MiniMax API pricing
12 MiniMax models: text, video, text to speech, from price book 2026-10-22.
Billing rules Veqen applies
- Token models: cached input at the cache-read rate, cache writes at the write rate; batch and service tiers at their own rates where published; long-context rates once the full prompt passes the threshold.
- Video models: per second of generated video, at the requested resolution's rate.
- Audio models: per second of audio or per character of text, or per token where the model bills tokens.
Reconcile your bill
MiniMax doesn't offer a cost API, so Veqen's ledger is your running record of spend. Enter each month's bill to reconcile it and book it in the close. How reconciliation works.
Prices come from MiniMax's pricing page. Negotiated rates or committed-use discounts can be set as custom prices.
Text 6 models
| Model | Input | Output | Cached input | Batch input | Context | Status |
|---|---|---|---|---|---|---|
| MiniMax-M2 | $0.30 | $1.20 | $0.03 | — | 200K | |
| MiniMax-M2.1 | $0.30 | $1.20 | $0.03 | — | 1M | |
| MiniMax-M2.1-lightning | $0.30 | $2.40 | $0.03 | — | 1M | |
| MiniMax-M2.5 | $0.30 | $1.20 | $0.03 | — | 1M | |
| MiniMax-M2.5-lightning | $0.30 | $2.40 | $0.03 | — | 1M | |
| MiniMax-M3 | $0.30 | $1.20 | $0.06 | — | 1M |
Video 2 models
| Model | Price | Status |
|---|---|---|
| MiniMax-H3 | $0.08 per second | |
| MiniMax-H3-Max | $0.08 per second |
Text to speech 4 models
| Model | Price | Status |
|---|---|---|
| speech-02-hd | $100.00 per 1M characters | |
| speech-02-turbo | $60.00 per 1M characters | |
| speech-2.6-hd | $100.00 per 1M characters | |
| speech-2.6-turbo | $60.00 per 1M characters |