per 1M tokens
MoonshotAI: Kimi K3
moonshotai/kimi-k3
Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI. It is suited for complex coding, knowledge work, and long-horizon agentic workflows, and is particularly strong at...
Price
per 1M tokens
Cheaper on Inference.net (−65%) versus the lab price
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
| Provider | Tag | Quant | Input | Output | Context | Uptime | Status | Source |
|---|---|---|---|---|---|---|---|---|
| Inference.net Price differs from the host list |
inference-net/fp4 | fp4 | $0.3/1M | $7.5/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Inference.net Price differs from the host list |
inference-net/us | fp4 | $0.3/1M | $7.5/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Wafer | wafer/us | mxfp4 | $0.276/1M | $9.94/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Sail Research | sail-research/fp4 | fp4 | $0.23/1M | $11/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Sail Research | sail-research/fp4/us | fp4 | $0.23/1M | $11/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Amazon Bedrock Price differs from OpenRouter |
batch | — | $1.65/1M | $8.25/1M | — | — | Listed | amazon-bedrock |
| Amazon Bedrock Price differs from OpenRouter |
flex | — | $1.65/1M | $8.25/1M | — | — | Listed | amazon-bedrock |
| Inference.net Price differs from the host list |
inference-net/fast | fp4 | $0.5/1M | $11.88/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Inference.net Price differs from the host list |
inference-net/us/fast | fp4 | $0.5/1M | $11.88/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Makora | makora/fp4 | fp4 | $0.5/1M | $13/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Chutes | chutes/mxfp4 | mxfp4 | $1.85/1M | $9.5/1M | 1.0M | — | Live | openrouter-endpoints |
| Decart | decart/mxfp4 | mxfp4 | $1.95/1M | $9.75/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Wafer | wafer | mxfp4 | $0.2/1M | $15/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Fireworks | fireworks/spot | — | $2.1/1M | $10.5/1M | 1.0M | 100% | Live | openrouter-endpoints |
| AkashML | akashml/fp4 | fp4 | $1.2/1M | $14/1M | 1.0M | 92% | Live | openrouter-endpoints |
| Morph | morph/fp8 | fp8 | $1.278/1M | $14.626/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Phala Price differs from the host list |
phala | — | $2.55/1M | $12.75/1M | 1.0M | 100% | Live | openrouter-endpoints |
| DigitalOcean | digitalocean | — | $2.55/1M | $12.95/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Sarvam | — | — | $2.834/1M | $14.17/1M | — | — | Listed | sarvam-docs |
| Wafer | wafer/fast | mxfp4 | $0.229/1M | $22/1M | 1.0M | 100% | Live | openrouter-endpoints |
| DeepInfra | — | — | $2.85/1M | $14.25/1M | 1.0M | — | Listed | deepinfra |
| DeepInfra | deepinfra/mxfp4 | mxfp4 | $2.85/1M | $14.25/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Amazon Bedrock Price differs from the host list |
amazon-bedrock/us-east-2 | — | $3/1M | $15/1M | 1.0M | 100% | Live | openrouter-endpoints |
| AtlasCloud | — | int4 | $3/1M | $15/1M | 1.0M | — | Listed | atlascloud |
| BaseTen | baseten/fp8 | fp8 | $3/1M | $15/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Fireworks | fireworks | — | $3/1M | $15/1M | 1.0M | — | Live | openrouter-endpoints |
| Inference.net Price differs from OpenRouter |
— | — | $3/1M | $15/1M | 1.0M | — | Listed | inferencenet |
| Modal | modal/mxfp4 | mxfp4 | $3/1M | $15/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Moonshot AI | moonshotai | — | $3/1M | $15/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Novita | — | — | $3/1M | $15/1M | 1.0M | — | Listed | novita |
| Parasail | parasail/fp4 | fp4 | $3/1M | $15/1M | 1.0M | 100% | Live | openrouter-endpoints |
| ParetoAlpha | pareto-alpha/us | — | $3/1M | $15/1M | 1.0M | — | Live | openrouter-endpoints |
| Phala Price differs from OpenRouter |
— | — | $3/1M | $15/1M | 1.0M | — | Listed | phala |
| Together | — | — | $3/1M | $15/1M | 1.0M | — | Listed | together |
| Together | together | — | $3/1M | $15/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Io Net | — | mxfp4 | $2.523/1M | $17.264/1M | 1.0M | — | Listed | ionet |
| Amazon Bedrock Price differs from OpenRouter |
standard | — | $3.3/1M | $16.5/1M | — | — | Listed | amazon-bedrock |
