InclusionAI
Ling 3.0 Flash token cost
Ling 3.0 Flash: 124B MoE with 5.1B active per token, at $0.06/$0.18 per 1M on Novita serverless.
Published list rates
Input
$0.06
per 1M tokens
Output
$0.18
per 1M tokens
Cached input
$0.012
per 1M tokens
Context window
256,000
tokens
Pricing source: Novita serverless 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 Ling 3.0 Flash 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 | $0.00000006 | $0.00000018 | $0.000000096 |
| 10 | $0.0000006 | $0.000002 | $0.00000096 |
| 100 | $0.000006 | $0.000018 | $0.00001 |
| 200 | $0.000012 | $0.000036 | $0.000019 |
| 300 | $0.000018 | $0.000054 | $0.000029 |
| 400 | $0.000024 | $0.000072 | $0.000038 |
| 500 | $0.00003 | $0.00009 | $0.000048 |
| 1,000 | $0.00006 | $0.00018 | $0.000096 |
| 2,000 | $0.00012 | $0.00036 | $0.000192 |
| 5,000 | $0.0003 | $0.0009 | $0.00048 |
| 10,000 | $0.0006 | $0.0018 | $0.00096 |
| 25,000 | $0.0015 | $0.0045 | $0.0024 |
| 50,000 | $0.003 | $0.009 | $0.0048 |
| 100,000 | $0.006 | $0.018 | $0.0096 |
| 250,000 | $0.015 | $0.045 | $0.024 |
| 500,000 | $0.03 | $0.09 | $0.048 |
| 1,000,000 | $0.06 | $0.18 | $0.096 |
| 5,000,000 | $0.3 | $0.9 | $0.48 |
| 10,000,000 | $0.6 | $1.80 | $0.96 |
| 50,000,000 | $3.00 | $9.00 | $4.80 |
| 100,000,000 | $6.00 | $18.00 | $9.60 |
| 500,000,000 | $30.00 | $90.00 | $48.00 |
| 1,000,000,000 | $60.00 | $180.00 | $96.00 |
| 10,000,000,000 | $600.00 | $1,800.00 | $960.00 |
| 100,000,000,000 | $6,000.00 | $18,000.00 | $9,600.00 |
Tokens for a fixed budget
Tokens Ling 3.0 Flash 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 | 166,667 | 55,556 | 104,167 |
| $0.1 | 1.67M | 555,556 | 1.04M |
| $0.5 | 8.33M | 2.78M | 5.21M |
| $1.00 | 16.7M | 5.56M | 10.4M |
| $5.00 | 83.3M | 27.8M | 52.1M |
| $10.00 | 166.7M | 55.6M | 104.2M |
| $20.00 | 333.3M | 111.1M | 208.3M |
| $25.00 | 416.7M | 138.9M | 260.4M |
| $30.00 | 500M | 166.7M | 312.5M |
| $50.00 | 833.3M | 277.8M | 520.8M |
| $100.00 | 1.67B | 555.6M | 1.04B |
| $250.00 | 4.17B | 1.39B | 2.6B |
| $500.00 | 8.33B | 2.78B | 5.21B |
| $1,000.00 | 16.7B | 5.56B | 10.4B |
| $5,000.00 | 83.3B | 27.8B | 52.1B |
| $10,000.00 | 166.7B | 55.6B | 104.2B |
At these rates
- A workload with 70% input and 30% output costs $0.096 per 1 million total tokens and $9.60 per 100 million.
- At the same token count, output costs 3 times the input rate. Response length therefore deserves its own budget limit.
- Filling the 256,000-token context window with input alone would cost about $0.01536, before any output.
- Cached input is $0.012 per million, 80% below standard input when the workload meets the provider’s cache rules.
MIT-licensed open weights. Rates shown are Novita's Standard serverless list; OpenRouter lists $0.021/$0.063 per 1M. Cache reads are $0.012 per 1M on Novita.
These figures use public list prices. Cache eligibility, batch or priority modes, long-context surcharges, discounts, and regional billing can change the invoice.