What is Devstral Small good for?

Agent-style coding on your own hardware. Apache 2.0 weights, small enough for a single consumer GPU.

When is Devstral Small not a good fit?

Hosted use: Mistral retired it from its API in May 2026, which leaves self-hosting. Text only, and its maximum output caps very long single responses.

What is the cheapest way to run Devstral Small?

No provider we track hosts it; self-hosting on the cheapest rental that fits (2x RTX 3060, $0.12 per hour) costs about $86 a month.

Can I self-host Devstral Small?

Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 20 GB of GPU memory, which starts at roughly $86 a month on the cheapest rental that fits.

Retired May 2026 Open weights · Apache 2.0

Devstral Small

Mistral AI's 24B agentic coding model, updated in July 2025, with weights under Apache 2.0.

Jump to: Specs Pricing Self-hosting FAQ More from Mistral

Visit website Compare vs other LLMs →

Key Specifications

Context window: 128K tokens
Max output: 33K tokens
Released: May 2025
Parameters: 24B
Inputs: Text

Capabilities Show details: Function calling Connect to external tools, APIs, and systems. Code execution Write and execute code in a sandboxed environment.

Hosted API pricing

Input tokens M Output tokens M

Provider	Input / 1M tokens	Output / 1M tokens	Cost at 10M in + 2M out
Mistral Creator	Open weights, no hosted price			View

Heads up: Base-tier, on-demand rates per 1M tokens; cached, batch and long-context tiers excluded. A provider may serve a shorter context or a quantized build than the creator's release. Verify before provisioning. More on how we price.

Estimated cost to self-host

Devstral Small needs about 20 GB of GPU memory at 4-bit with 32K context. The cheapest rental that fits is 2× RTX 3060 at about $86 a month.

Single node ≤ 8

Precision	Memory	Cheapest fit (32K context)(Full 128K context)	Cost / mo
4-bitINT4 / FP4	20 GB26 GB	2× RTX 3060	$86$158
8-bitFP8 / INT8	29 GB37 GB	2× RTX 4060 Ti	$158$288
16-bitFP16 / BF16	55 GB71 GB	4× RTX 4060 Ti	$317$346

Estimates based on median on-demand rates for Nvidia GPUs. Memory is weights plus KV cache for one request, using FP8 KV cache where supported and FP16/BF16 otherwise. No guarantee of runtime support, usable performance, or that a matching quantized build exists. How we estimate costs.

Salad

Our sponsor

Access 60,000+ daily active GPUs across 191 countries, from $0.02/hour

Run RTX 50-series and 40-series cards without datacenter pricing

Pick a priority level to balance cost against interruptions

Per-second billing, with no charge for cold starts or image pulls

View Pricing

Frequently Asked Questions

What is Devstral Small good for?: Agent-style coding on your own hardware. Apache 2.0 weights, small enough for a single consumer GPU.
When is Devstral Small not a good fit?: Hosted use: Mistral retired it from its API in May 2026, which leaves self-hosting. Text only, and its maximum output caps very long single responses.
What is the cheapest way to run Devstral Small?: No provider we track hosts it; self-hosting on the cheapest rental that fits (2x RTX 3060, $0.12 per hour) costs about $86 a month.
Can I self-host Devstral Small?: Yes. The weights are Apache 2.0 licensed. At 4-bit it needs about 20 GB of GPU memory, which starts at roughly $86 a month on the cheapest rental that fits.

More from Mistral

Model	Context	Input / 1M	Output / 1M
Ministral 3 14B Open weights	256K	$0.20	$0.20
Ministral 3 3B Open weights	256K	$0.10	$0.10
Ministral 3 8B Open weights	256K	$0.15	$0.15
Mistral Large 3 Open weights	256K	$0.50	$1.50
Mistral Medium 3.5 Open weights	256K	$1.50	$7.50
Mistral Small 4 Open weights	256K	$0.15	$0.60
Codestral	128K	$0.30	$0.90
Devstral Medium	128K