Mistral 7B v0.3.
The current Mistral 7B — adds function calling + extended vocab.
1× Nvidia P102-100.
Most-aggressive quantisation we have a working recommendation for. Lower precision = less VRAM = cheaper hardware, at a small accuracy cost.
Cheapest hosted endpoints.
| Provider | Access | $/M in | $/M out | |
|---|---|---|---|---|
| Mistral AI API | api direct | $0.2 | $0.6 | Launch ↗ |
| Together AI | hosted inference | $0.2 | $0.2 |
Smaller models distilled from Mistral 7B v0.3.
Lightweight student models trained to mimic Mistral 7B v0.3's outputs.
Variants in the Mistral 7B family.
Frequently asked.
How do I run Mistral 7B v0.3?
Where can I access Mistral 7B v0.3?
How much does it cost to run Mistral 7B v0.3?
Is Mistral 7B v0.3 open-source or proprietary?
Cheapest hardware per quantisation.
Each row is one quantisation tier (the same weights compressed differently). Lower precision → lower VRAM → cheaper hardware, at the cost of small accuracy loss. $/hr refreshed hourly from each provider's API.
| Quantisation | Cheapest GPU config | Total VRAM | Live $/hr | tokens/sec | |
|---|---|---|---|---|---|
|
FP16
FP16 — half precision (default)
|
24 GB | — | — | Compare → | |
|
FP8
FP8 — 8-bit float (Hopper / Blackwell)
|
10 GB | — | — | Compare → | |
|
INT8
INT8 — 8-bit integer
|
16 GB | $0.070/hr | — | Compare → | |
|
INT4
INT4 — 4-bit integer (~4× VRAM saving)
|
5 GB | — | — | Compare → |
What it costs per month across providers.
Estimate your monthly bill for Mistral 7B v0.3 across every host that publishes per-token pricing. Slide your token volumes; the chart + table re-rank cheapest-first.
Cheapest provider on the left.
Total monthly cost — input + output tokens combined.
Bill breakdown.
| Provider | Monthly total | |
|---|---|---|
| $2.4 | ||
| $3.2 | Sign up ↗ |
Rent the GPU instead of paying per token.
For an open-weights model like Mistral 7B v0.3, you can rent a GPU and serve inference yourself. The math: cheapest GPU rental × 730 hours/month + your electricity rate × power draw.
Assumes the GPU runs 24/7 at ~85% utilisation. If your traffic is bursty, you'll pay less for the API and probably more for the GPU (idle hours still cost rental). The breakeven analysis lives on the Self-host vs API breakeven tool.
About Mistral 7B v0.3.
Mistral 7B v0.3 is the current revision of the foundational Mistral 7B model. v0.3 added extended vocabulary (32K → 32768 tokens) and function calling support. Apache-2.0 licensed, runs on any GPU with ≥16 GB VRAM at FP16. Still one of the best 7B-class open-weight models for general chat and instruction-following.