Moonshot models in Big-AGI

Kimi K3's million-token context at Moonshot's own rates - both catalogs, pay-per-token and the Kimi Code subscription, with retired models marked in the list.

Kimi K3.1 Pro Kimi K3.1 Pro Highspeed Kimi K2.7 Code Kimi K3 Kimi K2.7 Code Highspeed

Moonshot setup guide Moonshot models

All supported Moonshot models

ModelContextInputOutputReleased

Kimi K3.1 ProNEWMost capable flagship: K3 with scaled-up post-training, stronger coding, 3D creation and financial research. Native multimodal (text, image, video inputs), thi…1M$2.00$10.00Oct 2026 Kimi K3.1 Pro HighspeedNEWHigh-speed K3.1 Pro: same model at about 2-3x the output speed. Native multimodal (text, image, video inputs), thinking on by default. 1M context.1M$4.00$20.00Oct 2026 Kimi K3Previous-generation flagship (2.8T parameters), native multimodal (text, image, video inputs) with thinking on by default. 1M context.1M$3.00$15.00Jul 2026 Kimi K2.7 CodeCode-focused multimodal model (text, image, video inputs) with always-on thinking. ~180 tok/s output (up to 260 in short contexts for highspeed). 256K context.262K$0.95$4.00Jun 2026 Kimi K2.7 Code HighspeedHigh-speed code variant with ~180 tok/s output (up to 260 in short contexts). Native multimodal with always-on thinking. 256K context.262K$1.90$8.00Jun 2026 Kimi K2.6Native multimodal flagship (text, image, video inputs) with thinking and non-thinking modes. Stronger long-form coding, improved instruction compliance and sel…262K$0.95$4.00Apr 2026 Kimi K2.5deprecatedSupports vision (images/videos), thinking mode, and Agent tasks. 256K context. Sunset on 2026-08-31.262K$0.60$3.00Jan 2026 V1 128K Vision (Preview)deprecatedLegacy vision model with 128K context. Sunset on 2026-08-31 - use Kimi K3 instead.131K$2.00$5.00Jan 2025 V1 32K Vision (Preview)deprecatedLegacy vision model with 32K context. Sunset on 2026-08-31 - use Kimi K3 instead.33K$1.00$3.00Jan 2025 V1 8K Vision (Preview)deprecatedLegacy vision model with 8K context. Sunset on 2026-08-31 - use Kimi K3 instead.8K$0.20$2.00Jan 2025 V1 128KdeprecatedLegacy V1 model with 128K context. Sunset on 2026-08-31 - use Kimi K3 instead.131K$2.00$5.00Feb 2024 V1 32KdeprecatedLegacy V1 model with 32K context. Sunset on 2026-08-31 - use Kimi K3 instead.33K$1.00$3.00Feb 2024 V1 8KdeprecatedLegacy V1 model with 8K context. Sunset on 2026-08-31 - use Kimi K3 instead.8K$0.20$2.00Feb 2024

13 models · sorted by release date · prices in USD per 1M tokens · refreshed hourlyCompare every model across vendors ->

Get started in 3 steps

Create an API key at the Moonshot console.

Paste it into Big-AGI's model settings.

Start chatting, or Beam it against other models and fuse the answers.

Running Moonshot in Big-AGI

Add your Moonshot API key and run the Kimi models at Moonshot's own API rates. Big-AGI adds no markup and no intermediary: billing runs directly between you and Moonshot, and your keys stay in your browser.

Your key, your billing. Usage is billed by Moonshot to your account. Big-AGI does not meter or charge for model usage.
Built for long context and tools. Kimi holds a very large context window and drives tool calls well, so it keeps up on agentic work and whole-codebase reads that shorter-context models choke on.
Freshness, judged honestly. Moonshot's API reports the same creation date for every model, so Big-AGI ignores that field rather than badging the whole catalog as new.

Why not just Kimi?

Kimi's own app is a solid way to chat, but it only ever shows you Kimi's take. Beam sends the same prompt to Kimi and to GPT, Claude, or Gemini at once, so a long-context read of your codebase or document gets checked against other labs' models before you trust it. You also get parameters Kimi's app does not expose: temperature, system prompt, per-turn model switching, and a real thinking on/off toggle for the Kimi models that support it (the flagship coding model reasons on every turn, so Big-AGI doesn't show a fake switch for it). Your keys stay in your browser instead of sitting on Moonshot's servers.

Your keys and your data

Turn on Direct Connection and the browser calls Moonshot directly, bypassing the Big-AGI server, whenever your key is client-side and Moonshot allows it. Your keys stay in your browser. Chats are stored locally first and sync only if you turn it on. The AI Inspector opens on any message to show the exact request sent to Moonshot, the token counts, and a cost estimate for that call.

Kimi in Beam

Run Kimi in parallel with Claude, GPT, and Gemini on the same prompt, then reach for Fusions: several strategies that combine, cross-check, and synthesize the parallel answers, which beats just picking the single best one. Parallel runs use more tokens than a single chat.

Bring your Moonshot key. Keep control.

Your key, your data, your choice of model. Big-AGI's Open branch is open source and self-hostable, so you can check exactly how Moonshot is called.

Launch Big-AGI

<- All Models

Alibaba

Anthropic

AWS Bedrock

Azure

Cerebras

DeepSeek

Fireworks AI

Google Gemini

Groq