Kimi K2.8 Preview vs Kimi K3: Which One Should You Use?
Compare Kimi K2.8 Preview and Kimi K3 across Kimi Code, Kimi open platform and APIMaster. K2.8 Preview is live on APIMaster as kimi-k2.8-preview at $1/M input and $4/M output, with 1M context and adjustable reasoning.
Published 2026-09-17 · Updated 2026-09-22
Kimi K2.8 Preview and Kimi K3 are both available through APIMaster. Start with K2.8 for routine coding and evaluate K3 for harder repository and reasoning tasks. On Kimi's open platform the flagship answers to kimi-k3; inside Kimi Code that same flagship answers to k3, while K2.8 Preview keeps the older ID kimi-for-coding.
Moonshot describes K2.8 Preview as approaching K3 in overall performance and documents a 1M-token window. K3 is the flagship with 2.8 trillion parameters. Kimi Code has separate membership permissions for each; those permissions do not define APIMaster billing or route limits.
APIMaster price check, 2026-09-24: The table puts the reference price, current APIMaster price, active routes, and model card side by side. Prices can change; use the market card as the source of truth。
| Model ID | Reference price (per 1M input / output) | Current APIMaster price | Active routes | Discount | Model card |
|---|---|---|---|---|---|
kimi-k2.8-preview |
$- / — |
$1 / $4 |
1 | — | View discount |
kimi-k3 |
$3 / $15 |
$2.25 / $11.25 |
6 | 25% off | View discount |
Moonshot has published no separate pay-as-you-go price for K2.8 Preview. On APIMaster, K2.8 Preview is now available as kimi-k2.8-preview at $1.00 per million input tokens and $4.00 per million output tokens, with one active route checked September 22, 2026. Kimi's open platform still does not publish a K2.8 public ID; APIMaster's gateway ID is provider-specific. See the live K2.8 card before use. Kimi K3 starts at $2.25/M input and $11.25/M output across 6 active routes, up to 25% off Moonshot's $3/$15 published prices at the same check. The marketplace cards are authoritative.
GPT Trial(GPT-6 Astra, GPT-6 Sol, GPT-5.6, and GPT-5.5 available)
Sign up and claim a $20 GPT trial
The same model has different IDs on different surfaces
This is the part that trips people up. Kimi runs two separate products, and each one names models its own way.
| Surface | What it is | Kimi K3 ID | Kimi K2.8 Preview ID |
|---|---|---|---|
| Kimi open platform | Pay-as-you-go API for any developer | kimi-k3 |
— not offered |
| Kimi Code | Coding service bundled with a Kimi membership | k3, k3-256k |
kimi-for-coding |
Kimi Code currently exposes four model IDs from three models: k3 and k3-256k (the 1M and 262,144-token variants of K3), kimi-for-coding (K2.8 Preview), and kimi-for-coding-highspeed (K2.7 Code HighSpeed).
Two practical consequences:
- Do not send
kimi-k2.8to an API. It is not the listed APIMaster ID; usekimi-k2.8-previewhere. On Kimi's open platform, the only current Kimi models arekimi-k3,kimi-k2.7-code,kimi-k2.7-code-highspeedandkimi-k2.6. - A gateway listing an old Kimi name has not automatically become K2.8; APIMaster now explicitly lists
kimi-k2.8-preview. Kimi's open platform discontinued thekimi-k2series in May 2026 andkimi-k2.5plus themoonshot-v1family in August 2026. None of those IDs now resolve to K2.8 Preview.
What each model is officially positioned for
Kimi K3 is Moonshot's most capable model. Kimi's model list describes it as designed for "frontier intelligence scenarios such as software engineering, knowledge work, and deep reasoning," built on 2.8 trillion parameters with native visual understanding and a 1,048,576-token context window. We cover its API surface, tool calling and operational limits in the Kimi K3 launch guide.
Kimi K2.8 Preview is positioned for everyday development rather than frontier work. Kimi's release notes say it improves coding and agent capability with noticeably better thinking efficiency than K2.7 Code, and is suited to code completion and routine development tasks. It shipped on September 11, 2026 as a full rollout inside Kimi Code — and the model ID did not move, so existing kimi-for-coding configurations picked it up without a client change. Our Kimi K2.8 Preview guide covers its live $1/$4 pricing and a direct API example.
