Mistral 7B Instruct v0.3
Input, lowest
—
Output, lowest
—
Providers
1
Providers & prices
| Provider | Input | Output | Context | Last sync | |
|---|---|---|---|---|---|
D
DigitalOcean
|
— | — | 32,768 |
About this model
Mistral-7B-Instruct-v0.3 is an instruction-tuned variant of Mistral-7B-v0.3: a dense Mistral architecture text LLM with extended vocabulary (32768), the v3 tokenizer, and native function-calling support via the chat template (tools, tool calls, and tool results with 9-character tool call IDs). It is aimed at chat and tool-augmented workflows; the model card notes it is a lightweight instruct demo without built-in moderation. Licensed under Apache 2.0.