PandaOSPandaOSby Pandata
Settings

Models

Connect and switch how PandaOS is powered: PandaOS Cloud, your own API keys, local models, or a provider subscription.

Ways to connect

PandaOS supports six model connections. You can set up all of them and switch between them at any time. Each connection has its own model catalog, and the models available in your chat picker reflect whichever connection is currently active.

ConnectionHow it worksBest for
PandaOS CloudIncluded with your subscription. Active by default after onboarding. You spend Credits as you work.Getting started immediately with no configuration.
Your API KeysAdd any number of providers (OpenAI, Anthropic, Google, Azure, OpenRouter, Mistral, and more) with your own credentials. Each provider may need an API key, base URL, region, or service-account JSON. You register which models each provider should expose.Full control over providers, pricing, and model selection.
LocalPandaOS scans for Ollama, LM Studio, KoboldCpp, and llama.cpp on their default ports and connects to whichever ones are running. You can add your own endpoint for any server that speaks /v1/chat/completions.Keeping prompts on your machine, or working offline.
OpenCode GoA subscription from opencode.ai, served through an OpenAI-compatible endpoint. Works with the OpenCode harness and with Claude Code.A single subscription across many models.
OpenAI CodexSign in with your ChatGPT account or paste an OpenAI API key (sk-...). Billed through your OpenAI account.Teams already invested in the OpenAI ecosystem.
ClaudeRun on your own Claude subscription, or on Claude models hosted in AWS Bedrock using a bearer token and region.Teams on an existing Anthropic or AWS contract.

Inside a connection

Every connection opens on three tabs, in the order you normally work through them:

TabWhat you do there
AccountSign in, paste a key, or add a region. A connection can hold several accounts, so you can keep a personal and a work login side by side and switch without signing out.
ModelsChoose which of the connection's models are shown in your pickers. Hiding the ones you never use keeps the composer short.
TiersSay which model each tier runs. Tiers are what agents, automations and new chats resolve against.

Selecting a connection makes it active immediately. Your next message uses it, with no restart.

Model tiers

Rather than one "default model", PandaOS resolves work through four tiers, set per connection. A connection you are not currently running on still has live tiers, because an agent or automation bound elsewhere resolves against the engine it runs on.

TierWhat runs on it
HighDeep work: planning, review, hard problems. Used by agents bound to the High tier.
MediumEveryday work, and the default for new chats. Changeable per chat in the composer.
LowQuick, simple tasks.
UtilityChat titles, commit messages, knowledge extraction. Nothing selects it, it just runs.

On PandaOS Cloud the tiers arrive pre-filled from the server's routing configuration and are re-seeded when that changes, but any tier you set by hand is respected from then on.

Each connection also carries its own reasoning effort default (Low through Max). Higher effort produces more thorough responses and uses more tokens. You can override effort per message in the composer, and an agent can carry its own effort override. See Agents for binding an agent to a tier or to one locked engine and model.

Auto-routing

With Auto selected in the composer, PandaOS picks a model per message based on how complex the request looks, instead of you choosing every time. Which model each complexity level maps to is exactly the tier configuration above, so tuning Auto means tuning your tiers.

The model catalog

Which models you can pick depends on the connection that is active. PandaOS Cloud serves a fixed catalog we host and pay for. Every other connection serves whatever your own account or machine exposes, so those catalogs are as wide as your keys are.

Per-token prices are not listed here. On PandaOS Cloud you spend a share of your plan's allowance rather than paying per model, and on every other connection you are billed by the provider directly, on their rates.

PandaOS Cloud

Fourteen chat models, several of them served from two providers at once so a provider outage does not take the model down with it.

