Mistral 7B — Specifications
| Developer | Mistral AI |
|---|---|
| Type | LLM (dense) |
| Modality | Text → Text |
| Parameters | 7B |
| Context window | 32K |
| Max output | — |
| License | Apache 2.0 (open) |
| Open weights | Yes |
| Released | 2023 |
| Input price | $0.02 /1M |
| Output price | $0.03 /1M |
| API providers | Mistral, DeepInfra, OpenRouter, Ollama |
Run it locally
| VRAM (4-bit) | ~4.5 GB |
|---|---|
| Minimum GPU | Any 6GB GPU |
What is Mistral 7B?
Mistral 7B is the model that kicked off the open-LLM wave — 7B parameters, Apache 2.0, a
32K context and a footprint of about 4.5 GB at 4-bit that runs on a 6 GB GPU. It is still a
solid, ultra-cheap baseline at $0.02 in / $0.03 out per million tokens.
Its remaining role is as a floor rather than a recommendation. The 32K context is the
binding constraint: every comparable small model now ships with 128K, so anything involving
documents, long conversations or substantial retrieval will hit the wall on Mistral 7B first.
Where it still earns a place is in tightly scoped, high-volume classification and routing
tasks with short inputs, on constrained hardware, or as the historical baseline in an
evaluation — if a newer model cannot beat Mistral 7B on your data, the problem is probably
your prompt or your data, not the model. For new local deployments, Qwen3 8B and Llama 3.1 8B
occupy the same hardware bracket with four times the context, and are the better starting
point.
Mistral 7B pricing: API cost per 1M tokens
| Input (per 1M tokens) | $0.0200 |
|---|---|
| Output (per 1M tokens) | $0.0300 |
| Output/input ratio | 1.5× |
| Blended (4:1 in:out) | $0.0220 per 1M tokens |
What Mistral 7B costs per month
Real monthly spend at a 4:1 input-to-output mix — the ratio a typical chat or RAG workload actually produces.
| Workload | Tokens / month | Cost / month |
|---|---|---|
| Side project | 1M in / 0.25M out | $0.03 |
| Small team | 20M in / 5M out | $0.55 |
| Production | 200M in / 50M out | $5.50 |
Run your own numbers in the AI API cost calculator.
Self-host or pay the API?
Mistral 7B is open-weight, so you can run it yourself. It needs ~4.5 GB of VRAM at 4-bit (Any 6GB GPU). Self-hosting only beats the API once your volume is high enough to keep that hardware busy — the self-hosting vs API calculator works out the break-even point for your token volume.
Frequently asked questions
How much does Mistral 7B cost per 1M tokens?
Mistral 7B costs $0.0200 per 1M input tokens and $0.0300 per 1M output tokens. At a typical 4:1 input-to-output mix that blends to about $0.0220 per 1M tokens.
How much does Mistral 7B cost per month?
A small-team workload of 20M input and 5M output tokens a month costs about $0.55 on Mistral 7B. A side project (1M in / 0.25M out) costs roughly $0.03.
Can I run Mistral 7B locally?
Yes. Mistral 7B is open-weight and needs about ~4.5 GB of VRAM at 4-bit quantisation (Any 6GB GPU).
Why does Mistral 7B charge more for output than input?
Output tokens are generated one at a time and cannot be batched the way a prompt can, so they cost the provider more to serve. Mistral 7B charges 1.5× more for output, which is why prompt-heavy workloads are far cheaper to run than generation-heavy ones.
Prices are the published list rates for the model's primary API and are reviewed as providers change them. Volume, batch and cached-input discounts are not included. Compare every model side by side in the AI models database or the LLM leaderboard.