The relationship between the two is deliberate: K2.8 Preview is the default working model, K3 is the escalation path.
Spec comparison
Everything below is Kimi's own published specification for Kimi Code, where both models are currently available side by side.
| Kimi K2.8 Preview | Kimi K3 | |
|---|---|---|
| Model ID | kimi-for-coding |
k3 / k3-256k |
| Parameter count | Not published | 2.8 trillion |
| Context window | 1,048,576 tokens | 1,048,576 tokens (k3) / 262,144 (k3-256k) |
| Reasoning effort | low / high / max, default max |
low / high / max, default high |
| Multimodal input | Images and video | Images and video (k3) / images only (k3-256k) |
| Kimi Code access | Plus+ on new plans; Andante+ on legacy plans | Plus+ / Moderato+; 1M requires Pro+ / Allegretto+ |
| Relative consumption | Standard | k3 (1M) costs roughly twice k3-256k |
| Public API price | Not published | $0.30 cached input / $3.00 input / $15.00 output per 1M tokens |
One routing rule is worth memorising because it silently changes which model serves your request: inside Kimi Code, turning thinking off routes both K3 and K2.8 Preview requests to K2.8 Preview without thinking. A request you configured as K3 can therefore be answered by K2.8. This is Kimi Code behaviour; do not assume the same rule applies to the open platform or to a third-party gateway.
What Moonshot has not published
Three gaps are worth stating plainly, because most comparison content fills them in with guesses:
- Parameter count. Kimi published 2.8T for K3. There is no published parameter count for K2.8 Preview.
- Benchmarks. The K2.8 Preview announcement publishes no scores and no reproducible K2.8-versus-K3 evaluation. "Approaches K3" is Moonshot's own assessment, not an independent measurement — ours included.
- Price. See the next section.
Pricing: Moonshot has no K2.8 list price, APIMaster has a live route
Kimi's public price table lists K3 and other open-platform models, but no separate K2.8 Preview token price. In Kimi Code, K2.8 is included in eligible membership plans; APIMaster separately offers token-based billing.
APIMaster now has a live K2.8 Preview route. The September 22, 2026 marketplace check found one status-1 route at $1.00/M input and $4.00/M output. Compared with K3's published $3/$15 reference, that is about 67% lower input and 73% lower output; Moonshot has not published a separate K2.8 list price, so this is a cross-model comparison.
| Route | Input | Output |
|---|---|---|
| Kimi K2.8 Preview on APIMaster | $1.00/M — 1 active route | $4.00/M — 1 active route |
| Kimi K3 on APIMaster | $2.25–$3.00/M across 6 active routes | $11.25–$15.00/M across 6 active routes |
Route prices and channel supply change. Check the live card in the marketplace before production traffic. A single API key can compare both models on the same verified task.
What this means in practice
The following cache and membership error behavior is documented for Kimi Code, not guaranteed for every API gateway.
Cache invalidation. Changing model or changing reasoning effort invalidates the context cache, so the next request re-prefills the conversation and costs more. Kimi recommends starting a new session instead of switching back and forth inside a long one. If you plan to compare K2.8 and K3 on the same task, budget for that first expensive request on each.
Permission errors look like authentication errors. A request that exceeds your plan returns 401, not a quota message. Calling k3 below Plus / Moderato, requesting its 1M window below Pro / Allegretto, or calling kimi-for-coding-highspeed without the required tier all surface as 401. If your key works for one model and fails for another, check the plan before rotating keys.
IDs differ per surface. A k3 configuration is only valid inside Kimi Code. On the open platform the same model is kimi-k3. Copy IDs from the surface you are actually calling, and record provider, endpoint and model ID alongside any benchmark you keep.
Verify, do not assume. A model's own claim about its identity is not proof of which model served a request. This matters more than usual here, because disabling thinking on K3 legitimately hands the request to K2.8 Preview — a routed result that looks like a downgrade if you did not expect it.
How to choose
- Code completion, small refactors and routine development: K2.8 Preview. Moonshot documents a 1M window in Kimi Code, and APIMaster lists a $1/$4 route. Check API context limits before planning a long request.
- Repository-scale changes, long agent runs, deep reasoning and knowledge work: K3. Its 2.8T-parameter flagship tier and 1M context are the reason to pay more.
