compute.info

Model pricing across providers

Kimi K3 API pricing across providers

Kimi K3 by Moonshot AI, as listed by DeepInfra, Fireworks AI and Moonshot AI. Headline rates are each provider's own published prices with dated evidence.

Same developer model, separate services. Hosts may serve different versions, quantizations, context limits or serving tiers of a model. A listing on several providers is not proof of identical weights or behavior. Labels such as "(US)" are each provider's own row names.

Capability (Epoch AI): Strong · ECI 157.5 (90% range 155.2–160.0) · range spans bands · Epoch AI score for Kimi K3, model dated 2026-07-16

Headline token rates per 1M by provider, ordered by listed USD input price; unknown or non-USD headlines come last. Each rate keeps its provider's currency, tier and conditions; follow the provider link for every rate and source.
Provider listingInputCached inputOutputSource observed
DeepInfraKimi K3 · moonshotai/Kimi-K3USD 2.85 / 1000000 tokensstandardUnknown — see the provider pageUSD 14.25 / 1000000 tokensstandard
Fireworks AIKimi K3USD 3.00 / 1000000 tokensstandardUSD 0.30 / 1000000 tokensstandardUSD 15.00 / 1000000 tokensstandard
Moonshot AIKimi K3 · kimi-k3USD 3.00 / 1000000 tokensTier unspecifiedUSD 0.30 / 1000000 tokensTier unspecifiedUSD 15.00 / 1000000 tokensTier unspecified
Fireworks AIKimi K3 (US)USD 4.50 / 1000000 tokensstandardUSD 0.45 / 1000000 tokensstandardUSD 22.50 / 1000000 tokensstandard
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 2026-10-14. 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; a range that crosses a band boundary is flagged. 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 these listings were matched

Each listing was reviewed on 2026-10-10 and is linked by evidence, never by name alone: the provider's official model ID, or the model page its price row links. The build fails if a listing disappears, is renamed or its model ID or page changes. Unmatched listings are not shown here. Routed or aggregator listings (e.g. OpenRouter) are not grouped: they resell other providers' capacity rather than host the model themselves.

Headline rates follow the directory's shared rule: the rate a buyer meets by default, never chosen by price. No currency conversion is performed; unknown cache prices are not zero. See the methodology.