What is Mistral Medium?
Mistral Medium is a language model in the o10 fulfillment catalog (slug: mistral-medium). Published input pricing starts at $0.400/1M tokens. Context window: 128K tokens.
Catalog snapshot 2026-06-27.
Mistral Medium costs $0.400/1M input tokens and $2.00/1M output tokens as of 2026-06-27. Mistral publishes this model with a 128K tokens context window. o10 lists Mistral Medium on Mistral AI at routing band C4.
Last updated: 2026-06-27. Full catalog
Mistral Medium — specs, hosts, and routing
AnswersSelf-contained
How much does Mistral Medium cost per million tokens?
Mistral Medium costs $0.400/1M input tokens and $2.00/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
Where can you run Mistral Medium?
Mistral Medium is configured on Mistral AI. Each host maps to an upstream model ID listed in the fulfillment routes table. This model is routable through o10 eval-gated routing.
What is Mistral Medium's context window?
Mistral Medium supports a 128K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
What o10 routing band is Mistral Medium?
Mistral Medium is classified at o10 routing band C4. Bands group models by cost tier and eval profile: C0 (economy), C1 (standard), C2 (capable), C3/C4 (frontier). Production routing is enabled for this slug.
Who makes Mistral Medium?
Mistral Medium is attributed to source provider mistral in the o10 catalog. Fulfillment hosts (Mistral AI) supply API access; list pricing may differ by venue.
01Deep dive
Specifications
Mistral Medium in the o10 unified catalog.
| Field | Value |
|---|---|
| o10 slug | `mistral-medium` |
| Type | text |
| Band | C4 |
| Routable | Yes |
| Source provider | mistral |
| Primary host | Mistral AI |
| Gateway ID | `mistral/mistral-medium` |
| Context window | 128,000 tokens |
| Released | 2025-05-07 |
02Deep dive
Token pricing
Gateway snapshot pricing for Mistral Medium.
| Unit | Price |
|---|---|
| Input | $0.4/1M tokens |
| Output | $2/1M tokens |
03Deep dive
Fulfillment hosts
Upstream venues configured for Mistral Medium.
| Host | Upstream model ID |
|---|---|
| mistral | mistral/mistral-medium |
04Deep dive
Gateway provider endpoints
Endpoint-level pricing and latency from the gateway catalog.
| Provider | Input ($/1M) | Latency p50 | Uptime 1d |
|---|---|---|---|
| mistral | $0.4 | 255ms | 10000.0% |
05Deep dive
Routing with o10
Eval-gated model selection for this slug.
o10 slug: mistral-medium. Band: C4. Routable: yes.
See [/models/routing](/models/routing) for smart aliases (o10/auto, o10/economy) and [/kyi](/kyi) for governance.
SourceMethodology
Fulfillment catalog 2026-06-27. Gateway pricing joined where slug match exists.
FAQFrequently asked questions
Common questions
How much does Mistral Medium cost?
Mistral Medium costs $0.400/1M input tokens and $2.00/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
What is Mistral Medium's context window?
Mistral Medium supports 128K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
Which hosts serve Mistral Medium?
Mistral Medium (mistral-medium) is configured on: Mistral AI. Upstream model IDs are listed in the fulfillment routes section.
Is Mistral Medium routable through o10?
Yes. Mistral Medium is routable at band C4. Send model: "mistral-medium" or use an o10 smart routing alias.
How do I call Mistral Medium via o10?
Use o10 slug "mistral-medium" or gateway ID "mistral/mistral-medium" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
How does o10 route this model?
o10 routes Mistral Medium only when per-use-case evals clear at your quality floor. Band C4 indicates cost tier. See /kyi for governance and /models/routing for smart aliases.