- You need a public API, SDK compatibility or predictable per-token billing: K3 today, because K2.8 Preview has no public API ID.
- You want the highest throughput inside Kimi Code: neither of the above —
kimi-for-coding-highspeedprovides roughly 6x output speed at 3x consumption, with the same coding capability as K2.7 Code.
What the community is talking about
The two models have very different levels of public discussion, and that is itself a useful signal.
K3 has been heavily discussed since July 2026. On Hacker News, "Kimi K3: Open Frontier Intelligence" reached 2,107 points and 1,214 comments, "Kimi-K3 on HuggingFace" 1,382 points, "Kimi K3 Is Competitive with Fable" 877 points, and "Moonshot AI suspends new subscriptions due to Kimi K3 demand" 284 points — the last one is a reminder that capacity, not just quality, shaped how Moonshot chose to sell its models. Architecture notes, the technical report and local-inference experiments (running K3 in 29 GB of RAM) all attracted substantial threads.
The earlier September 17 research found much less English-language discussion of K2.8 Preview than K3. That historical search snapshot is not an availability signal: APIMaster now lists K2.8 Preview as kimi-k2.8-preview. Treat community attention as evidence of interest, not as a K2.8-versus-K3 quality verdict.
FAQ
What is the model ID for Kimi K2.8 Preview?
Inside Kimi Code, kimi-for-coding. The ID did not change when the underlying model was upgraded, so existing configurations keep working. Kimi's open platform does not offer K2.8 Preview, while APIMaster exposes it as kimi-k2.8-preview.
Is Kimi K2.8 Preview better than Kimi K3?
Moonshot describes K2.8 Preview as approaching K3 with better thinking efficiency than K2.7 Code, but publishes no benchmark scores for it. K3 remains the flagship 2.8T-parameter model. For a real answer, run your own task — a failing test, a multi-file change, a long-document question — on both and compare correctness, completion time and cost.
Can I call Kimi K2.8 Preview from an API?
Yes. APIMaster exposes it through an OpenAI-compatible endpoint as kimi-k2.8-preview, currently at $1/M input and $4/M output on one active route checked September 22, 2026. Kimi's own open platform does not publish a separate K2.8 ID; inside Kimi Code the ID remains kimi-for-coding.
Why is the Kimi Code ID k3 when the API ID is kimi-k3?
They are two products with two naming schemes. Kimi Code's four IDs are k3, k3-256k, kimi-for-coding and kimi-for-coding-highspeed; the open platform's current IDs are kimi-k3, kimi-k2.7-code, kimi-k2.7-code-highspeed and kimi-k2.6. Always copy the ID from the surface you are calling.
Does disabling thinking give me Kimi K2.8 Preview?
Inside Kimi Code, yes: requests configured for K3 or K2.8 Preview with thinking turned off are both served by K2.8 Preview without thinking. Do not generalise this rule to the open platform or to a third-party gateway without checking that provider's documentation.
Is Kimi K2.8 Preview available on APIMaster?
Yes. It is listed as kimi-k2.8-preview with one active route at $1/M input and $4/M output in the September 22, 2026 check. Open the live card because routes and prices can change.
Sources and verification date
- Kimi Code: model configuration, IDs, limits and routing, checked September 22, 2026.
- Kimi Code: release notes for the September 11, 2026 K2.8 Preview rollout.
- Kimi Code: membership, shared quota, 5-hour window and extra usage.
- Kimi open platform: model list and discontinued models.
- Kimi open platform: model inference pricing.
- Hacker News discussions cited above: 48935342, 49065752, 48999291, 48969291.
- APIMaster live pricing catalog and marketplace cards, checked September 22, 2026. Availability and route prices can change after publication.
Start with Kimi K2.8 Preview on APIMaster.ai
Kimi K2.8 Preview is now the lower-cost, long-context option you can call through APIMaster. A single OpenAI-compatible key also covers Kimi K3 and other Claude, GPT, DeepSeek, Gemini and GLM routes, so you can compare models on the same verified task.
Create an APIMaster account, generate a key in the console, point your client at https://apimaster.ai/v1 and set the model to kimi-k2.8-preview. Open the Kimi K2.8 card for current route status before you scale.