How much does Kimi K2 cost per million tokens?
Kimi K2 costs $0.570/1M input tokens and $2.30/1M output tokens in the gateway catalog snapshot (2026-06-27). Endpoint pricing may differ by fulfillment host.
Sourced from gateway catalog snapshot.
Kimi K2 costs $0.570/1M input tokens and $2.30/1M output tokens as of 2026-06-27. Openrouter publishes this model with a 131K tokens context window. o10 lists Kimi K2 on Moonshot AI at routing band C4. API slug kimi-k2. Verify list prices against the venue you call.
Last updated: 2026-06-27. Full catalog. Reference prices are dated snapshots. Compare total cost and measured task quality before choosing a route.
Kimi K2 pricing. Input/output per 1M tokens
On this page
AnswersSelf-contained
Where can you run Kimi K2?
Kimi K2 is configured on Moonshot AI. Known host IDs: moonshotai: moonshot/kimi-k2. This model is routable through o10 eval-gated routing.
What is Kimi K2's context window?
Kimi K2 supports a 131K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
01Deep dive
Token pricing
Gateway snapshot pricing for Kimi K2.
| Unit | Price |
|---|---|
| Input | $0.57/1M tokens |
| Output | $2.3/1M tokens |
02Deep dive
Fulfillment hosts
Upstream venues configured for Kimi K2.
| Host | Upstream model ID |
|---|---|
| moonshotai | moonshot/kimi-k2 |
03Deep dive
Routing with o10
Eval-gated model selection for this slug.
o10 slug: kimi-k2. Band: C4. Routable: yes.
See [/models/routing](/models/routing) for smart aliases (o10/auto, o10/frontier, o10/squad) and [/kyi](/kyi) for governance.
SourceMethodology
Gateway catalog snapshot 2026-06-27. Fulfillment catalog synced from o10 control plane. Verify list prices against openrouter and host providers.
FAQFrequently asked questions
Common questions
How much does Kimi K2 cost?
Kimi K2 costs $0.570/1M input tokens and $2.30/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
What is Kimi K2's context window?
Kimi K2 supports 131K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
Which hosts serve Kimi K2?
Kimi K2 (kimi-k2) is configured on: Moonshot AI. Upstream model IDs are listed in the fulfillment routes section.
Is Kimi K2 routable through o10?
Yes. Kimi K2 is routable at band C4. Send model: "kimi-k2" or use an o10 smart routing alias.
How do I call Kimi K2 via o10?
Use o10 slug "kimi-k2" or gateway ID "moonshotai/kimi-k2" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
How does o10 route this model?
o10 routes Kimi K2 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.