Models

Kimi-K2-Thinking

gmi · 262K ctx · 8 providers · updated 2026-08-05 00:15 UTC

Cheapest
$0.900 Official list · GMI
Avg price
$1.18 /1M
providers
8
(3 × $0.800 + $1.20) ÷ 4 = $0.900/1M — the $/1M figure blends input and output at 3:1 — that is the only way models with two different rates can be ranked on one axis. Your actual rate depends on your own input:output mix — input only $0.800, 3:1 $0.900, 1:1 $1.00, output only $1.20 per 1M.

The board shows this model's cheapest measured offer ($0.900/1M); the smaller figure under it is the mean of the 11 offers listed below ($1.18/1M). Add those up and divide — it matches.

ProviderRouter / Source$ in /1M$ out /1MTTFTTPSUptimeEvidence
gmi Pricebook (LiteLLM) $0.800$1.20 — — — Official list
burncloud burncloud $0.574$2.29 — — — API-measured
fireworks_ai Pricebook (LiteLLM) $0.600$2.50 — — — Official list
baseten Pricebook (LiteLLM) $0.600$2.50 — — — Official list
moonshot Pricebook (LiteLLM) $0.600$2.50 — — — Official list
novita Pricebook (LiteLLM) $0.600$2.50 — — — Official list
novita HuggingFace Router $0.600$2.50 — — — API-measured
novita-ai Novita AI $0.600$2.50 — — — API-measured
Novita (bf16) OpenRouter $0.600$2.50 997ms 38 95.6% API-measured
Google OpenRouter $0.600$2.50 2533ms 24 74.5% API-measured
crusoe Pricebook (LiteLLM) $2.50$2.50 — — — Official list

Price trend

$0.9 $0.9 2026-07-06 → 2026-08-05 · 31d 2026-07-06 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-07 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-08 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-09 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-10 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-11 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-12 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-13 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-14 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-15 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-16 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-17 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-18 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-19 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-20 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-21 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-22 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-23 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-24 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-25 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-26 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-27 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-28 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-29 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-30 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-07-31 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-08-01 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-08-02 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-08-03 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-08-04 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M2026-08-05 · O 0.9 H 0.9 L 0.9 C 0.9 $/1M

Cheapest blended price, last 31 days (USD/1M): $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9 → $0.9

Data & method

Cheapest ranked by blended = (3×in + out) ÷ 4; performance columns show only when a source provides them, never estimated. “Official list” = LiteLLM open pricebook (MIT); “API-measured” = provider/aggregator public APIs. Machine-readable data: /api/v1/models/kimi-k2-thinking.json. Free reuse requires attribution to tkx.org.

About

Kimi-K2-Thinking is an AI model that specializes in natural language processing tasks, served by multiple inference providers on AI model marketplaces under the organization tag "gmi".

AI-generated summary from public information — is this yours?

FAQ

How much does Kimi-K2-Thinking cost?

Cheapest measured offer right now: $0.8/1M input, $1.2/1M output via gmi — across 8 tracked providers, refreshed hourly.

Who serves Kimi-K2-Thinking?

8 providers currently serve it. The table above lists each with input/output price, TTFT, TPS, uptime and an evidence tier.

Is the price of Kimi-K2-Thinking going up or down?

The daily candles above track the cheapest blended price ($/1M, 3:1 in:out). TKX snapshots every hour, so drops and hikes show up the same day they happen.

Related analysis

Back to rankings