21 | +31% |
| $0.14 | $0.40 | $0.21 | +31% | |
| ● NextBit fp4 | $0.15 | $0.40 | $0.21 | +31% |
| $0.15 | $0.40 | $0.21 | +31% | |
| ● PrimeIntellect fp8 | $0.32 | $0.53 | $0.37 | +131% |
| ● Io Net | $0.36 | $1.09 | $0.54 | +238% |
| $0.38 | $1.15 | $0.57 | +256% | |
| ● ModelRun fp4 | $0.75 | $1.00 | $0.81 | +406% |
| ● SiliconFlow fp8 | $0.75 | $1.00 | $0.81 | +406% |
● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.
- Ctx
- 262K
- max output
- 16K
- Family
- gemma
- Modalities
- image · text · video
- Features
- json · reasoning · tools
Live pricing, updated 2026-11-03.
Google models at a similar price
| Model | In | Out | Ctx |
|---|---|---|---|
| Gemma 4 26B A4B | $0.059 | $0.178 | 262K |
| Gemma 3 27B | $0.08 | $0.35 | 131K |
| Gemini 2.5 Flash Lite | $0.1 | $0.4 | 1.048576M |
| Gemma 4 31B · this model | $0.2 | $0.4 | 262K |
| Gemini 3.1 Flash Lite | $0.25 | $1.5 | 1.048576M |
| Gemini 2.5 Flash | $0.3 | $2.5 | 1.048576M |