MoonshotAI: Kimi Latest
moonshotai/kimi-latestThis model always redirects to the latest model in the Kimi family.
Modalities
In / out per 1M$0.70 / $14
Context1M
ReleasedApr 27, 2026
Providers
25 providers serve this model upstream.
| Provider | Input /M | Output /M | Cache read /M | Latency P50 | Throughput P50 | Uptime |
|---|---|---|---|---|---|---|
| $0.54 | $14 | $0.30 | 1.81s | 52 tps | 100% | |
 DigitalOcean | $2.55 | $13 | $0.26 | 0.99s | 40 tps | 100% |
| $3.00 | $15 | $0.30 | 5.59s | 24 tps | 100% | |
| $0.70 | $15 | $0.32 | 1.04s | 78 tps | 99.97% | |
| $2.80 | $16 | $0.30 | 0.73s | 55 tps | 99.97% | |
| $2.99 | $18 | $0.45 | 0.88s | 93 tps | 99.97% | |
| $0.72 | $24 | $0.30 | 0.90s | 53 tps | 99.95% | |
 Fireworks Fast | $4.50 | $23 | $0.45 | 1.32s | 70 tps | 99.95% |
| $2.60 | $13 | $0.26 | 1.48s | 72 tps | 99.92% | |
| Fireworksus | $4.50 | $23 | $0.45 | 1.23s | 43 tps | 99.9% |
| $2.55 | $13 | $0.26 | 1.46s | 78 tps | 99.84% | |
| $3.00 | $15 | $0.30 | 1.90s | 61 tps | 99.82% | |
| $3.45 | $17 | $0.34 | 3.94s | 31 tps | 99.79% | |
 Basetenfp8 | $3.00 | $15 | $0.30 | 3.83s | 77 tps | 99.75% |
| Fireworks | $3.00 | $15 | $0.30 | 1.26s | 28 tps | 99.71% |
 DeepInfraus · mxfp4 | $2.85 | $14 | $0.28 | 0.97s | 39 tps | 98.82% |
| $3.00 | $15 | $0.30 | 0.54s | 93 tps | 98.63% | |
| $3.00 | $15 | $0.30 | 0.97s | 55 tps | 98.34% | |
| $1.85 | $9.50 | $0.18 | 3.38s | 17 tps | 96.2% | |
 Amazon Bedrockus-east-2 | $3.00 | $15 | $0.30 | 4.46s | 51 tps | 95.29% |
| $1.53 | $13 | $0.20 | 0.85s | 67 tps | 94.62% | |
| $1.20 | $14 | $1.20 | 1.28s | 43 tps | 91.58% | |
| $0.67 | $20 | $0.29 | 2.86s | 27 tps | 90.04% | |
| $0.84 | $14 | $0.30 | 2.25s | 69 tps | 89.79% | |
| $2.31 | $12 | $0.23 | 2.25s | 88 tps | 84.1% |
Market-wide measurements, refreshed every 15 minutes. They describe who serves Kimi Latest in general, not how ProjectCOZY routes your requests.
Pricing
List rates per 1M tokens — what Kimi Latest costs pay-as-you-go elsewhere, not what you pay here.
Input
$0.70
per 1M tokens
Output
$14
per 1M tokens
Cache read
$0.28
per 1M cached tokens
Included in every pass
Kimi Latest 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.
0.0s200.0s400.0s600.0s800.0s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Together Alibaba Cloud Int. inference.net Fast Decart Morph Sail Research Moonshot AI AkashML Amazon Bedrock (us-east-2) Fireworks (us) Fireworks Fast Wafer (us) Relace DeepInfra (us) Phala Parasail Fast Makora inference.net Wafer Modal Baseten DigitalOcean Parasail Fireworks Chutes
0 tok/s500 tok/s1000 tok/s1500 tok/s2000 tok/s
Oct 11, 12 AMOct 11, 8 AMOct 11, 4 PMOct 12, 12 AMOct 12, 8 AMOct 12, 4 PMOct 13, 12 AMOct 13, 8 AMOct 13, 4 PMOct 14, 12 AMOct 14, 8 AM
Together Alibaba Cloud Int. inference.net Fast Decart Morph Sail Research Moonshot AI AkashML Amazon Bedrock (us-east-2) Fireworks (us) Fireworks Fast Wafer (us) Relace DeepInfra (us) Phala Parasail Fast Makora inference.net Wafer Modal Baseten DigitalOcean Parasail Fireworks Chutes
Uptime
Share of requests that at least one provider served successfully.
Last 3 days
Oct 11, 2:00 PMNow
Availability over the last 24 hours
100% 98% 97% 95%
Oct 13, 2:40 PMNow
Apps
Tools that most often run Kimi Latest, by tokens this week.
No apps published
This measurement has not been published for the model yet. It appears as soon as it is.
Activity
Tokens processed market-wide.
No activity published
This measurement has not been published for the model yet. It appears as soon as it is.
FAQ
Which model id do I use for Kimi Latest?
~moonshotai/kimi-latest. Send it as the model field from any OpenAI-compatible client, against http://192.168.1.55/v1.
How much context does Kimi Latest 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 Latest cost on a pass?
Nothing beyond the pass itself. Pay-as-you-go elsewhere it lists at $0.70 per 1M input tokens and $14 per 1M output tokens.
Who built Kimi Latest?
MoonshotAI, in the Kimi family.
Explore
Other models your pass can call.
