Moonshotai Kimi K2 Thinking costs $0.600/1M input tokens and $2.50/1M output tokens as of 2026-06-27. Openrouter publishes this model with a 262K tokens context window. o10 lists Moonshotai Kimi K2 Thinking on OpenRouter at routing band C3. API slug moonshotai-kimi-k2-thinking. 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.
Moonshotai Kimi K2 Thinking. Price, context, and routing
Moonshotai Kimi K2 Thinking is a chat model from openrouter (slug: moonshotai-kimi-k2-thinking). Pick Moonshotai Kimi K2 Thinking when your evals pass at band C3 and the fulfillment hosts below are allowed venues. Published input pricing starts at $0.600/1M tokens. Context window: 262K tokens.
Catalog snapshot 2026-06-27.
When should you pick Moonshotai Kimi K2 Thinking?
Pick Moonshotai Kimi K2 Thinking when your evals pass at band C3 and the fulfillment hosts below are allowed venues. Moonshotai Kimi K2 Thinking is the openrouter SKU in this catalog. Compare same-provider siblings before jumping labs.
How does Moonshotai Kimi K2 Thinking differ from sibling models?
Moonshotai Kimi K2 Thinking is the openrouter SKU in this catalog. Compare same-provider siblings before jumping labs.
How much does Moonshotai Kimi K2 Thinking cost per million tokens?
Moonshotai Kimi K2 Thinking costs $0.600/1M input tokens and $2.50/1M 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 Moonshotai Kimi K2 Thinking?
Moonshotai Kimi K2 Thinking is configured on OpenRouter. Known host IDs: openrouter: openrouter/moonshotai/kimi-k2-thinking. This model is routable through o10 eval-gated routing.
What is Moonshotai Kimi K2 Thinking's context window?
Moonshotai Kimi K2 Thinking supports a 262K tokens context window in the gateway catalog snapshot. Context limits may vary by fulfillment host endpoint.
What o10 routing band is Moonshotai Kimi K2 Thinking?
Moonshotai Kimi K2 Thinking is classified at o10 routing band C3. 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 Moonshotai Kimi K2 Thinking?
Moonshotai Kimi K2 Thinking is attributed to source provider openrouter in the o10 catalog. Fulfillment hosts (OpenRouter) supply API access; list pricing may differ by venue.
01Deep dive
Specifications
Moonshotai Kimi K2 Thinking in the o10 unified catalog.
Moonshotai Kimi K2 Thinking specifications
Field
Value
o10 slug
`moonshotai-kimi-k2-thinking`
Type
text
Band
C3
Routable
Yes
Source provider
openrouter
Primary host
OpenRouter
Gateway ID
`moonshotai/kimi-k2-thinking`
Context window
262,114 tokens
Released
2025-11-06
02Deep dive
Token pricing
Gateway snapshot pricing for Moonshotai Kimi K2 Thinking.
Moonshotai Kimi K2 Thinking token pricing
Unit
Price
Input
$0.6/1M tokens
Output
$2.5/1M tokens
03Deep dive
Fulfillment hosts
Upstream venues configured for Moonshotai Kimi K2 Thinking.
Moonshotai Kimi K2 Thinking fulfillment routes
Host
Upstream model ID
openrouter
openrouter/moonshotai/kimi-k2-thinking
04Deep dive
Gateway provider endpoints
Endpoint-level pricing and latency from the gateway catalog.
Moonshotai Kimi K2 Thinking costs $0.600/1M input tokens and $2.50/1M output tokens in the gateway snapshot (2026-06-27). Verify against your provider's published pricing.
What is Moonshotai Kimi K2 Thinking's context window?
Moonshotai Kimi K2 Thinking supports 262K tokens in the gateway catalog snapshot. Host-specific endpoints may differ.
Which hosts serve Moonshotai Kimi K2 Thinking?
Moonshotai Kimi K2 Thinking (moonshotai-kimi-k2-thinking) is configured on: OpenRouter. Upstream model IDs are listed in the fulfillment routes section.
Is Moonshotai Kimi K2 Thinking routable through o10?
Yes. Moonshotai Kimi K2 Thinking is routable at band C3. Send model: "moonshotai-kimi-k2-thinking" or use an o10 smart routing alias.
How do I call Moonshotai Kimi K2 Thinking via o10?
Use o10 slug "moonshotai-kimi-k2-thinking" or gateway ID "moonshotai/kimi-k2-thinking" depending on your integration. Gateway-compatible endpoints accept OpenAI-style /v1 requests.
How does o10 route this model?
o10 routes Moonshotai Kimi K2 Thinking only when per-use-case evals clear at your quality floor. Band C3 indicates cost tier. See /kyi for governance and /models/routing for smart aliases.