Prices per 1M tokens · Serverless tier. A dash under capability means no independent score.

API prices by model
ModelInputCache readOutputCapability (Epoch AI)
Ling 3.1 FlashCN¥2.00CN¥0.40CN¥6.00No independent capability score

Rates, billing conditions and sources

Ling 3.1 Flash

Model ID: inclusionai/ling-3.1-flash · Context window: 1M 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¥2.00 per 1M tokens · Serverless tier · Modality: text

  • Listed prompt/input token rate; separately listed cache-read rates apply only to cache hits.

Output: CN¥6.00 per 1M tokens · Serverless tier · Modality: text

  • Listed completion/output token rate.

Cache read: CN¥0.40 per 1M tokens · Serverless tier · Modality: text

  • Cache-read input; read-cache TTL is unspecified.

Context window: 1,000,000 tokens

Price observed:

API availability: not verified

Collection record

Raw API evidence ↗ · provider API · Claims: ppio-ling-3-1-flash: 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":"inclusionai/ling-3.1-flash" has "context_size":262144. 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 same entry's description says "具备100万token上下文窗口" ("a 1M-token context window") for the model; the value published here is the listing's context_size. 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-ling-3-1-flash: specifications · Retrieved · Checked · Reviewed · Freshness: unknown · Confidence: A

  • Official PPIO models API (https://api.ppio.com/openai/v1/models, the 2026-10-27 daily archive, raw SHA-256 2b5286a4a9438b9b8adfadce645734b944dc00568c89f5788112c6b994d48e89): the entry "id":"inclusionai/ling-3.1-flash" has "context_size":1000000. 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 2026-10-26 archive listed 262144 for the same entry; only context_size changed between the two bodies. The value now matches the entry's own description, "具备100万token上下文窗口" ("a 1M-token context window"); the same entry gives "max_output_tokens":262144. The daily refresh failed closed on this change (#794, "PPIO curated context drift"); this record is its review (#803).
  • Specifications only: no pricing, availability, capability or release-date assertion.

Raw API evidence ↗ · provider API · Claims: ppio-ling-3-1-flash: 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.
About capability scores (Epoch AI)

Capability scores: Epoch AI, 'Capabilities & benchmarking'. Published online at epoch.ai. Retrieved from 'https://epoch.ai/benchmarks' [online resource], epoch.ai/benchmarks. Accessed Nov 18, 2026. Licensed CC BY 4.0; values here are rounded to one decimal place and grouped into bands.

The Epoch Capabilities Index (ECI) combines many benchmarks on a scale where Claude 3.5 Sonnet is 130 and GPT-5 is 150. Bands, on the displayed one-decimal score: Frontier 160+, Strong 150–159.9, Capable 140–149.9, Entry below 140. Each score has a 90% range, listed with each model's rates and sources; a range that crosses a band boundary is flagged there. Models are not ranked: neighbouring scores often overlap.

A benchmark is not your workload. Epoch's scores mostly reflect runs at the highest reasoning effort, which use more output tokens than default settings. Scores are dated and can shift between Epoch releases. A score belongs to the developer's model; a host listing shows the same model's score, but hosts may serve different versions or quantizations.

How headline rates are chosen

Headline rates use the directory's shared rule: the rate a buyer meets by default, chosen by billing, tier and context dimensions and never by price. Context caps, the bracket starting at zero and short-context variants are labeled. Every price is a listed price, not a service guarantee; each offer's details say what its source states about availability. Batch, off-peak and other variants remain in the details; where no single rate is the default, the table shows a dash.

No currency conversion is performed. Missing cache prices are unknown, not zero. Equal units do not establish equivalent models or service conditions. See the methodology and source register.