Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi-step reasoning. It is particularly strong at reliable multi-tool calling and long-horizon tasks, with a 256K context window, configurable reasoning effort per request, and a custom vision encoder that handles variable image sizes and aspect ratios. Self-hostable on as few as four GPUs and available under open weights.
$0.75
$0.75
$3.75
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.
Not enough throughput data
Not enough TTFT data
Works with the OpenAI SDK pointed at our base URL. Every parameter is in the API reference.
Tokens processed per day on NagaAI.
Mistral Medium 3.5 is a dense 128B instruction-following model from Mistral AI. It supports text and image inputs with text output, and is designed for agentic workflows, coding, and complex multi-step reasoning.
On NagaAI, Mistral Medium 3.5 costs $0.75 per 1M input tokens and $3.75 per 1M output tokens. You pay only for what you use, with no subscription.
Mistral Medium 3.5 reads up to 262.1k tokens in one request, counting the prompt and the answer together.
Yes. Mistral Medium 3.5 can call your functions as tools and can answer in a JSON schema you give it.
It takes text, images and files 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 2603MistralAIDevstral 2 2512MistralAI$0.20 / $1 per 1MMinistral 3 14B 2512MistralAI$0.10 / $0.10 per 1MMinistral 3 3B 2512MistralAI$0.05 / $0.05 per 1MMistral Large 12-2025MistralAINot enough activity data to display a chart