LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Mistral Medium 3.5

mistral·mistral/mistral-medium-3-5·GA·Closed·mistral-medium series
Mistral model for multilingual chat, reasoning, and tool-assisted workflows

Specs & pricing

Input / output per 1M tokens
Official price
—
Lowest paid·LLM GatewayGateway
$1.50 / $7.50
Blended $3.00 · 1.1× spread
Context
262,144
Output limit
209,715
Knowledge cutoff
—
Released / updated
2026-04-30 / 2026-04-30
Capabilities
✓ Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF

Mistral Medium 3.5 is offered by 11 providers on this page. No official API price is listed for it; the prices below come from third-party channels. The lowest paid channel is LLM Gateway at $1.50 / $7.50 per 1M. That channel is a third-party gateway, so confirm its availability and rate limits before depending on it.

Artificial Analysis rates it 4.6 on the Intelligence Index, with 12.2 for Engineering, its strongest domain. Against its lowest blended price of $3.00 per 1M, that is roughly 2 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 171 tokens per second, with 2.41s to the first token. Running one task of the Artificial Analysis suite costs about $1.0391, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 256,000 to 262,144, so the usable window depends on the provider you pick. It supports reasoning, tool use, and structured output. Accepted input modalities are Text, Image, and PDF. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence4.6
Value2
Engineering12.2
Finance & Accounting11.1
Legal9.7
Healthcare & Medical10.7
Strategy & Ops9.4
Economics11.6
Output speed171 tok/s
TTFT2.41 s
Cost per task$1.04
Value formulaIQ 4.6 ÷ min blended $3.000 = 2

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

Available at 11 providers11 with public prices

  • ProviderInput / Output
  • LLM GatewayGateway
    $1.50 / $7.50
    Context 262,144Output limit 262,144
  • DevPass (LLM Gateway)Gateway
    $1.50 / $7.50
    Context 262,144Output limit 262,144
  • OpenRouterGateway
    $1.50 / $7.50
    Context 262,144Output limit 209,715
  • Eden AIGateway
    $1.50 / $7.50
    Cache read $0.15Context 262,144Output limit 209,715
  • Kilo GatewayGateway
    $1.50 / $7.50
    Cache read $0.15Context 262,144Output limit 209,715
  • Vercel AI GatewayCloud
    mistral/mistral-medium-3.5
    $1.50 / $7.50
    Cache read $0.15Context 262,144Output limit 256,000
  • CortecsGateway
    mistral-medium-3.5
    $1.53 / $7.84
    Cache read $0.15Context 256,000 ⚠Output limit 256,000
  • AI/ML APIGateway
    $1.59 / $7.94
    Context 262,144Output limit 209,715
  • RequestyGateway
    $1.65 / $8.25
    Cache read $1.65Context 262,144Output limit 209,715
  • RequestyGateway
    mistral-medium-3-5@eu
    $1.65 / $8.25
    Cache read $1.65Context 262,144Output limit 209,715
  • Eden AIGateway
    mistral/mistral-medium-3-5@eu
    $1.65 / $8.25
    Cache read $0.17Context 262,144Output limit 209,715
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
LLM GatewayGateway$1.50$7.50——262,144262,144
DevPass (LLM Gateway)Gateway$1.50$7.50——262,144262,144
OpenRouterGateway$1.50$7.50——262,144209,715
Eden AIGateway$1.50$7.50$0.15—262,144209,715
Kilo GatewayGateway$1.50$7.50$0.15—262,144209,715
Vercel AI Gateway
mistral/mistral-medium-3.5
Cloud$1.50$7.50$0.15—262,144256,000
Cortecs
mistral-medium-3.5
Gateway$1.53$7.84$0.15—256,000 ⚠256,000
AI/ML APIGateway$1.59$7.94——262,144209,715
RequestyGateway$1.65$8.25$1.65—262,144209,715
Requesty
mistral-medium-3-5@eu
Gateway$1.65$8.25$1.65—262,144209,715
Eden AI
mistral/mistral-medium-3-5@eu
Gateway$1.65$8.25$0.17—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.

Reasoning control

effort = noneeffort = higheffort = loweffort = mediumeffort = max

1 / 11 providers expose no reasoning control (reasoning_options: []).

Your usage cost

Common scenarios
1Eden AI$513.00
2Kilo Gateway$513.00
3Vercel AI Gateway$513.00
4Cortecs$533.19
5Eden AI$564.30
6LLM Gateway$675.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$7.50$02026-08-052026-11-18
2026-11-18Input list —Output list —Min blended $3.00

Artificial Analysis evaluations26 items

GPQA Diamond74.9%
Humanity's Last Exam13.8%
HLE-Diamond4.7%
MMMU-Pro64.9%
CritPt0.0%
CritPt v2 Hard0.5%
SciCode40.2%
FrontierCode 2.01.8%
Terminal-Bench Hard33.3%
Terminal-Bench 2.150.6%
Terminal-Bench 4.00.0%
Terminal-Bench-Science0.0%
τ²-Bench Telecom94.2%
τ³-Bench Banking15.0%
AutomationBench-AA6.3%
AA-AnalystAgent12.5%
EnterpriseOps-Gym-AA33.7%
AA-Briefcase523
GDPval-AA769
GDP.pdf2.8%
AA-LCR69.3%
MLCR-AA10.0%
IFBench68.8%
AA-Omniscience Index-38.7
AA-Omniscience Accuracy23.0%
AA-Omniscience Non-Hallucination19.8%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

Mistral Medium 3.5 Thinkingsame series—Mistral Medium 3.5same series$1.50 / $7.50Mistral Medium (latest)same series$1.50 / $7.50Mistral Medium 3same lab$0.40 / $2.00Mistral Medium 3.1same lab$0.40 / $2.00
Data partly from models.dev (MIT)