Skip to main content

Kimi K3.1 Pro (US)

Kimi K3.1 Pro sparse MoE model (the post-trained update of Kimi K3), self-hosted on the Wafer fleet. Available serverless with a 1M-token context window and strong coding/agentic performance.

Input / output price
$2.00 / $10.00 per 1M
Context
1M tokens
Released
Oct 23, 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-k3.1-pro-us".

Read docs

Providers

One provider serves this model, priced per 1M tokens after gateway discounts.

ProviderInputOutput
Waferwafer/Kimi-K3.1-Pro-US
$2.00/M$10.00/M

Pricing

USD per 1M tokens on Wafer, after gateway discounts.

Input
$2.00 per 1M
Output
$10.00 per 1M
Cache read
$0.20 per 1M

Cost by volume

Total cost from 0 to 1T tokens.

$2.00/MWafer

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

81tokens/sacross providers

Faster than 74% of the other 599 models on the gateway

Response latency

Lower is better

0.5sacross providers

Faster than 86% of the other 780 models on the gateway

Benchmarks

The Respan Index plus 11 published scores from 4 sources, each linked to where it was published.

71.4/ 100

Respan Index#9 of 176

176 ranked models. The shaded band is this model's 95% interval, 60.1 to 79.1. Claude Fable 5.1 and Muse Wonder Full fall inside it, so the gap is within the margin of error.
Kimi K3.1 Pro (US) by category: Coding 68.7, Agents 70.3, Reasoning 82.7 (estimated), Knowledge & language 72.2 (estimated), Human preference 58.3
  1. 9Kimi K3.1 Pro71.4
  2. 7Claude Fable 5.172.3
  3. 10Muse Wonder Full70.8

Published scores

BenchmarkScore
Terminal-Bench 4.0kimi.com65.7%
Terminal-Bench 4.0Vals AI63.6%
Kimi Code Bench 3.0 Long-horizonkimi.com61.2%

Compare Kimi K3.1 Pro (US): Kimi K3.1 Pro vs Kimi K3, Kimi K3.1 Pro vs Kimi K2.6, Kimi K3.1 Pro vs Kimi K2.7 Code, Kimi K3.1 Pro vs Kimi K2.5, Kimi K3.1 Pro vs Kimi K2

Apps

Use Kimi K3.1 Pro (US) 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 K3.1 Pro (US) FAQ

Short answers, built from the data on this page.

Kimi K3.1 Pro (US) is a model from Moonshot, released on Oct 23, 2026. Kimi K3.1 Pro sparse MoE model (the post-trained update of Kimi K3), self-hosted on the Wafer fleet. Available serverless with a 1M-token context window and strong coding/agentic performance.

On the Respan gateway, Kimi K3.1 Pro (US) costs $2.00 per 1M input tokens and $10.00 per 1M output tokens on Wafer, after gateway discounts.

Kimi K3.1 Pro (US) is served by Wafer.

Kimi K3.1 Pro (US) accepts up to 1M tokens of context.

Point any OpenAI-compatible SDK at https://gateway.respan.ai/v1 with your Respan API key and set the model to "kimi-k3.1-pro-us". To set it up with a coding agent, copy the agent setup prompt at the top of this page.

Kimi K3.1 Pro (US) scores 71.4 out of 100 on the Respan Index v1.1, ranking #9 of 176 models. By category: Coding 68.7, Agents 70.3, Reasoning 82.7 (estimated), Knowledge & language 72.2 (estimated), and Human preference 58.3. The Respan Index combines independent and lab-reported benchmark results into one score, using benchmark data collected by Respan.

Kimi K3.1 Pro (US) has 11 published benchmark scores, including Terminal-Bench 4.0 65.7%, APEX-Agents 65.5%, and LMArena WebDev 1683. Each score links to where it was published; the data is collected by Respan.

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.