Kimi K2 Instruct
Model ID: moonshotai/kimi-k2-instruct · Context window: 131K tokens
All rates, conditions and sources
Conditions of every rate below:
- PPIO hosted serverless listing, CNY per 1M tokens; standard listed prices only. Batch, priority, dedicated, promotional and free-limited offers are excluded.
- Native decimal values agree with integer ten-thousandths and original/listed amounts. No tiered billing is reported for this listing.
- Account and regional eligibility, status-code semantics and effective dates are unverified; listing is not an inference service test.
Input: CN¥4.00 per 1M tokens · Serverless tier · Modality: text
- Listed prompt/input token rate; separately listed cache-read rates apply only to cache hits.
Output: CN¥16.00 per 1M tokens · Serverless tier · Modality: text
- Listed completion/output token rate.
Capability (Epoch AI): ECI 141.3 (90% range 138.3–144.0) · range spans bands · Epoch AI score for Kimi K2 (Jul 2025), model dated Jul 12, 2025
Context window: 131,072 tokens
Price observed:
API availability: not verified
Collection record
Primary source ↗ · provider documentation · Claims: ppio-kimi-k2-instruct: pricing · 1 more claim about 1 other catalog entry · Retrieved · Checked · Review due · Freshness: stale · Confidence: A
- Raw SHA-256: ddead68d36320cd9b8e86319bf842c24732daf07ad13dead65237473d24a1798; separately archived pricing-table amounts and five-minute cache-write TTL; both selected API/table amounts agree.
Raw API evidence ↗ · provider API · Claims: ppio-kimi-k2-instruct: specifications · Retrieved · Checked · Reviewed · Freshness: unknown · Confidence: A
- Official PPIO models API (https://api.ppio.com/openai/v1/models, the 2026-10-26 daily archive, raw SHA-256 cd0b517f307a65d174ed6e4c885fd410e2a804b802326d818c64d0eb24bc58d4): the entry "id":"moonshotai/kimi-k2-instruct" has "context_size":131072. PPIO's API reference (https://ppio.com/docs/models/reference-llm-list-models.md, raw SHA-256 cd028a88e2d5b6086cc425c51b038614dce72e3afa2cbdb07e8cd13cc869d098, fetched 2026-10-26T18:25:12Z) defines this field of each listed model as "模型允许的最大上下文长度。" ("the maximum context length the model allows"). This is PPIO's stated maximum context size for this listing; the model's developer and other hosts may state different limits. The value comes from the archived body behind this offer's current pricing evidence; no new collection was made and no model page was read (#788).
- Specifications only: no pricing, availability, capability or release-date assertion.
Raw API evidence ↗ · provider API · Claims: ppio-kimi-k2-instruct: pricing · 8 more claims about 8 other catalog entries · Retrieved · Checked · Review due · Confidence: B
- Raw SHA-256: e7089f3545d53d14c7de1240f3ec10f3b76b6e0641c65022ea9975bfc5432bc3; collector ppio-inventory-6; daily collection independently replayed with zero source requests.
- CNY/scale interpretation reviewed on 2026-10-02 against the official PPIO pricing table (#105); API original/decimal/integer values retained privately. No cache-write rate is priced without the reviewed pricing-table TTL.
- Curated hosted listings priced here: 9 (75 models listed). No verified checkpoint/developer/license/weight-access link; availability remains unknown because numeric status semantics are undocumented.