aiticker

Moonshot AI · Released Sep 4, 2025

Kimi K2 0905

Kimi K2 0905 is the September update of [Kimi K2 0711](moonshotai/kimi-k2). It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32...

Open weights
  • Top 47%Aider Polyglot
Compare in showdown → OpenRouter ↗ All Moonshot AI models
Released
Sep 4 2025
Context window
262K 98K out
Input / 1M tokens
$0.60 from Free
Output / 1M tokens
$2.50 from Free

Where to run it

14 providers compared

Free to try on iFlow — free endpoints are often limited-time and rate-limited. Cheapest: NanoGPT at $0.40 / $1.80 per 1M input / output tokens — 64% less than the priciest option.

ProviderInputOutputCache readContextMax outputUptimevs. best
iFlowfree · may be limited-time Free Free —256K64K— Free
NanoGPT $0.40 $1.80 $0.20262K100K— Cheapest
Helicone $0.50 $2.00 $0.40262K16K— +17%
OpenCode $0.40 $2.50 $0.40262K262K— +23%
IO.NET $0.57 $2.30 $0.2833K4K— +34%
NovitaFP8 $0.60 $2.50 —262K98K100%24h +43%
Kilo Gateway $0.60 $2.50 —262K98K— +43%
ZenMux $0.60 $2.50 $0.15262K64K— +43%
Novita AI $0.60 $2.50 —262K98K— +43%
Jiekou.AI $0.60 $2.50 —262K100K— +43%
Prime Inference $0.60 $2.50 —262K98K— +43%
302.AI $0.63 $2.52 —262K262K— +47%
Hugging Face $1.00 $3.00 —262K16K— +100%
AI/ML API $1.38 $4.13 —262K98K— +175%

Value

Price vs. performance

5 models score higher for the same price or lesson Aider Polyglot, e.g. DeepSeek V3.2.
3.6%31.7%59.9%88.0% $0.01$0.10$1.00$10.00$100.00 DeepSeek V3.2 (DeepSeek) — 74.2% · $0.28/1M in DeepSeek V3.2 Exp (DeepSeek) — 74.2% · $0.27/1M in GPT-5 (OpenAI) — 88.0% · $1.25/1M in gpt-oss-120b (OpenAI) — 41.8% · $0.15/1M in Codestral 2508 (Mistral) — 11.1% · $0.30/1M in Qwen3 235B A22B Instruct 2507 (Qwen) — 59.6% · $0.09/1M in o3 Pro (OpenAI) — 84.9% · $20.00/1M in R1 0528 (DeepSeek) — 71.4% · $0.50/1M in Qwen3 32B (Qwen) — 40.0% · $0.08/1M in o3 (OpenAI) — 81.3% · $2.00/1M in o4 Mini (OpenAI) — 72.0% · $1.10/1M in GPT-4.1 (OpenAI) — 52.4% · $2.00/1M in GPT-4.1 Mini (OpenAI) — 32.4% · $0.40/1M in GPT-4.1 Nano (OpenAI) — 8.9% · $0.10/1M in Gemma 3 27B (Google) — 4.9% · $0.08/1M in o3 Mini (OpenAI) — 60.4% · $1.10/1M in DeepSeek V3 (DeepSeek) — 70.2% · $0.26/1M in o1 (OpenAI) — 61.7% · $15.00/1M in GPT-4o (2024-11-20) (OpenAI) — 23.1% · $2.50/1M in GPT-4o (2024-08-06) (OpenAI) — 23.1% · $2.50/1M in GPT-4o-mini (OpenAI) — 3.6% · $0.15/1M in GPT-4o-mini (2024-07-18) (OpenAI) — 3.6% · $0.15/1M in GPT-4o (OpenAI) — 23.1% · $2.50/1M in GPT-4o (2024-05-13) (OpenAI) — 23.1% · $5.00/1M in Kimi K2 0711 (Moonshot AI) — 59.1% · $0.57/1M in Kimi K2 0905 (Moonshot AI) — 59.1% · $0.60/1M in Kimi K2 0905

Kimi K2 0905 Other Moonshot AI Other labs Value frontier · Aider Polyglot vs. input price per 1M tokens (log scale) · Drag to pan, pinch or Ctrl + scroll to zoom, double-click to zoom in.

Benchmarks

1 benchmark score

BenchmarkScoreRankLeader
Aider PolyglotSoftware engineering · Hard Exercism problems in many languages 59.1% #12of 26 GPT-588.0%

Specs

Details

Model ID
moonshotai/kimi-k2-0905
Developer
Moonshot AI
Release date
Sep 4, 2025 ·
Context window
262,144 tokens
Max output
98,304 tokens
API price
$0.60 / $2.50 per 1M input / output tokens
Providers
14
Input types
text
Reasoning
No
Tool calling
Yes
Open weights
Yes
Free tier
No

Release date and prices from OpenRouter's catalog; providers from OpenRouter and models.dev. Buying directly from a provider can cost a little differently. Speed, latency and uptime are measured on OpenRouter only; uptime is the share of OpenRouter requests each provider served over the last day. Benchmark scores are the best result per benchmark from Epoch AI, licensed CC BY 4.0. Rank counts every model tracked here with a score.