Migrate off Kimi K2 Thinking Turbo
DeprecatedKimi K2 Thinking Turbo is deprecated. Moonshot's official replacement is Kimi K3. The cheapest comparable model we track is Amazon Nova Lite (Amazon) at $0.105 per 1M tokens blended.
Last verified: 26 Sep 2026 · sourced from official provider documentation
◎ You're on the watch list. We'll ping you the moment a model launches, changes price, or gets deprecated.
✕ Couldn't subscribe right now — please try again in a moment.
Free forever · no spam · unsubscribe anytime.
Kimi K2 Thinking Turbo → Kimi K3
Moving to Kimi K3 means a larger context window (262K → 1.0M).
| Spec | Kimi K2 Thinking Turbo | Kimi K3 |
|---|---|---|
| Status | Deprecated | GA |
| Blended price /1M | — | $6 |
| Input / output /1M | — | $3 / $15 |
| Context window | 262K | 1.0M |
| Max output | — | — |
| Modality | text | text, image |
| Knowledge cutoff | — | — |
API string was kimi-k2-thinking-turbo → switch to kimi-k3. See Kimi K3's full spec sheet →
Budget-friendly replacements for Kimi K2 Thinking Turbo
Generally-available models that match Kimi K2 Thinking Turbo's capabilities (and at least half its 262K context), ranked by blended price. Every number is computed from official catalog prices.
| Model | Blended /1M | Input / output | Context |
|---|---|---|---|
| Amazon Nova Lite Amazon | $0.105 | $0.06 / $0.24 | 300K |
| Qwen-Flash Alibaba | $0.138 | $0.05 / $0.4 | 1M |
| Llama 4 Scout (17B-16E Instruct) Meta | $0.15 | $0.1 / $0.3 | 10M |
Migrating off Kimi K2 Thinking Turbo
What replaces Kimi K2 Thinking Turbo?
Moonshot's recommended migration for Kimi K2 Thinking Turbo is Kimi K3. The cheapest comparable model in our catalog is Amazon Nova Lite (Amazon) at $0.105/1M blended.
When is Kimi K2 Thinking Turbo shut down?
Kimi K2 Thinking Turbo is deprecated; Moonshot has not yet published a firm shutdown date. Plan your migration now.
What is the cheapest alternative to Kimi K2 Thinking Turbo?
Amazon Nova Lite (Amazon) is the cheapest generally-available alternative we track that matches Kimi K2 Thinking Turbo's capabilities, at $0.06 per 1M input and $0.24 per 1M output tokens ($0.105/1M blended).
Browse the full deprecation watch → or see Kimi K2 Thinking Turbo's full spec sheet →
Get a heads-up before your model is retired
New models, price cuts, and deprecations — a short email when something actually changes. No spam, unsubscribe anytime.
The last few changes we caught — this is what lands in your inbox:
- DeprecatingGoogle re-pointed the Gemini 2.5 TTS migration path past the 3.1 preview and onto the new GA 3.8 TTS models
- New modelGemini 3.8 Flash TTS is GA - a flagship text-to-speech model at under half the audio rate of the preview it replaces, on a two-column price schedule
- New modelGemini 3.8 Flash-Lite TTS is GA - Google's cost-efficient TTS, which Google says was built to replace Gemini 3.1 Flash TTS
◎ You're on the watch list. We'll ping you the moment a model launches, changes price, or gets deprecated.
✕ Couldn't subscribe right now — please try again in a moment.
Free forever · powered by the same data on this page.