Skip to content
ModelCap

Inference provider

Mistral: AI models and API pricing

Every tracked model Mistral serves through OpenRouter, with Mistral's own input and output price per 1M tokens, the context window it serves, disclosed quantization and measured endpoint uptime. Rows link to the model page, where every provider's deployment is listed side by side.

Snapshot as of 1 October 2026

Mistral serves 19 tracked models through 47 endpoints as of 1 October 2026; the highest-ranked is GLM 5.3 (ModelCap Index #11); mean measured uptime is 99.72%.

Models served
19
On the ModelCap Index
6
Cheapest output price
$0.10/1M

Language models on Mistral (19)

Ranked models first, in ModelCap Index order. Prices are the lowest Mistral lists for the model; the endpoint count shows how many deployments carry it.

Language models served by Mistral, with price, context, quantization and uptime
#ModelModelCap IndexInput $/1MOutput $/1MContextQuantizationUptime (30 min)Endpoints
1GLM 5.3Z.ai#1180.9$1.40$4.401Mnvfp499.01%2
2Mistral Medium 3.5Mistral AI#6561.9$1.50$7.50262K—100.0%3
3Mistral Large 3 2512Mistral AI#7459.9$0.50$1.50262K—100.0%2
4Mistral Small 4Mistral AI#9455.0$0.15$0.60262K—100.0%4Open weights
5Mistral Small 3.2 24BMistral AI#14143.1$0.10$0.3033K——1Open weights
6Mixtral 8x22B InstructMistral AI#22915.7$2.00$6.0066K——3Open weights
7Codestral 2508Mistral AI—$0.30$0.90256K—100.0%2
8Devstral 2 2512Mistral AI—$0.40$2.00262K—100.0%1
9Ministral 3 14B 2512Mistral AI—$0.20$0.20262K—99.15%3Open weights
10Ministral 3 3B 2512Mistral AI—$0.10$0.10131K—100.0%3Open weights
11Ministral 3 8B 2512Mistral AI—$0.15$0.15262K—99.06%3Open weights
12Mistral NemoMistral AI—$0.15$0.15131K——1Open weights
13SabaMistral AI—$0.20$0.6033K——3
14Voxtral Small 24B 2507Mistral AI—$0.10$0.3033K—99.62%3Open weights
15GLM 5.2Z.ai—$1.40$4.401Mnvfp4100.0%2Open weights
16Mistral LargeMistral AI—$2.00$6.00128K—100.0%2
17Mistral Large 2407Mistral AI—$2.00$6.00131K——3
18Mistral Medium 3Mistral AI—$0.40$2.00131K——3
19Mistral Medium 3.1Mistral AI—$0.40$2.00131K—99.94%3

Mistral on ModelCap: common questions

How many AI models does Mistral serve?

19 tracked models as of 1 October 2026: 19 language models (6 with a public ModelCap Index position), across 47 live endpoints observed through OpenRouter.

What is the best model available on Mistral?

GLM 5.3 from Z.ai is the highest-ranked language model Mistral serves, at ModelCap Index position #11 and $4.40 per 1M output tokens on Mistral. The table lists every model in Index order.

What is the cheapest model on Mistral?

Ministral 3 3B 2512 at $0.10 per 1M output tokens ($0.10 per 1M input), the lowest positive language-token price Mistral lists. Free-tier endpoints, where present, show as $0 and are excluded from that comparison.

Which Mistral model has the largest context window?

GLM 5.3, served with a 1M-token context window on Mistral. Providers sometimes serve less than the model's published maximum, so the figure here is the provider's own.

How reliable is Mistral?

Mean measured uptime across Mistral endpoints is 99.72% over the last 30 minutes, as reported by OpenRouter at the time of the snapshot. Per-model uptime is in the table; it is a live operational signal, not a service-level guarantee.

Where do the Mistral prices come from?

From the OpenRouter catalogue entry for each Mistral endpoint, in USD per 1M tokens, re-observed on every ModelCap refresh. Where Mistral exposes several deployments of one model at different prices, the table shows the lowest and notes the count; the model page lists each deployment.

How current is this page?

This page uses the published ModelCap snapshot dated 1 October 2026. Publication and page updates happen separately. Offers retained from a failed refresh are marked stale in the data and are not counted here.

Explore further