Kimi Token API Pricing, Top-up, Deals & Updates | Article

Kimi Token API pricing. Kimi K3, Kimi K2.7 Code and 9 more models. OpenAI-compatible API, Claude Code, Cline and 1 more tools integrations. Includes cache tiers and rate limits. API key setup, usage quotas, and official entry—is it worth it?

41
Platforms
395+
Models
140+
IDE Tools
11
Kimi Token API models
¥2 / ¥10
Kimi Token API entry price
View
Vendor details

Kimi API Latest Updates

Kimi K3 Released: World's First Open 3T-Class Model, Now on API

Published Updated
ModelK3Kimi K3Model ReleaseAPI UpdateOpen Source
Summary

On July 16, 2026, Moonshot AI released Kimi K3 — a 2.8T-parameter MoE model and the world's first open 3T-class model. K3 API is now available at $0.30/MTok (cache-hit input), $3.00/MTok (cache-miss input), and $15.00/MTok (output), with >90% cache hit rate on coding workloads.

API Update Overview

Kimi K3 is a 2.8-trillion-parameter open-source MoE model released by Moonshot AI on July 16, 2026, with immediate API availability (source). The world's first open 3T-class model, featuring native vision and a 1-million-token context window.

In official evaluations, K3 consistently outperforms all other tested models, though still trailing Claude Fable 5 and GPT 5.6 Sol.

Architectural Innovations

K3's architecture centers on Kimi Delta Attention (KDA) and Attention Residuals (AttnRes), with quantization-aware training and fully-balanced expert parallelism for efficient inference (source).

Kimi Delta Attention (KDA)

KDA optimizes attention information flow across sequence length. A KDA prefix cache implementation has been contributed to vLLM, achieving >90% cache hit rate on long-context API workloads for dramatically lower inference cost.

Attention Residuals (AttnRes)

AttnRes selectively retrieves representations across depth rather than accumulating them uniformly, improving training stability in very deep models.

Stable LatentMoE

K3 scales MoE to 896 experts (16 active). Quantile Balancing derives allocation from router-score quantiles. Per-Head Muon optimizes attention heads independently.

Quantization & Inference Optimization

K3 applies quantization-aware training from SFT onward, using MXFP4 weights + MXFP8 activations for broad hardware compatibility. Fully-balanced expert-parallel training (static shapes, no host sync on critical path) prevents throughput degradation at large scales. 64+ accelerator supernode configurations are recommended for optimal inference.

Coding Capabilities

K3 excels at long-horizon autonomous coding — competing with Claude Fable 5 on kernel optimization, and building its own GPU compiler and chip (source).

Kernel Optimization

In head-to-head comparison with Claude Fable 5 and GPT 5.6 Sol, K3 completed profiling, rewriting, and benchmarking across NVIDIA Hopper GPUs and alternative GPGPUs within 24 hours, substantially outperforming Opus 4.8 and GPT 5.6 Sol.

GPU Compiler Development

K3 built MiniTriton from scratch — a Triton-like GPU compiler with its own tile-level IR, optimization passes, and PTX codegen pipeline. Roofline benchmarks match or beat Triton and torch.compile.

Chip Design

In a single 48-hour autonomous run, K3 designed a chip using open-source EDA tools (Nangate 45nm). Within 4 mm²: 1.46M standard cells, 0.277 MB SRAM, INT4 MAC array at 8,700+ tokens/s decode.

API Pricing & Availability

K3 is live on the Kimi API Platform (platform.kimi.ai) — model weights were open-sourced on July 27, 2026.

Pricing

Item Price Notes
Cache-hit input $0.30 / MTok >90% hit rate on coding
Cache-miss input $3.00 / MTok First request or expired cache
Output $15.00 / MTok Per generated token

With Mooncake's disaggregated inference and KDA prefix caching, cache hit rates exceed 90% on coding workloads.

Access

Visit the Kimi API Platform and select kimi-k3. 64+ accelerator supernode deployment is recommended.

Limitations

K3's main limitations are thinking history sensitivity and over-proactiveness — use explicit behavioral constraints in API system prompts (source).

  1. Thinking history sensitivity: K3 was trained in preserved thinking history mode. Agent harnesses must pass back all thinking content. Switching models mid-session may cause instability.
  2. Over-proactiveness: K3's training emphasizes long-horizon tasks. Provide more explicit behavioral instructions in API calls.
  3. Overall user experience still shows a gap vs Claude Fable 5 and GPT 5.6 Sol.

Sources and verification

Last verified

Kimi Token API FAQ

What is the Kimi K3 API pricing? How does it compare to K2?

K3 API pricing: $0.30/MTok for cache-hit input, $3.00/MTok for cache-miss input, and $15.00/MTok for output. Powered by Mooncake's disaggregated inference architecture and KDA prefix caching, cache hit rates exceed 90% on coding workloads, maintaining competitive pricing even at million-token contexts. K3 achieves ~2.5× overall scaling efficiency improvement over K2.

Is Kimi K3 open source? When were the weights released?

Yes, K3 is the world's first open 3T-class model. Full model weights were released on July 27, 2026. The KDA prefix caching implementation has also been contributed to the vLLM community.

How do I access Kimi K3 via API?

Visit the Kimi API Platform (platform.kimi.ai) and select the kimi-k3 model. For optimal inference efficiency, we recommend deploying on supernode configurations with 64 or more accelerators.
AI Token Plan

Global AI Token Comparison

AI Token Plan is not just a collection of vendor links. It places 41+ domestic and international AI platforms into one comparison framework, covering 395+ model entries plus common plan types such as Token Plans, Coding Plans, IDE Tools and LLM APIs.

When you need to compare AI subscription pricing, coding plan quota, API usage cost or official deal entry points, AI Token Plan brings official prices, plan tiers, usage rules, model capabilities and tool integrations into one place, reducing the need to check multiple vendor sites manually.

Data is continuously organized as vendor pricing pages, plan pages and product documentation change, making the homepage a pricing comparison entry point while detail pages explain whether each vendor plan fits individual developers, team purchasing or long-term API usage.

Prices come from each platform's official site and may change at any time; the official price prevails.

© 2026 AI Token Plan · All rights reserved · First published June 18, 2026 · 64 days running · Sitemap