Skip to content
ModelCap

Head-to-head comparison

Codestral 2508 vs Mistral Medium 3.5

Codestral 2508 (Mistral AI) and Mistral Medium 3.5 (Mistral AI) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.

Snapshot as of 17 August 2026

As of 17 August 2026, Mistral Medium 3.5 holds the stronger ModelCap Index position (#40 vs #226); Codestral 2508 is 8.3× cheaper per output token ($0.90/1M vs $7.50/1M); and Mistral Medium 3.5 offers the longer context window (262K vs 256K tokens).

Which should you choose?

Choose Codestral 2508 if…

  • API cost matters — $0.90/1M output tokens against $7.50/1M, about 8.3× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.30/1M against $1.50/1M.

Choose Mistral Medium 3.5 if…

  • you want the stronger overall ModelCap Index position — #40 against #226 (54.0 vs 0.0 points).
  • you need the longer context window — 262K tokens against 256K.
  • you want the more recently listed model — Mistral Medium 3.5 was listed 30 April 2026, Codestral 2508 1 August 2025.

Codestral 2508 vs Mistral Medium 3.5: specs, pricing and context

Specification comparison of Codestral 2508 and Mistral Medium 3.5
FieldCodestral 2508Mistral AIMistral Medium 3.5Mistral AI
ModelCap Index position#226#40
Index score0.054.0
EvidenceEstimatedMeasured
Input price / 1M tokens$0.30$1.50
Output price / 1M tokens$0.90$7.50
Context window256K tokens262K tokens
Max output tokens——
API providers listed11
Weight accessAPI onlyAPI only
Input modalitiesText, FileText, Image, File
First listed1 August 202530 April 2026
PublisherMistral AIMistral AI

Evidence: publisher corpus prior · leave-one-anchor-out calibrated · 4 public benchmark observations across 4 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Codestral 2508 vs Mistral Medium 3.5

Public benchmark boards where Codestral 2508 or Mistral Medium 3.5 has a published result
BoardCodestral 2508Mistral Medium 3.5Leads
Arena codingArena (LMArena)—14791468–1490Only one result
LMArena AgentLMArena—-7.0%-9.0%–-5.0%Only one result
Artificial Analysis Intelligence IndexArtificial Analysis—30.4intelligence-indexOnly one result

Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.

Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.

Codestral 2508 vs Mistral Medium 3.5: common questions

Is Codestral 2508 better than Mistral Medium 3.5?

Mistral Medium 3.5 ranks higher on the ModelCap Index as of 17 August 2026: #40 against #226. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it.

Is Codestral 2508 cheaper than Mistral Medium 3.5?

Codestral 2508 is cheaper on output tokens: $0.90/1M against $7.50/1M. Input tokens are $0.30/1M for Codestral 2508 and $1.50/1M for Mistral Medium 3.5. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens.

Which has the bigger context window, Codestral 2508 or Mistral Medium 3.5?

Mistral Medium 3.5 has the larger context window: 262K tokens against 256K.

Which is better for coding, Codestral 2508 or Mistral Medium 3.5?

The two models do not share a coding benchmark board on ModelCap yet, so no head-to-head coding score is published; the ModelCap Index position is the closest overall signal.

Are Codestral 2508 and Mistral Medium 3.5 open-weight models?

Codestral 2508: API only. Mistral Medium 3.5: API only. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.

Where can I run Codestral 2508 and Mistral Medium 3.5?

ModelCap currently lists 1 API provider for Codestral 2508 and 1 for Mistral Medium 3.5, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Codestral 2508 vs Mistral Medium 3.5 comparison?

Every figure comes from the sealed ModelCap dataset published 17 August 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.

Explore further