Google: Gemma 4 31B
microgoogle/gemma-4-31b-it
Gemma 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...
AA INDEX14.7
CONTEXT262K
MODALITYtext+image+video->text
OPENNESSProprietary
ADDEDAug 2026
LAST PRICED13 min ago
Input
$0.14 /M
Output
$0.40 /M
Blended (40/60)
$0.30 /M
Cost / IQ
$0.8126 /M
Cost / IQ = Blended Price ÷ (AA Intelligence Score ÷ 40). Normalises price by model intelligence so you can compare value across tiers. Lower = better value per unit of intelligence. Not a transactional price.
24h0%
7d0%
Price History
30-day view, daily close
Low: $0.30/M
High: $0.30/M
Average: $0.30/M
Pricing Variants
Batch (async)
$0.74/M
-147.7% cheaper than standard
In: $0.39/M · Out: $0.97/M
Provider Comparison
12 providers · click a column to sort
| Provider | Input $/M | Output $/M | Blended $/M ↑ | vs Median |
|---|---|---|---|---|
| ↓CoreWeave | $0.10 | $0.34 | $0.24 | -18.1% |
| Venice | $0.12 | $0.36 | $0.26 | -11.4% |
| Chutes | $0.12 | $0.37 | $0.27 | -9.4% |
| Crusoe | $0.14 | $0.40 | $0.30 | -0.7% |
| Friendli | $0.14 | $0.40 | $0.30 | -0.7% |
| Novita | $0.14 | $0.40 | $0.30 | -0.7% |
| Parasail | $0.15 | $0.40 | $0.30 | +0.7% |
| DeepInfra | $0.20 | $0.40 | $0.32 | +7.4% |
| Io Net | $0.36 | $1.09 | $0.80 | +168.4% |
| SambaNova | $0.38 | $1.15 | $0.84 | +182.6% |
| ModelRun | $0.75 | $1.00 | $0.90 | +202.0% |
| SiliconFlow | $0.75 | $1.00 | $0.90 | +202.0% |
Blended price = 40% input + 60% output. Median price shown in header is the reference price for this model.
Cost / IQ Comparison
Cost / IQ (quality-adjusted $/M)$0.8126/M
Cost per GPT-4-equivalent token. Lower = better value. Comparable across all models.
At or below SIT TPI
Value Ranking (by Cost / IQ)
Rank #229 of 521 micro models
← YOU ARE HERE | Google: Gemma 4 31B
Data Sources
Source
Aggregator & direct provider data
12 sources · updated recently
API Access
# Get this model's current price
curl https://api.inferenceindexer.ai/v1/models/google/gemma-4-31b-it
# Response (truncated)
{ "model_id": "google/gemma-4-31b-it", "name": "Google: Gemma 4 31B", "blended_price_per_m": 0.298, "sit_adjusted_price": 0.812601 }