Ministral 8B is an 8B parameter model with a unique interleaved sliding-window attention pattern for faster and more memory-efficient inference. Optimized for edge use cases, it supports up to 128k context length and delivers strong performance in knowledge and reasoning tasks. Exceeding other models in the sub-10B category, it is ideal for low-latency and privacy-focused applications.
$0.075market price $0.15
$0.0075market price $0.015
$0.075market price $0.15
Throughput is how fast the model writes (tokens per second, higher is better). Time to first token is how long before the answer starts (lower is better).
Share of requests served without a server error. Client errors (4xx) do not count.
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Daily usage of this model on NagaAI.
Ministral 8B is an 8B parameter model with a unique interleaved sliding-window attention pattern for faster and more memory-efficient inference. Optimized for edge use cases, it supports up to 128k context length and delivers strong performance in knowledge and reasoning tasks.
On NagaAI, Ministral 8B 2410 costs $0.075 per 1M input tokens and $0.075 per 1M output tokens. You pay only for what you use, with no subscription.
Ministral 8B 2410 reads up to 131.1k tokens in one request, counting the prompt and the answer together.
Yes. Ministral 8B 2410 can call your functions as tools and can answer in a JSON schema you give it.
It takes text as input and returns text.
Create an API key, copy the model ID from the top of this page and send requests with the OpenAI or Anthropic SDK pointed at NagaAI. The API section on this page has a ready example.
Mistral Large 4MistralAIMistral Small 2603MistralAIMistral Large 12-2025MistralAIOpen Mistral Nemo 2407MistralAI$0.0175 / $0.04 per 1MCodestral 2501MistralAI
Kimi K3.1 ProMoonShotAI