Kimi K2.6 moonshotai/kimi-k2.6
Served by 21 providers. Cheapest: Chutes at $1.09 blended /1M tokens. The most expensive listing costs 2.1× as much for the same model.
| Provider | Type | Input /1M | Output /1M | Cached input | Blended | Context | Notes | Source |
|---|---|---|---|---|---|---|---|---|
| Chutes moonshotai/Kimi-K2.6-TEE |
Inference hosts | $0.50 | $2.85 | $0.05 | $1.09 | 262k | int4 TEE (confidential compute); upstream weights moonshotai/Kimi-K2.6 |
✓ src src2 2026-09-18 |
| CoreWeave moonshotai/Kimi-K2.6 |
Inference hosts | $0.65 | $3.41 | $0.15 | $1.34 | 262k | Context from docs model table (rounded, e.g. "262k"). |
✓ src src2 2026-09-18 |
| Crusoe | Inference hosts | $0.70 | $3.50 | $0.35 | $1.40 | — |
✓ src 2026-09-18 |
|
| SiliconFlow moonshotai/Kimi-K2.6 |
Inference hosts | $0.77 | $3.40 | $0.14 | $1.43 | — | context shown on pricing page as "262K" |
✓ src 2026-09-18 |
| DeepInfra moonshotai/Kimi-K2.6 |
Inference hosts | $0.75 | $3.50 | $0.15 | $1.44 | 262k | fp4 |
✓ src src2 2026-09-18 |
| Parasail | Inference hosts | $0.75 | $3.50 | $0.16 | $1.44 | — |
✓ src 2026-09-18 |
|
| Venice.ai API kimi-k2-6 |
Inference hosts | $0.75 | $3.50 | $0.16 | $1.44 | 256k | int4 |
✓ src src2 2026-09-18 |
| Featherless moonshotai/Kimi-K2.6 |
Inference hosts | $0.80 | $3.40 | $0.154 | $1.45 | 262k | Developer-plan per-token rate; model_class kimi-k25; also usable flat-rate on $25/mo Chat plan (32K ctx, human chat only) |
✓ src src2 src3 2026-09-18 |
| Novita AI moonshotai/kimi-k2.6 |
Inference hosts | $0.80 | $3.40 | $0.16 | $1.45 | 262k |
✓ src src2 2026-09-18 |
|
| Atlas Cloud moonshotai/kimi-k2.6 |
Inference hosts | $0.95 | $4 | $0.16 | $1.71 | 262k | int4 |
✓ src 2026-09-18 |
| Baseten | Inference hosts | $0.95 | $4 | $0.16 | $1.71 | — | Model API id not shown on pricing page. |
◐ src 2026-09-18 |
| Cloudflare Workers AI @cf/moonshotai/kimi-k2.6 |
Inference hosts | $0.95 | $4 | $0.16 | $1.71 | — | Billed in neurons ($0.011/1k neurons); USD per-M-token equivalent as published by Cloudflare; requires Workers Paid or AI Gateway credits |
✓ src 2026-09-18 |
| DigitalOcean kimi-k2.6 |
Inference hosts | $0.95 | $4 | $0.19 | $1.71 | 262k |
✓ src src2 2026-09-18 |
|
| Fireworks AI accounts/fireworks/models/kimi-k2p6 |
Inference hosts | $0.95 | $4 | $0.16 | $1.71 | — | batch −50% Priority $1.50/$0.22/$6.00 |
✓ src 2026-09-18 |
| GMI Cloud Inference Engine moonshotai/Kimi-K2.6 |
Inference hosts | $0.95 | $4 | — | $1.71 | — | list price; currently discounted to $0.855 in / $3.6 out (10% off, effective 2026-04-20); from GMI console public pricing API (console is client-rendered; docs say prices live in console Model Hub) |
✓ src src2 2026-09-18 |
| Microsoft Foundry (Azure AI Foundry / Azure OpenAI) Kimi-K2.6 |
Hyperscaler AI platforms | $0.95 | $4 | $0.16 | $1.71 | — | Global Standard, Azure Retail Prices API meter 'K2.6 Thinking Inp glbl Tokens' (eastus); API meter is per 1K tokens, multiplied by 1000 (unit conversion only) |
✓ src src2 2026-09-18 |
| Moonshot AI (Kimi API Platform) kimi-k2.6 |
Model labs | $0.95 | $4 | $0.16 | $1.71 | 262k | batch −40% Batch: $0.57 in / $0.10 cache hit / $2.40 out (60% of standard). Visual+text input, thinking/non-thinking. |
✓ src src2 2026-09-18 |
| OpenRouter moonshotai/kimi-k2.6 |
LLM routers | $0.95 | $4 | $0.16 | $1.71 | 262k | api modality text+image->text |
✓ src 2026-09-18 |
| Replicate moonshotai/kimi-k2.6 |
Inference hosts | $0.95 | $4 | — | $1.71 | — |
✓ src 2026-09-18 |
|
| Requesty moonshot/kimi-k2.6 |
LLM routers | $0.95 | $4 | $0.16 | $1.71 | 262k | int4 upstream route moonshot; geo global; 6 other upstream routes listed (input $0.6-$1/M); API list price; Requesty's 5% markup on model cost (pricing page) is not included |
✓ src 2026-09-18 |
| Inference.net kimi-k2.6 |
Inference hosts | $1.25 | $5.30 | $0.21 | $2.26 | 262k | https://inference.net/models shows the same figures |
✓ src 2026-09-18 |
✓ from the provider's own pricing page · ◐ partly confirmed there · 2° third-party source. Router prices may exclude the router's own fees; see each router's page.