MoonshotAI: Kimi K3
moonshotai/kimi-k3Kimi K3 is a 2.8T parameter open-weight multimodal reasoning model from Moonshot AI.
Modalities
In / out per 1M$0.25 / $12
Context1M
ReleasedJul 16, 2026
Providers
26 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.24 | $13 | $0.23 | 0.80s | 55 tps | 100% | |
| $0.36 | $12 | $0.36 | 0.87s | 58 tps | 100% | |
| $2.49 | $15 | $0.35 | 0.84s | 74 tps | 100% | |
| $1.20 | $9.00 | $0.40 | 2.27s | 56 tps | 100% | |
| $1.20 | $9.00 | $0.40 | 1.31s | 64 tps | 100% | |
| $3.45 | $17 | $0.34 | 2.12s | 41 tps | 100% | |
| $3.00 | $15 | $0.30 | 4.90s | 25 tps | 100% | |
 DigitalOcean | $2.55 | $13 | $0.26 | 1.81s | 25 tps | 100% |
 Basetenfp8 | $3.00 | $15 | $0.30 | 2.73s | 59 tps | 100% |
| $3.00 | $15 | $0.30 | 0.85s | 71 tps | 99.97% | |
 Fireworks | $3.00 | $15 | $0.30 | 2.21s | 34 tps | 99.97% |
 DeepInfraus · mxfp4 | $2.85 | $14 | $0.28 | 2.58s | 22 tps | 99.97% |
| $0.24 | $12 | $0.21 | 2.22s | 22 tps | 99.83% | |
| $0.80 | $3.00 | $0.60 | 3.86s | 28 tps | 99.83% | |
| $2.55 | $13 | $0.26 | 5.10s | 45 tps | 99.81% | |
 Amazon Bedrockus-east-2 | $3.00 | $15 | $0.30 | 1.51s | 87 tps | 99.77% |
| $0.37 | $15 | $0.33 | 2.77s | 40 tps | 99.77% | |
| $1.20 | $14 | $1.20 | 2.06s | 47 tps | 99.25% | |
| $1.53 | $13 | $0.20 | 2.35s | 27 tps | 99.19% | |
| $3.00 | $15 | $0.30 | 1.56s | 37 tps | 98.08% | |
| Fireworks | $4.50 | $23 | $0.45 | 1.43s | 60 tps | 97.74% |
| $1.65 | $8.25 | $0.17 | 2.16s | 42 tps | 96.43% | |
| $3.00 | $15 | $0.30 | 1.30s | 66 tps | 94.18% | |
| $1.85 | $9.50 | $0.18 | 3.94s | 12 tps | 93.51% | |
| $3.00 | $15 | $0.30 | 1.34s | 44 tps | 92.8% | |
| Fireworksus | $4.50 | $23 | $0.45 | 1.54s | 49 tps | 88.8% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Kimi K3 in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Kimi K3 costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.25
per 1M tokens
Output
$12
per 1M tokens
Cache read
$0.21
per 1M cached tokens
Included in every pass
Kimi K3 is included in every ProjectCOZY pass at no extra cost — one flat rate, no per-token metering. The rates above are there for comparison.
Performance
Time to first token and output speed across every provider, over the last 3 days.
0.0s20.0s40.0s60.0s80.0s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Together Alibaba Cloud Int. inference.net Decart Morph Sail Research Moonshot AI AkashML Amazon Bedrock (us-east-2) Fireworks (us) Fireworks Wafer (us) Relace DeepInfra (us) Phala Parasail Makora inference.net Chutes Wafer Modal Baseten DigitalOcean Parasail Fireworks Sail Research (us)
0 tok/s500 tok/s1000 tok/s1500 tok/s2000 tok/s
Oct 16, 12 AMOct 16, 8 AMOct 16, 4 PMOct 17, 12 AMOct 17, 8 AMOct 17, 4 PMOct 18, 12 AMOct 18, 8 AMOct 18, 4 PMOct 19, 12 AMOct 19, 8 AM
Together Alibaba Cloud Int. inference.net Decart Morph Sail Research Moonshot AI AkashML Amazon Bedrock (us-east-2) Fireworks (us) Fireworks Wafer (us) Relace DeepInfra (us) Phala Parasail Makora inference.net Chutes Wafer Modal Baseten DigitalOcean Parasail Fireworks Sail Research (us)
Uptime
100% of requests were served successfully over the last 3 days, across all providers.
Last 3 daysAvailability 99.82%
Oct 16, 12:00 PMNow
Availability over the last 24 hoursAvailability 99.86%
100% 98% 97% 95%
Oct 18, 12:10 PMNow
Apps
Tools that most often run Kimi K3, by tokens this week.
Activity
7846.4B tokens processed market-wide in the last month.
0200.0B400.0B600.0B800.0B
Sep 19Sep 24Sep 29Oct 4Oct 9Oct 14Oct 19
Tokens
FAQ
Which model id do I use for Kimi K3?
moonshotai/kimi-k3. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Kimi K3 hold?
1,048,576 tokens per request, of which up to 943,718 can be the response.
What can it accept and return?
Input: text, image, video. Output: text.
What does Kimi K3 cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.25 per 1M input tokens and $12 per 1M output tokens.
Who built Kimi K3?
MoonshotAI, in the Kimi family.
Explore
Other models your pass can call.
