Kimi K3 Fast
Kimi K3 served by Morph on GB300 racks tuned for latency: the same 2.8T MoE weights and full 1M context as morph-kimik3, with prefill/decode disaggregation shaped for time-to-first-token and per-request speed instead of batch throughput.
Model card on Hugging Face- Input / output price
- $4.50 / $22.50 per 1M
- Context
- 1M tokens
- Released
- Jul 27, 2026
Paste into Claude Code, Cursor, or Codex
Help me set up the Respan gateway: fetch and follow https:/
Providers
3 providers, cheapest first, priced per 1M tokens after gateway discounts.
| Provider | Input | Output |
|---|---|---|
Inference.net inference_net/moonshotai/kimi-k3-fast | $4.50/M | $22.50/M |
Parasail parasail/moonshotai/Kimi-K3-fast | $4.50/M | $22.50/M |
MorphLLM morphllm/morph-kimik3-fast | $6.00/M | $22.50/M |
Pricing
Averaged across 3 providers, in USD per 1M tokens after gateway discounts.
- Average input
- $5.00 per 1M
- Average output
- $22.50 per 1M
- Average cache read
- $0.50 per 1M
Cost by volume
Total cost from 0 to 1T tokens on the cheapest and most expensive provider.
Throughput and latency
30-day averages from requests through the Respan gateway. Under each figure, every model on the gateway by its average, this one in blue.
Output speed
Higher is better40tokens/sacross providers
Response latency
Lower is better1.5sacross providers
Apps
Use Kimi K3 Fast in the tools you already run. Each guide points the app at the Respan gateway.
Setup guides for more apps are in the integration docs.
Kimi K3 Fast FAQ
Short answers, built from the data on this page.
Kimi K3 Fast is a model from Moonshot, released on Jul 27, 2026. Kimi K3 served by Morph on GB300 racks tuned for latency: the same 2.8T MoE weights and full 1M context as morph-kimik3, with prefill/decode disaggregation shaped for time-to-first-token and per-request speed instead of batch throughput.
On the Respan gateway, input starts at $4.50 per 1M tokens on Inference.net and Parasail, and output starts at $22.50 per 1M tokens on every provider, after gateway discounts. Averaged across its 3 providers, it costs $5.00 per 1M input tokens and $22.50 per 1M output tokens.
Kimi K3 Fast is available through 3 providers: Inference.net, Parasail, and MorphLLM.
Kimi K3 Fast accepts up to 1M tokens of context on its largest provider route.
Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "kimi-k3-fast". To set it up with a coding agent, copy the agent setup prompt at the top of this page.
Certified where it counts.
Built to meet the security and privacy standards that enterprise and healthcare teams require.
ISO 27001
The internationally recognized standard for information security management.
SOC 2
Secure, compliant management of your data across all of our systems.
GDPR
Operated under GDPR, the world's strictest standard for data privacy.
HIPAA
HIPAA compliant, with a BAA available for healthcare teams.