Kimi K2.5 — Available Providers
Last refreshed 2026-11-05. Next refresh: weekly.
Compare pricing and deployment options across 7 providers.
Monthly cost ranking
Ranked for 1M input and 0.2M output tokens per month. Cache and batch discounts are applied only when the provider row has sourced prices.
Traffic profile
US default
Cost bars
Cheapest
OpenRouter
$0.84 at the selected traffic profile.
Cache-heavy
Vercel AI Gateway
Cache read is sourced at $0.10/1M.
Recipe-ready
AWS Bedrock
Install, auth, and call snippets are available from curated provider snippet data.
Provider matrix
Region, SLA, and compliance rows are hidden until curated source fields exist.Microsoft Foundry
hyperscaler
Not enough pricing
Input / OutputContact sales / Contact sales
Cache-
Serverless
| Provider | Profile cost | Input / Output | Cache | Deploy | Recipe | Links |
|---|---|---|---|---|---|---|
| OpenRouter aggregator | $0.84 | $0.44 / $2.00 | - | Serverless | Docs only | |
| AWS Bedrock hyperscaler | $1.20 | $0.60 / $3.00 | - | Serverless | Snippets | |
| Fireworks AI inference | $1.20 | $0.60 / $3.00 | - | Serverless | Snippets | |
| Novita AI inference | $1.20 | $0.60 / $3.00 | - | Serverless | Docs only | |
| Replicate API marketplace | $1.20 | $0.60 / $3.00 | - | Serverless | Snippets | |
| Vercel AI Gateway gateway | $1.20 | $0.60 / $3.00 | read $0.10 | Serverless | Snippets | |
| Microsoft Foundry hyperscaler | Not enough pricing | Contact sales / Contact sales | - | Serverless | Docs only |
Kimi K2.5 operational data note: this page ranks sourced token, cache, and batch fields only. Region, SLA, compliance, and latency claims are intentionally omitted until a curated matrix is added.
Deprecated provider routes(3)
| Provider | Status | Catalog ID |
|---|---|---|
| Cloudflare Workers AI | Deprecated | @cf/moonshotai/kimi-k2.5 |
| Together AI | DeprecatedRetired May 21, 2026 | moonshotai/Kimi-K2.5 |
| NVIDIA NIM | Deprecated | moonshotai/kimi-k2.5 |