Skip to main content

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
Agent setup

Paste into Claude Code, Cursor, or Codex

Help me set up the Respan gateway: fetch and follow https://www.respan.ai/docs/agent-setup.md. Use model "kimi-k3-fast".

Read docs

Providers

3 providers, cheapest first, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Inference.netinference_net/moonshotai/kimi-k3-fast
$4.50/M$22.50/M
Parasailparasail/moonshotai/Kimi-K3-fast
$4.50/M$22.50/M
MorphLLMmorphllm/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.

Highest$6.00/MMorphLLMLowest$4.50/MInference.net and Parasail

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 better

40tokens/sacross providers

Faster than 57% of the other 599 models on the gateway

Response latency

Lower is better

1.5sacross providers

Faster than 57% of the other 780 models on the gateway

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.

Works with your entire stack

Use Respan with your favorite frameworks and tools.

AnthropicAI21 LabsxAIVercel AI SDK
LangChainOpenRouterAssemblyAICursor
LiteLLMGroqBasetenMem0
CohereCogneeLlamaIndexFireworks
DeepSeekLinkupHaystackTogether AI
PerplexityInference.netPostHogRubyLLM
SlackMastraAzure OpenAIMistral
AWS BedrockMoonshotHyperspellBAML
ModaInstructorGoogle GeminiParasail
ReductoZapierAgnoNebius
OpenAINovita AIReplicateSuperagent

Built for AI agents.
Break less.
Ship more.