Kimi K3
Kimi K3 is Moonshot AI's frontier open-weight multimodal reasoning model, built for long-horizon coding, knowledge work, and deep reasoning.
input · usd / 1m tok
$3.00
output · usd / 1m tok
$15.00
context window
1.05mtokens
modalities · in → out
takes text and image in, gives text out
pricing
base api ratesusd per 1m tokens
- input
- $3.00
- output
- $15.00
- cache read
- $0.30
providers
Different companies host Kimi K3. Impossibl routes your request intelligently and handles failover automatically when a provider is down.
Azure AI Foundry
Azure AI Foundry serving options endpoint location routes East US 1 East US 2 1 locations describe provider endpoints; they do not guarantee where inference runs.
- Fireworks
- Moonshot AI
- Qwen
specifications
takes text and image in, gives text outmoonshotai/kimi-k3
- creatorMoonshot AI
- model typeText generation
- context window1,048,576 tokens
- maximum outputnot published
- input
takes text and image in, gives text out
- outputtext
- tool callingnot verified
- releasedjul 16, 2026
- endpoint
/v1/chat/completions
unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.
try it · your prompt, this model, live
# responses API
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["IMPOSSIBL_API_KEY"],
base_url="https://api.impossibl.com/v1",
)
resp = client.responses.create(
model="moonshotai/kimi-k3",
input="",
)
print(resp.output_text)
edit the prompt, then run
benchmarks
intelligence index
43.8#9 of 90 models on the gateway
- coding index76.2#9 of 60
- agentic index50.6#9 of 49
- omniscience19.7#17 of 86
- gpqa93.5%#8 of 88
- humanity’s last exam46.9%#11 of 89
- terminal-bench v2.185.0%#9 of 57
- Harvey LAB94.6%
- GPQA93.5%
- AA-LCR88.7%
- Terminal-Bench v2.185.0%
- MMMU-Pro80.5%
- SciCode59.5%
- AutomationBench Partial58.3%
- ITBench47.7%
- Humanity’s Last Exam46.9%
- Tau Banking46.0%
- APEX-Agents41.3%
- AnalystAgent38.8%
- Multilingual LCR38.3%
- CritPt23.4%
- GDP.pdf All-pass22.0%
- Terminal-Bench v4.012.6%
- Intelligence Index43.78
- Omniscience Index19.70
- GDPval Elo1583.53
- coding index (API)76.2
- agentic index (API)50.6
- intelligence index (API)43.8
each configuration is listed separately; these evaluations describe the tested model configuration, and performance and costs can differ on impossibl. unmeasured scores are omitted and api values keep their source units. last checked 2026-09-11.
compare Kimi K3 with other models
frontier labs and open weights, best-ranked firstusd / 1m tok · in / out
- anthropic/claude-fable-5-1$10.00 / $50.00compare →
- openai/gpt-6-astra$10.00 / $50.00compare →
- meta/muse-spark-1.3$1.25 / $4.25compare →
- zai/glm-5.3$1.40 / $4.40compare →
frequently asked questions
What is Kimi K3?
Kimi K3 is Moonshot AI's frontier open-weight multimodal reasoning model, built for long-horizon coding, knowledge work, and deep reasoning. It is natively multimodal, handles long inputs, and is positioned for agentic workflows across code, analysis, spreadsheets, and slides.
How much does Kimi K3 cost?
Kimi K3 costs $3.00 per million input tokens and $15.00 per million output tokens through the Impossibl API. Cache reads cost $0.30 per million tokens. All rates are in USD.
What is the context length of Kimi K3?
Kimi K3 has a 1,048,576-token context window through the Impossibl API.
What inputs and outputs does Kimi K3 support?
Kimi K3 accepts text and image as input. Kimi K3 returns text.
How do I use Kimi K3 through an API?
Kimi K3 is available through the Impossibl API. Use moonshotai/kimi-k3 as the model identifier with /v1/chat/completions. The quickstart explains how to create an API key and send your first request.
When was Kimi K3 released?
Moonshot AI released Kimi K3 on July 16, 2026.
this page describes Kimi K3 as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes. model descriptions and release dates, where available, use the creator sources linked under the answers above.
view the source catalog ↗model as markdown ↗report a correction →