What is Kimi K2 6?
Kimi K2 6 is a language model in the o10 fulfillment catalog (slug: kimi-k2-6). Published input pricing starts at $0.950/1M tokens. Context window: 262K tokens.
Catalog snapshot 2026-06-27.
Kimi K2 6 costs $0.950/1M input tokens and $4.00/1M output tokens as of 2026-06-27. Openrouter publishes this model with a 262K tokens context window. o10 lists Kimi K2 6 on Moonshot AI at routing band C1.
Last updated: 2026-06-27. Full catalog
Kimi K2 6 — specs, hosts, and routing
AnswersSelf-contained
How much does Kimi K2 6 cost per million tokens?
Kimi K2 6 costs $0.950/1M input tokens and $4.00/1M 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 Kimi K2 6?
Kimi K2 6 is configured on Moonshot 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 Kimi K2 6's context window?
Kimi K2 6 supports a 262K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
What o10 routing band is Kimi K2 6?
Kimi K2 6 is classified at o10 routing band C1. 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 Kimi K2 6?
Kimi K2 6 is attributed to source provider openrouter in the o10 catalog. Fulfillment hosts (Moonshot AI) supply API access; list pricing may differ by venue.
01Deep dive
Specifications
Kimi K2 6 in the o10 unified catalog.
| Field | Value |
|---|---|
| o10 slug | `kimi-k2-6` |
| Type | text |
| Band | C1 |
| Routable | Yes |
| Source provider | openrouter |
| Primary host | Moonshot AI |
| Gateway ID | `moonshotai/kimi-k2.6` |
| Context window | 262,000 tokens |
| Released | 2026-04-20 |
02Deep dive
Token pricing
Gateway snapshot pricing for Kimi K2 6.
| Unit | Price |
|---|---|
| Input | $0.95/1M tokens |
| Output | $4/1M tokens |
03Deep dive
Fulfillment hosts
Upstream venues configured for Kimi K2 6.
| Host | Upstream model ID |
|---|---|
| moonshot | moonshot/kimi-k2.6 |
04Deep dive
Gateway provider endpoints
Endpoint-level pricing and latency from the gateway catalog.
| Provider | Input ($/1M) | Latency p50 | Uptime 1d |
|---|---|---|---|
| baseten | $0.95 | 474.5ms | 9962.7% |
| fireworks | $0.95 | 861ms | 10000.0% |
| moonshotai | $0.95 | 2846ms | 9998.3% |
| novita | $0.95 | 3098ms | 9997.8% |
| togetherai | $1.2 | 347.5ms | 9947.6% |
05Deep dive
Routing with o10
Eval-gated model selection for this slug.
o10 slug: kimi-k2-6. Band: C1. 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 Kimi K2 6 cost?
Kimi K2 6 costs $0.950/1M input tokens and $4.00/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
What is Kimi K2 6's context window?
Kimi K2 6 supports 262K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
Which hosts serve Kimi K2 6?
Kimi K2 6 (kimi-k2-6) is configured on: Moonshot AI. Upstream model IDs are listed in the fulfillment routes section.
Is Kimi K2 6 routable through o10?
Yes. Kimi K2 6 is routable at band C1. Send model: "kimi-k2-6" or use an o10 smart routing alias.
How do I call Kimi K2 6 via o10?
Use o10 slug "kimi-k2-6" or gateway ID "moonshotai/kimi-k2.6" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
How does o10 route this model?
o10 routes Kimi K2 6 only when per-use-case evals clear at your quality floor. Band C1 indicates cost tier. See /kyi for governance and /models/routing for smart aliases.