Devstral Small

Retired May 2026

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

Params: 24B
Context: 128K tokens
Max output: 33K
Released: May 2025
License: Apache 2.0

Hosted API pricing

How we price

Order

Providers are listed cheapest input rate first, then by output rate, a tie going to the creator's own listing. A provider that lists the model without a published rate sits at the end.

Prices

Base-tier, on-demand rates in USD per 1M tokens, converted at ECB reference rates where a provider publishes in another currency. Cached-input and batch rates show only where a provider publishes them. "Cheapest" marks the one provider with the lowest input and output pair; a tie wears no badge.

Cost

Input rate times the input tokens plus output rate times the output tokens, at the monthly volume set above the table. Cached-input, batch, long-context and reasoning-token billing are not modelled.

Transparency and funding

Affiliates: Affiliate links are marked. We may earn a commission if you click them, but commissions never affect the order.

Every provider serving Devstral Small, cheapest input first. Set your monthly volume to see what each would bill.

Input M Output M

Every provider serving Devstral Small, with its price per 1M input and output tokens and what the volume above would cost
Provider	Input /1M	Output /1M	Cost at 10M in + 2M out	Link
Mistral Creator	Open weights, no hosted price			Visit website

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 $115 a month.

Single node ≤ 8

What it costs to self-host Devstral Small at each precision: the memory it needs, the cheapest rental that holds it, that rental's month and the API volume it pays off at
Precision	Memory	Cheapest fit (32K context)(Full 128K context)	Cost /mo
4-bit INT4 / FP4	20 GB26 GB	2× RTX 3060	$115$187
8-bit FP8 / INT8	29 GB37 GB	2× RTX 4060 Ti	$187$374
16-bit FP16 / BF16	55 GB71 GB	4× RTX 4060 Ti	$374$461

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. Pricing methodology.

Salad

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

Capabilities

What Devstral Small accepts and can do, as published by Mistral.

Text Accepts and generates natural-language text.
Function calling Connect to external tools, APIs, and systems.
Code execution Write and execute code in a sandboxed environment.

Common 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, $0.16 per hour) costs about $115 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 $115 a month on the cheapest rental that fits.