kimi-k3Fireworks AI
- api
- chat
- hosting
- US
- model lab
- Moonshot AI
- weights
- open
- added
- July 2026
- model id
- fireworks/kimi-k3
capabilities 5/8
5 providers serve kimi-k3. This page is one of them. Compare all endpoints
- input
- $3.00
- output
- $15.00
- cache write
- -
- cache read
- $0.30
worked cost
| volume | cost |
|---|---|
| 100K in + 10K out | $0.45 |
| 1M in + 100K out | $4.50 |
| 10M in + 1M out | $45.00 |
Requesty charges what the upstream provider charges, with no markup and no per-request fee. Prompt caching and smart routing cut the effective cost further on repeated context. Gateway pricing
- median ttft
- 2.01s
- median tok/s
- 54.0
- blended /1M
- $0.90
- cache hit
- 84.8%
- answered
- 99.90%
Weekly aggregates from production traffic routed through Requesty to this endpoint. A metric with no qualifying sample is left out rather than filled in. Compare against the other providers
| eval | Score as a share of 100 | /100 |
|---|---|---|
| GPQA Diamond | 93.5 | |
| Coding Index | 76.2 | |
| SciCode | 59.5 | |
| Humanity's Last Exam | 46.9 | |
| Intelligence Index | 43.8 | |
| 5 evals | mean | 64.0 |
Scores from Artificial Analysis and public leaderboards, normalised to 100. Bar colour is the band, not the rank: green 80 and up, blue 55 and up, amber 30 and up. Benchmarks measure narrow skills, so test on your own workload before committing. Released 2026-07-16.
- retention
- none
- trains on prompts
- no
- hosted in
- US
Terms are the provider's, not Requesty's: routing a request here puts it under them. Fireworks Privacy Policy
Need every request to stay in one jurisdiction? EU hosting routes only through EU-hosted providers.
fireworks/kimi-k3this id pins the fireworks ai deployment, with no routing and no failover. the managed id on the canonical page routes across all 5 providers instead
from openai import OpenAI client = OpenAI( api_key="YOUR_REQUESTY_API_KEY", base_url="https://router.requesty.ai/v1",) response = client.chat.completions.create( model="fireworks/kimi-k3", messages=[ {"role": "user", "content": "Explain quantum computing in one paragraph."}, ],) print(response.choices[0].message.content)
Change the base url to https://router.requesty.ai/v1, use your Requesty key, set the model to the id above. Existing OpenAI SDK code needs no other edit, and the same key reaches every other model in the catalog. Browse all models
Kimi’s most capable flagship model to date, with 2.8 trillion parameters. It is built on Kimi Delta Attention (KDA), a hybrid linear attention mechanism, and Attention Residuals, with native visual understanding and a 1M-token context window. It is the world’s first open-source model in the 3-trillion-parameter class, designed for frontier intelligence scenarios including long-horizon coding, knowledge work, and reasoning.
questions 6
How much does kimi-k3 cost?
What is the context window of kimi-k3?
How does kimi-k3 perform on benchmarks?
What can kimi-k3 do?
How do I use kimi-k3 with the OpenAI SDK?
Can I run kimi-k3 through Requesty?
more from fireworks ai 8
| endpoint | ctx | in /M |
|---|---|---|
| deepseek-v4.1-flash | 1.0M | $0.22 |
| deepseek-v4-flash-vision-exp | 1.0M | $0.22 |
| glm-5.3-flash | 1.0M | $0.15 |
| glm-5.3 | 1.0M | $1.40 |
| nemotron-lightning-3.5-30b-a3b | 262K | $0.05 |
| deepseek-v4-pro-0813 | 1M | $1.32 |
| muse-glimmer-30b | 131K | $0.35 |
| qwen3.8-max | 1M | $2.00 |
call kimi-k3 through one endpoint
One key for this endpoint and 600+ other models. No markup on provider prices, automatic failover when a provider degrades, and prompt caching built in. Methodology