Devstral Small

Last verified August 24, 2026 · Mistral pricing ↗

$0.100/1M input · $0.300/1M output · 256K context · Mistral

Devstral Small last cost $0.100 per 1M input tokens and $0.300 per 1M output tokens from Mistral, with a 256K-token context window. A typical chat reply (1,500 tokens in, 400 out) costs $0.0003, or $2.70 per 10,000 requests.

Retired

Not generally available

Mistral has shut Devstral Small down. You cannot buy it at the rate below. The price is kept so past spend and old estimates still reconcile, and it is excluded from the calculator’s default model list and from every ranking.

Mistral’s own page ↗

Count Tokens

Tokens

—

Input Cost

—

Output Cost

—

Tokens

—

Input Cost

—

Output Cost

Estimate Monthly Cost

Monthly Cost Estimator

Quick:

API calls / dayAvg input tokens / callAvg output tokens / call

<$0.0001/mo

Pick a preset above or enter custom usage

What Devstral Small Costs Per Request

At $0.100 per 1M input and $0.300 per 1M output tokens, before caching or batch discounts.

Workload	Input / output tokens	Per request	Per 10,000 requests
Chat reply	1,500 / 400	$0.0003	$2.70
RAG answer over retrieved docs	8,000 / 600	$0.0010	$9.80
Coding-agent step	30,000 / 2,000	$0.0036	$36.00

Devstral Small vs Similarly Priced Models

Nearest buyable models by price, with the RAG answer above (8,000 in / 600 out) priced on each.

Model	Input /1M	Output /1M	Context	RAG answer
Devstral Small Mistral	$0.100	$0.300	256K	$0.0010
Ministral 3 14B Mistral	$0.200	$0.200	262K	$0.0017
Llama 4 Scout Meta	$0.080	$0.300	1.0M	$0.0008
MiMo-V2.6-Flash Xiaomi	$0.140	$0.280	1.0M	$0.0013

Alternatives to Devstral Small

Cheaper Alternative

Llama 4 Scout

$0.080 in · $0.300 out · Meta

5% cheaper with same or larger context

Premium Upgrade

MiMo-V2.6-Flash

$0.140 in · $0.280 out · Xiaomi

Upgrade with 1049K context and 131K max output

Same Provider

Ministral 3 14B

$0.200 in · $0.200 out · Mistral

Higher tier in Mistral ecosystem

Pricing Details

MistralRETIRED: Mistral deprecated Devstral Small 2 on February 27, 2026 and retired it on March 31, 2026, and it is absent from mistral.ai/pricing/api. This row carried a buyable $0.10/$0.30 for roughly five months after the retirement date, because the July 27 check read the price card rather than the lifecycle table. Listed for historical cost comparison only. Estimated tokens.

Input / 1M tokens

$0.1

Output / 1M tokens

$0.3

Context Window

256K

Max Output

33K

Full Pricing Table Token Calculator

Price History

No price change recorded since 2026-07-27, when this site started tracking this model.

Frequently Asked Questions

Common questions about Devstral Small pricing and usage

How much does Devstral Small cost?

Devstral Small costs $0.1 per 1 million input tokens and $0.3 per 1 million output tokens. This pricing is set by Mistral.

What tokenizer does Devstral Small use?

Devstral Small uses the cl100k_base tokenizer. This tokenizer has a vocabulary of ~100,000 tokens and is widely used across many models.

What is Devstral Small's context window?

Devstral Small supports a context window of 256K tokens (256,000 tokens). The maximum output length is 33K tokens.

How does Devstral Small compare to other models?

On an 8,000-token-in, 600-token-out RAG answer, Devstral Small costs $0.0010 per request. The nearest-priced alternatives cost: Ministral 3 14B (Mistral) $0.0017, Llama 4 Scout (Meta) $0.0008, MiMo-V2.6-Flash (Xiaomi) $0.0013. The table above lists their full rates and context windows.

How do I count tokens for Devstral Small?

Use the token counter at the top of this page or visit the homepage calculator. Paste your text and it will show the exact token count and cost for Devstral Small using the cl100k_base tokenizer.

Full Pricing Table Compare Models Cost Calculator Mistral Token Counter