Mara pricing overview
TokenWatch tracks 4 text, 0 image, and 0 video model records for this provider. TokenWatch does not have a provider-wide zero-retention verdict for this page.
Cheapest input price: gpt-oss-120b at $0.150 per million input tokens and $0.750 per million output tokens. 0 of 4 text models publish a cache-read price; 4 carry a zero-data-retention tag.
Mara text-model pricing
Text offerings ranked by the Agentic workload mix (2.5% input, 97% cached input, 0.5% output). Change the calculator mix for a workload-specific estimate.
| Org | Provider | Model | Input $/M | Output $/M | Cache $/M | Blended $/M |
|---|---|---|---|---|---|---|
| openai | mara | OpenAI: gpt-oss-120b | $0.150 | $0.750 | — | $0.153 |
| deepseek | mara | DeepSeek: DeepSeek V3.1 | $0.600 | $1.70 | — | $0.605 |
| minimax | mara | MiniMax: MiniMax M3 | $0.600 | $2.40 | — | $0.609 |
| deepseek | mara | DeepSeek: DeepSeek V3.2 | $3.00 | $4.50 | — | $3.01 |
Catalog snapshot 2026-10-29 from direct-provider APIs, OpenRouter endpoint data, and maintained fallbacks. See the sources and calculation rules; verify rates on the provider's official pricing page before committing spend.