gemma-4-31B-it pricing
gemma-4-31B-it, Small-tier from SambaNova, costs $0.38 per 1M input tokens and $1.15 per 1M output tokens.
Input$0.38per 1M tokens
Output$1.15per 1M tokens
Context window—tokens
TierSmallSambaNova
Price your own workload against gemma-4-31B-it in the calculator →
Specs and pricing
| Provider | SambaNova |
| Tier | Small |
| Context window | — |
| Max output | — |
| Input price | $0.38 / 1M tokens |
| Output price | $1.15 / 1M tokens |
| Modalities | text |
Note. SambaNova lists Gemma 4 31B IT at $0.38 / $1.15 per 1M tokens on its own pricing page.
What it costs at realistic volumes
Assuming a 4:1 input:output token ratio, a common shape for chat and RAG-style workloads:
| Volume (4:1 in:out ratio) | Input cost | Output cost | Total / month |
|---|---|---|---|
| 1,000,000 in / 250,000 out | $0.38 | $0.29 | $0.67 |
| 10,000,000 in / 2,500,000 out | $3.80 | $2.88 | $6.67 |
| 100,000,000 in / 25,000,000 out | $38.00 | $28.75 | $66.75 |
Cheaper alternatives
Same tier (Small), a different provider, and a lower blended cost at the 4:1 ratio used above:
| Model | Provider | $/1M in | $/1M out | At the 4:1 ratio |
|---|---|---|---|---|
| Meta-Llama-3.1-8B-Instruct-Turbo | DeepInfra | $0.02 | $0.04 | 95.5% cheaper blended |
| Solar Pro 4 | OpenRouter | $0.03 | $0.12 | 91% cheaper blended |
| GPT-OSS 20B | OpenRouter | $0.03 | $0.13 | 90.6% cheaper blended |
| schematron-v2-turbo | inference.net | $0.03 | $0.15 | 89.9% cheaper blended |
| Amazon Nova Micro | Amazon (Nova) | $0.035 | $0.14 | 89.5% cheaper blended |