mistral-large-3:675b

mistral-large-3:675b does not have a publicly published per-token price in our data source. This usually means it is gated behind enterprise sales or invite access. Check ollama-cloud's official pricing page for the most current rates.

mistral-large-3:675b has a context window of 262K tokens, with a max output of 262K tokens per reply. This is the total combined size of prompt + completion.

Yes. mistral-large-3:675b supports tool calling (function calling). This makes it suitable for production agent and automation workloads where the model has to invoke external functions reliably.

Support for structured output / JSON-schema-constrained decoding is not reported for mistral-large-3:675b in our data source. Verify with ollama-cloud's official documentation before relying on it in production.

Yes. mistral-large-3:675b accepts both text and image input. Vision pricing per image is usually billed on top of the regular token rate — check ollama-cloud's docs for the exact rule.

Yes. mistral-large-3:675b's weights are publicly available, so you can self-host or fine-tune. Note that open weights ≠ open source — the training data and code are typically not released.

If mistral-large-3:675b doesn't fit, consider ministral-3:14b, rnj-1:8b, ministral-3:8b. Each one targets the same use case — see the Related links below for direct head-to-head pages.

All numbers come from the public models.dev API and are normalised into a single canonical model record. We re-pull daily and write any changes (price, context, capability) to the /changelog page.