| NEAR AI | — | — | $3.3/1M | $16.5/1M | 1.0M | — | Listed | nearai |
| Alibaba | alibaba | — | $3.45/1M | $17.25/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Venice | — | — | $3.75/1M | $18.75/1M | 1M | — | Listed | venice |
| Tinfoil | — | — | $4/1M | $20/1M | 262K | — | Listed | tinfoil |
| Fireworks | fireworks/fast | — | $4.5/1M | $22.5/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Fireworks | fireworks/us | — | $4.5/1M | $22.5/1M | 1.0M | 100% | Live | openrouter-endpoints |
| Amazon Bedrock Price differs from OpenRouter |
priority | — | $5.775/1M | $28.875/1M | — | — | Listed | amazon-bedrock |
| Relace | relace/fp4 | fp4 | $0.19/1M | $9.339/1M | 1.0M | 76% | Down | openrouter-endpoints |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$15.19 at list price for this workload
Cache
per 1M tokens
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $0.192/1M | $15/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-09-15 | token | $2.648 | $13.283 | Not published— |
| 2026-09-16 | token | $3 | $15 | Not published— |
| 2026-09-17 | token | $3 | $15 | Not published— |
| 2026-09-18 | token | $2.1 | $10.95 | Not published— |
| 2026-09-19 | token | $1.7 | $8.5 | Not published— |
| 2026-09-20 | token | $1.7 | $8.5 | Not published— |
| 2026-09-21 | token | $3 | $15 | Not published— |
| 2026-09-22 | token | $3 | $15 | Not published— |
| 2026-09-23 | token | $3 | $15 | Not published— |
| 2026-09-24 | token | $3 | $15 | Not published— |
| 2026-09-25 | token | $3 | $15 | Not published— |
| 2026-09-26 | token | $3 | $15 | Not published— |
| 2026-09-27 | token | $3 | $15 | Not published— |
| 2026-09-28 | token | $3 | $15 | Not published— |
| 2026-09-29 | token | $3 | $15 | Not published— |
| 2026-09-30 | token | $3 | $15 | Not published— |
| 2026-10-01 | token | $0.6635 | $10 | Not published— |
| 2026-10-02 | token | $2.7 | $13.5 | Not published— |
| 2026-10-03 | token | $0.99 | $13 | Not published— |
| 2026-10-04 | token | $0.72 | $13 | Not published— |
| 2026-10-05 | token | $1.39 | $14 | Not published— |
| 2026-10-06 | token | $0.69 | $14 | Not published— |
| 2026-10-07 | token | $0.5 | $15 | Not published— |
| 2026-10-08 | token | $1.09 | $14 | Not published— |
| 2026-10-09 | token | $0.95 | $14 | Not published— |
| 2026-10-10 | token | $0.5 | $13.5 | Not published— |
| 2026-10-11 | token | $0.8 | $13.5 | Not published— |
| 2026-10-12 | token | $0.73 | $10 | Not published— |
| 2026-10-13 | token | $0.73 | $10 | Not published— |
| 2026-10-14 | token | $0.5 | $15 | Not published— |
| 2026-10-15 | token | $0.45 | $16.5 | Not published— |
| 2026-10-16 | token | $0.304 | $11.936 | Not published— |
| 2026-10-17 | token | $0.304 | $11.936 | Not published— |
| 2026-10-18 | token | $0.304 | $11.936 | Not published— |
| 2026-10-19 | token | $0.239 | $11.936 | Not published— |
| 2026-10-20 | token | $0.239 | $11.936 | Not published— |
| 2026-10-21 | token | $0.239 | $11.936 | Not published— |
| 2026-10-22 | token | $0.239 | $11.936 | Not published— |
| 2026-10-23 | token | $0.239 | $10.8 | Not published— |
| 2026-10-24 | token | $0.239 | $10.8 | Not published— |
| 2026-10-25 | token | $0.239 | $10.8 | Not published— |
| 2026-10-26 | token | $0.179 | $20 | Not published— |
| 2026-10-27 | token | $0.169 | $20 | Not published— |
| 2026-10-28 | token | $0.201 | $20 | Not published— |
| 2026-10-29 | token | $0.239 | $10.8 | Not published— |
| 2026-10-30 | token | $0.192 | $15 | Not published— |
Alternatives
- e2ee-gemma-4-26b-a4b-uncensored-p$0.19/1M · Compare
- Qwen: Qwen3 Coder Flash$0.195/1M · Compare
- Meta: Llama 4 Maverick$0.1875/1M · Compare
- minimax-m3-1-flash$0.1875/1M · Compare
- Qwen: Qwen3.6 Flash$0.1875/1M · Compare
- Qwen3.6 35B A3B$0.186/1M · Compare
Parameters (22)
frequency_penaltyinclude_reasoninglogit_biaslogprobsmax_completion_tokensmax_tokensmin_pparallel_tool_callspresence_penaltyreasoningreasoning_effortrepetition_penaltyresponse_formatseedstopstructured_outputstemperaturetool_choicetoolstop_ktop_logprobstop_p
Call this model
OpenRouter id moonshotai/kimi-k3. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"moonshotai/kimi-k3","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "moonshotai/kimi-k3",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "moonshotai/kimi-k3", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())