ModelServed byNotes
GPT-5.5OpenAIAuto's medium and complex route on OpenAI
GPT-5.4OpenAIPrevious GPT generation
GPT-5 miniOpenAIAuto's simple route on OpenAI
GPT-5.3 CodexOpenAITuned for code
DeepSeek V4 FlashFireworks, TogetherAuto's default and coding route
DeepSeek V4 ProFireworks
MiniMax M2.7Fireworks, TogetherAuto's simple and medium route on both pools
MiniMax M3Fireworks, TogetherAuto's vision route, for images and visual work
GLM 5.2FireworksAuto's complex route on Fireworks
GLM 5.1Together
Kimi K2.6Fireworks, Together
Kimi K2.7Fireworks, TogetherAuto's complex route on Together
Kimi K3Fireworks, TogetherFrontier-priced, so it draws down faster
Qwen3.7 PlusFireworks

Claude models are not part of the PandaOS Cloud catalog. To run Claude, connect your own Claude subscription, an Anthropic key under Your API Keys, or Bedrock.

Voice, embeddings and image generation run on their own models, covered below.

Claude

The same eight models whether you arrive by Claude subscription, an Anthropic key, or Bedrock. Reasoning effort is per model, not universal, so the ladder below is what the composer will actually offer you.

ModelReasoning effortNotes
Claude Fable 5Low, Medium, High, MaxLatest Fable generation
Claude Opus 5Low, Medium, High, XHigh, MaxNewest Opus, most capable
Claude Opus 4.8Low, Medium, High, XHigh, MaxHidden by default while Opus 5 is present
Claude Opus 4.7Low, Medium, High, XHigh, MaxHidden by default while Opus 5 is present
Claude Opus 4.6Low, Medium, High, MaxHidden by default while Opus 5 is present
Claude Sonnet 5Low, Medium, High, MaxNear-Opus intelligence
Claude Sonnet 4.6Low, Medium, High, MaxHidden by default while Sonnet 5 is present
Claude Haiku 4.5Not applicableFastest and cheapest, no effort levels

Superseded generations are hidden from the composer until you opt back in from the connection's Models tab. Hiding is conditional: a model is only hidden while its successor is in the same list, so a connection whose newest Sonnet is 4.6 still shows it.

OpenAI Codex

Codex ships no fixed list. PandaOS reads the catalog from the Codex CLI on the account you signed in with, and remembers the last good answer per account, so the models you see are the ones your ChatGPT plan actually entitles you to.

The current generation is GPT-5.6, in Sol, Terra and Luna variants. Earlier ones (GPT-5.5, 5.4, 5.4 mini, 5.2, and 5.3 Codex Spark) are hidden by default once a newer generation appears in the same list.

Codex resolves reasoning effort against its own ladder rather than the shared one, and a model that does not accept an effort level simply will not be sent one.

Your API keys, Local, and OpenCode Go

These three have no catalog of ours to list, because the catalog is yours.

ConnectionWhere the list comes from
Your API KeysThe providers you add and the models you register on each. Because one list can mix keys, the picker groups models under the provider paying for them.
LocalWhatever is loaded in Ollama, LM Studio, KoboldCpp, llama.cpp, or your own endpoint. Grouped by runner, since the same model name can exist on two of them.
OpenCode GoThe models your opencode.ai subscription serves.

Voice, embeddings and image generation

The Models page also configures the models that are not chat models. Each is set independently of your coding engine, so switching harness never disturbs them.

CapabilityWhat it powersProviders
VoiceDictation in the composer and on mobile.PandaOS Cloud, or your own Together.ai or OpenAI key.
EmbeddingsSemantic search across your sessions and project knowledge.PandaOS Cloud, or your own key.
Image generationThe text-to-image tool in chat, generated pictures render inline in the thread.PandaOS Cloud, or your own OpenAI or Together key. In Codex with a ChatGPT login, PandaOS uses Codex's own hosted image tool and it bills to your ChatGPT plan.

Image generation is off until you turn it on from the Tools menu in the chat bar. The first PandaOS Cloud generation asks you to acknowledge that it spends Credits.

Provider preference

Several PandaOS Cloud models are served from two providers at once, for example DeepSeek V4 Flash and Kimi K2.7 run on both Fireworks and Together. Where that happens you can set a preference order, and PandaOS routes to the first available provider in it. That gives you a say in latency and in which pool absorbs the load, without changing model.

The same applies when a model you have on PandaOS Cloud is also reachable through a key of your own.

  • Credits - your PandaOS Cloud balance and top-ups.