Exact model · mistral-medium-3-5-26-04
Mistral Medium 3.5 API pricing and monthly cost by provider
Compare the versioned Mistral Medium 3.5 release across owner-direct and routed access while keeping upstream identity and missing cache evidence visible.
Exact model · mistral-medium-3-5-26-04
Mistral Medium 3.5 monthly cost comparison
Compare the versioned Mistral Medium 3.5 release across owner-direct and routed access while keeping upstream identity and missing cache evidence visible.
| Rank status | Provider | Input price | Cache-read price | Output price | Monthly cost | Exact configuration | Sources and freshness |
|---|---|---|---|---|---|---|---|
| —Not ranked | Mistral AI APIofficial | $1.5 / 1M input tokens | $0.15 / 1M cached input tokens | $7.5 / 1M output tokens | $300.00Included | mistral-medium-3-5-26-04 · owner-direct · standard pay-as-you-go |
|
| —Not ranked | OpenRouterrouter | $1.5 / 1M input tokens | Not published | $7.5 / 1M output tokens | $300.00Included | mistralai/mistral-medium-3.5-20260430 · Mistral upstream · standard |
|
Missing and excluded providers (5)
- Azure AI Foundry: A discoverable deployment listing did not expose an accepted public pay-as-you-go price for the exact release, so it is excluded.
- Together AI: No accepted exact Mistral Medium 3.5 route and matching public price observation was found in this review.
- Fireworks AI: No accepted exact Mistral Medium 3.5 route and matching public price observation was found in this review.
- DeepInfra: No accepted exact Mistral Medium 3.5 route and matching public price observation was found in this review.
- Novita AI: No accepted exact Mistral Medium 3.5 route and matching public price observation was found in this review.
Strict boundary: Mistral direct and OpenRouter are separate purchasing channels, but the reviewed OpenRouter endpoint resolves to Mistral upstream; they are not counted as independent infrastructure. Both channels match on standard input and output rates. OpenRouter has no accepted cache-read meter, so cached workloads reduce to one unranked direct price card. Context, latency, quotas, retries, taxes, support, data terms, and availability remain outside the cost order.
Embeddable result
Put this exact-model comparison on your site
The SVG card is cookie-free and links back to the same source-auditable workload. It shows a rank only while at least three routes qualify.
<script async referrerpolicy="no-referrer" src="https://apidir.dev/embed/model-cost.js?model=mistral-medium-3-5&input=100000000&cached=0&output=20000000"></script>
Exact-model alert · controlled rollout
Join the Mistral Medium 3.5 price alert waitlist.
Confirm your address to join the waitlist. Delivery remains paused until sender, suppression, and evidence checks are ready; ambiguous or stale changes stay quarantined.
Evidence boundary
What the monthly comparison proves
Mistral direct and OpenRouter are separate purchasing channels, but the reviewed OpenRouter endpoint resolves to Mistral upstream; they are not counted as independent infrastructure. Both channels match on standard input and output rates. OpenRouter has no accepted cache-read meter, so cached workloads reduce to one unranked direct price card. Context, latency, quotas, retries, taxes, support, data terms, and availability remain outside the cost order.
A row qualifies only when the exact model route, channel, region, mode, tier, and input/output meters match the reviewed definition. Cached input becomes mandatory when your cached-input volume is above zero.
Questions developers ask
Which exact Mistral Medium 3.5 route is compared?
This page is locked to mistral-medium-3-5-26-04. Family-only names, near matches, different model versions, and unreviewed aliases are excluded.
When is a lowest-cost label shown?
Only when at least three unique providers have complete fresh evidence for every token meter used by the submitted workload. Equal monthly costs share a rank.
What is excluded from monthly cost?
Retries, failed requests, networking, storage, taxes, support, dedicated capacity, latency, rate limits, and provider-specific service quality are outside this token-meter estimate.