MiniMax M3
Wandb textwandb/MiniMaxAI/MiniMax-M3
Input
$0.2300
per 1M input tokens
Output
$0.9600
per 1M output tokens
Cache read
$0.0500
per 1M cached read tokens
Cache write
n/a
per 1M cache write tokens
Context window
262,000
Max output
262,144
Effective date
Oct 27, 2026
Estimate a workload
Enter token counts to see the cost at this model's rates.
Estimated cost:
$0.00
Price history
blended $ per 1M tokens (3:1)| Effective | Input | Output | Blended |
|---|---|---|---|
| Oct 27, 2026 | $0.23 | $0.96 | $0.41 |
| Sep 18, 2026 | $0.23 | $0.96 | $0.41 |
| Aug 28, 2026 | $0.23 | $0.96 | $0.41 |
MiniMax M3 on other providers
Empiriolabs
· $0.2250 in / $0.9000 out
Gmi
· $0.2400 in / $0.9600 out
Deepinfra
· $0.2800 in / $1.10 out
Aihubmix
· $0.2880 in / $1.15 out
Opencode Go
· $0.3000 in / $1.20 out
Fireworks Ai
· $0.3000 in / $1.20 out
Fireworks Ai
· $0.3000 in / $1.20 out
Minimax
· $0.3000 in / $1.20 out
Nebius
· $0.3000 in / $1.20 out
Together Ai
· $0.3000 in / $1.20 out
Tencent
· $0.3000 in / $1.20 out
Novita
· $0.3000 in / $1.20 out
Other Wandb models
wandb/openai/gpt-oss-120b
· $0.1700/Mtok out
wandb/openai/gpt-oss-20b
· $0.1300/Mtok out
wandb/ibm-granite/granite-4.1-8b
· $0.1000/Mtok out
wandb/JetBrains/Mellum2-12B-A2.5B-Instruct
· $0.1000/Mtok out
wandb/OpenPipe/Qwen3-14B-Instruct
· $0.2200/Mtok out
wandb/ibm-granite/granite-4.2-8b
· $0.1500/Mtok out
Source: litellm. Confirm against the provider's official pricing before relying on these figures.