FriendliAI
Gemma 4 31B (FriendliAI) token cost
Gemma 4 31B on FriendliAI for fast open multimodal-class inference.
Published list rates
Input
$0.14
per 1M tokens
Output
$0.4
per 1M tokens
Context window
128,000
tokens
Pricing source: FriendliAI pricing
Estimate cost
Estimate from text
Calculate from a token total
Project monthly volume
Daily requests × tokens per request × 30 days.
Estimated cost
- Estimated tokens
- —
- Characters
- —
- Words
- —
- Input tokens
- —
- Output tokens
- —
- Input cost
- —
- Output cost
- —
- Total cost
- —
- Combined price per 1M tokens
- —
- Estimated monthly cost
- —
- Estimated daily cost
- —
Cost as volume grows
Read down to see Gemma 4 31B (FriendliAI) get more expensive as tokens grow. The last column is a typical mix: 70% input, 30% output.
| Tokens | Input only | Output only | Mix (70% in / 30% out) |
|---|---|---|---|
| 1 | $0.00000014 | $0.0000004 | $0.000000218 |
| 10 | $0.000001 | $0.000004 | $0.000002 |
| 100 | $0.000014 | $0.00004 | $0.000022 |
| 200 | $0.000028 | $0.00008 | $0.000044 |
| 300 | $0.000042 | $0.00012 | $0.000065 |
| 400 | $0.000056 | $0.00016 | $0.000087 |
| 500 | $0.00007 | $0.0002 | $0.000109 |
| 1,000 | $0.00014 | $0.0004 | $0.000218 |
| 2,000 | $0.00028 | $0.0008 | $0.000436 |
| 5,000 | $0.0007 | $0.002 | $0.00109 |
| 10,000 | $0.0014 | $0.004 | $0.00218 |
| 25,000 | $0.0035 | $0.01 | $0.00545 |
| 50,000 | $0.007 | $0.02 | $0.0109 |
| 100,000 | $0.014 | $0.04 | $0.0218 |
| 250,000 | $0.035 | $0.1 | $0.0545 |
| 500,000 | $0.07 | $0.2 | $0.109 |
| 1,000,000 | $0.14 | $0.4 | $0.218 |
| 5,000,000 | $0.7 | $2.00 | $1.09 |
| 10,000,000 | $1.40 | $4.00 | $2.18 |
| 50,000,000 | $7.00 | $20.00 | $10.90 |
| 100,000,000 | $14.00 | $40.00 | $21.80 |
| 500,000,000 | $70.00 | $200.00 | $109.00 |
| 1,000,000,000 | $140.00 | $400.00 | $218.00 |
| 10,000,000,000 | $1,400.00 | $4,000.00 | $2,180.00 |
| 100,000,000,000 | $14,000.00 | $40,000.00 | $21,800.00 |
Tokens for a fixed budget
Tokens Gemma 4 31B (FriendliAI) can process for a set budget — send-only, reply-only, and a 70/30 mix.
| Budget | Input tokens | Output tokens | Mixed tokens (70/30) |
|---|---|---|---|
| $0.01 | 71,429 | 25,000 | 45,872 |
| $0.1 | 714,286 | 250,000 | 458,716 |
| $0.5 | 3.57M | 1.25M | 2.29M |
| $1.00 | 7.14M | 2.5M | 4.59M |
| $5.00 | 35.7M | 12.5M | 22.9M |
| $10.00 | 71.4M | 25M | 45.9M |
| $20.00 | 142.9M | 50M | 91.7M |
| $25.00 | 178.6M | 62.5M | 114.7M |
| $30.00 | 214.3M | 75M | 137.6M |
| $50.00 | 357.1M | 125M | 229.4M |
| $100.00 | 714.3M | 250M | 458.7M |
| $250.00 | 1.79B | 625M | 1.15B |
| $500.00 | 3.57B | 1.25B | 2.29B |
| $1,000.00 | 7.14B | 2.5B | 4.59B |
| $5,000.00 | 35.7B | 12.5B | 22.9B |
| $10,000.00 | 71.4B | 25B | 45.9B |
At these rates
- A workload with 70% input and 30% output costs $0.218 per 1 million total tokens and $21.80 per 100 million.
- At the same token count, output costs 2.86 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 128,000-token context window with input alone would cost about $0.01792, before any output.
These figures use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the invoice.