LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Mistral Large 3

mistral·mistral/mistral-large-2512·GA·Open weights·mistral-large series
Mistral's largest general model for enterprise agents, coding, and multilingual reasoning

Specs & pricing

Input / output per 1M tokens
Official price·Mistral
$0.50 / $1.50
Blended $0.75 · Cache read $0.05
Lowest paid·MistralFirst-party
$0.50 / $1.50
Blended $0.75 · 2.2× spread
Context
262,144
Output limit
262,144
Knowledge cutoff
2024-11
Released / updated
2025-12-02 / 2025-12-02
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF
Weights
Hugging Face

Mistral Large 3 is offered by 16 providers on this page. Public prices are shown for 15 of them. Its official list price is $0.50 per 1M input tokens and $1.50 per 1M output tokens. No paid channel is priced below the official list price. Prices vary about 2.2× across the providers that host it.

Median output speed is 86 tokens per second, with 1.13s to the first token.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 128,000 to 262,144, so the usable window depends on the provider you pick. It supports tool use and structured output. Accepted input modalities are Text, Image, and PDF. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use. Its training knowledge cuts off at 2024-11.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed86 tok/s
TTFT1.13 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 16 providers15 with public prices

  • ProviderInput / Output
  • MistralOfficialFirst-party
    $0.50 / $1.50
    Cache read $0.05Context 262,144Output limit 262,144
  • LLM GatewayGateway
    $0.50 / $1.50
    Context 262,144Output limit 262,144
  • Amazon BedrockCloud
    mistral.mistral-large-3-675b-instruct
    $0.50 / $1.50
    Context 262,144Output limit 8,192
  • DevPass (LLM Gateway)Gateway
    $0.50 / $1.50
    Context 262,144Output limit 262,144
  • Merge GatewayGateway
    $0.50 / $1.50
    Cache read $0.05Context 256,000 ⚠Output limit 256,000
  • OpenRouterGateway
    $0.50 / $1.50
    Cache read $0.05Context 262,144Output limit 209,715
  • OpperGateway
    $0.50 / $1.50
    Context 256,000 ⚠Output limit 8,192
  • Prime InferenceGateway
    $0.50 / $1.50
    Context 262,144Output limit 209,715
  • Eden AIGateway
    $0.50 / $1.50
    Cache read $0.05Context 262,144Output limit 262,144
  • Kilo GatewayGateway
    $0.50 / $1.50
    Cache read $0.05Context 262,144Output limit 209,715
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
MistralOfficialFirst-party$0.50$1.50$0.05—262,144262,144
LLM GatewayGateway$0.50$1.50——262,144262,144
Amazon Bedrock
mistral.mistral-large-3-675b-instruct
Cloud$0.50$1.50——262,1448,192
DevPass (LLM Gateway)Gateway$0.50$1.50——262,144262,144
Merge GatewayGateway$0.50$1.50$0.05—256,000 ⚠256,000
OpenRouterGateway$0.50$1.50$0.05—262,144209,715
OpperGateway$0.50$1.50——256,000 ⚠8,192
Prime InferenceGateway$0.50$1.50——262,144209,715
Eden AIGateway$0.50$1.50$0.05—262,144262,144
Kilo GatewayGateway$0.50$1.50$0.05—262,144209,715

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

Common scenarios
1Mistral · Official$121.00
2Merge Gateway$121.00
3OpenRouter$121.00
4Eden AI$121.00
5Kilo Gateway$121.00
6Vercel AI Gateway$121.00
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$1.50$02026-08-052026-08-13
2026-08-13Input list $0.50Output list $1.50Min blended $0.75

Benchmark3 items

NameConditionsScoreMetricSource
Artificial Analysis Coding Index—22.7indexSource ↗
SciCode—36.2percent correctSource ↗
Terminal-Bench Hard—15.9success rateSource ↗

The same benchmark scores very differently across harness / dataset, so the qualifying conditions must be shown together.

Related models

Mistral Large 4same series$0.70 / $2.10Mistral Large (latest)same series—Mistral Large 2.1same series—Nova Litecheaper alternative$0.06 / $0.24Ministral 3 14Bcheaper alternative$0.20 / $0.20Lyria 3 Clip Previewcheaper alternative$0 / $0Lyria 3 Pro Previewcheaper alternative$0 / $0
Data partly from models.dev (MIT) · Mistral official docs ↗