model · class value · updated 2026-07-29
What it's for
Best for: Local/private assistants, multimodal summaries, and document/image understanding.
Not ideal for: Lowest-resource laptops or top-tier coding agents.
Role: Open multimodal local generalist
Specifications
| Provider | |
| API format | openai |
| Context window | 262144 |
| Restricted access | No |
| Capabilities | Vision, Tools, Thinking |
| Execution Paths | api, self_host |
Price components
| Type | USD | Basis | Conditions | Source | Verified | Freshness |
|---|---|---|---|---|---|---|
| per_million_in | $0.14 | required · verified | OpenRouter default price-weighted routing observation; this pair matched the Novita BF16 Gemma 4 31B endpoint on 2026-07-29, but the actual routed provider and billed rate can vary with availability, quantization, and routing preferences. | OpenRouter Gemma 4 31B routing price row | 2026-07-29 | vendor · 24d |
| per_million_out | $0.34 | required · reported | OpenRouter default price-weighted routing observation; this pair matched the Novita BF16 Gemma 4 31B endpoint on 2026-07-29, but the actual routed provider and billed rate can vary with availability, quantization, and routing preferences. | src_model_price_api | 2026-08-21 | vendor · 0d |
Cost at three usage tiers
| A few questions and small tasks each day. | $1.15/mo |
| Daily use, plus some scheduled tasks. | $3.82/mo |
| Working for you most of the day, including web tasks. | $11.46/mo |
Token cost only; add a host for the full-stack estimate.