The right model for every agent.
Planning, building, testing and reviewing need different strengths. An AI profile decides which model each agent runs, so you pay for capability where it matters and save where it doesn’t. Use one of ours, or build your own.
- FreeZero CostUS$0.00 - US$0.30 / 1M tokens
- BudgetLow cost, everyday workUS$0.00 - US$1.20 / 1M tokens
- SmartestHighest capabilityUS$0.00 - US$50.00 / 1M tokens
- QuickFastest turnaroundUS$0.00 - US$10.00 / 1M tokens
- LudicrousSpeed over ceremonyUS$0.00 - US$5.00 / 1M tokens
- EU OnlyEU data residencyUS$0.00 - US$4.18 / 1M tokens
- Low carbonLower estimated CO2eUS$0.00 - US$5.00 / 1M tokens
Seven profiles, one choice per task
Every profile is a tested set of models for each agent role. Set a default for your organisation and override it for a single task or plan. Prices are live from the model catalog.
Cost against quality
Select a profile to open it
Output cost per million tokens
EU-hosted models only
Low carbon profile
Larger mark = faster
FreeZero CostNemotron 3 SuperJev 1.14Tencent Hy-MT2 30B A3BSpeedMediumQualityGoodUS$0.00 - US$0.30 / 1M tokensOutput · Input US$0.00 - US$0.07 / 1M tokens
Coroid routes each task to cost-efficient models at no cost to you. Good for trying Coroid and for lightweight work. The models used may change over time.
Best For
- Evaluating Coroid
- Personal projects
- Lightweight coding tasks
- Zero-budget experimentation
- Input
- US$0.00 - US$0.07 / 1M tokens
- Output
- US$0.00 - US$0.30 / 1M tokens
- Models
- Nemotron 3 Super · Jev 1.14 · Tencent Hy-MT2 30B A3B
BudgetLow cost, everyday workGLM-5.3 FlashTencent Hy-MT2 30B A3BDeepSeek V4.1 Flash 1017+2SpeedFastQualityGoodUS$0.00 - US$1.20 / 1M tokensOutput · Input US$0.04 - US$0.30 / 1M tokens
Cost-efficient models for routine implementation, documentation, and refactoring, where the spec is clear and the change is contained.
Best For
- Simple feature implementations
- Documentation and comments
- Code formatting and linting
- Refactoring tasks
- Input
- US$0.04 - US$0.30 / 1M tokens
- Output
- US$0.00 - US$1.20 / 1M tokens
- Models
- GLM-5.3 Flash · Tencent Hy-MT2 30B A3B · DeepSeek V4.1 Flash 1017 · Nemotron 3 Nano 30B · Jev 1.14
- Est. CO2e
- 927.5 g / 1M
- Estimated operational inference electricity using Ember/eGRID location factors. Excludes training, devices, water, and embodied hardware.
SmartestHighest capabilityFable 5Jev 1.14Tencent Hy-MT2 30B A3B+1SpeedMediumQualityOutstandingUS$0.00 - US$50.00 / 1M tokensOutput · Input US$0.04 - US$10.00 / 1M tokens
The strongest available models, for architecture decisions, hard debugging, and security-critical code where a wrong call costs more than the tokens.
Best For
- Complex architecture design
- Debugging intricate issues
- Security-critical code
- Algorithm optimisation
- Input
- US$0.04 - US$10.00 / 1M tokens
- Output
- US$0.00 - US$50.00 / 1M tokens
- Models
- Fable 5 · Jev 1.14 · Tencent Hy-MT2 30B A3B · Sonnet 5
- Est. CO2e
- 548.8 g / 1M
- Estimated operational inference electricity using Ember/eGRID location factors. Excludes training, devices, water, and embodied hardware.
QuickFastest turnaroundGPT-6 SolJev 1.14Tencent Hy-MT2 30B A3B+3SpeedFastQualityGoodUS$0.00 - US$10.00 / 1M tokensOutput · Input US$0.03 - US$2.00 / 1M tokens
Fast, inexpensive models for small fixes, prototypes, and exploration, when a quick answer is worth more than a deep one.
Best For
- Rapid prototyping
- Quick iterations
- Simple fixes
- Exploration tasks
- Input
- US$0.03 - US$2.00 / 1M tokens
- Output
- US$0.00 - US$10.00 / 1M tokens
- Models
- GPT-6 Sol · Jev 1.14 · Tencent Hy-MT2 30B A3B · Nemotron 3 Nano 30B · Haiku 4.5 · Qwen3.7 Flash
- Est. CO2e
- 235.2 g / 1M
- Estimated operational inference electricity using Ember/eGRID location factors. Excludes training, devices, water, and embodied hardware.
LudicrousSpeed over ceremonyJev 1.14Haiku 4.5Tencent Hy-MT2 30B A3BSpeedFastQualityExcellentUS$0.00 - US$5.00 / 1M tokensOutput · Input US$0.04 - US$1.00 / 1M tokens
The fastest models with relaxed quality gates. Use it for drafts and urgent fixes, and expect to review the output more closely.
Best For
- Emergency fixes
- Maximum velocity
- Draft implementations
- Rapid experimentation
- Input
- US$0.04 - US$1.00 / 1M tokens
- Output
- US$0.00 - US$5.00 / 1M tokens
- Models
- Jev 1.14 · Haiku 4.5 · Tencent Hy-MT2 30B A3B
- Est. CO2e
- 235.2 g / 1M
- Estimated operational inference electricity using Ember/eGRID location factors. Excludes training, devices, water, and embodied hardware.
EU OnlyEUEU data residencyMistral Large 4Jev 1.14Tencent Hy-MT2 30B A3BSpeedFastQualityExcellentUS$0.00 - US$4.18 / 1M tokensOutput · Input US$0.04 - US$1.36 / 1M tokens
Runs only on models hosted in the EU, so prompts and code are processed within EU jurisdiction. Built for teams with GDPR and data-residency requirements.
Best For
- GDPR-sensitive projects
- EU data residency requirements
- Privacy-critical applications
- Enterprise compliance
- Input
- US$0.04 - US$1.36 / 1M tokens
- Output
- US$0.00 - US$4.18 / 1M tokens
- Models
- Mistral Large 4 · Jev 1.14 · Tencent Hy-MT2 30B A3B
Low carbonLower estimated CO2eHaiku 4.5Jev 1.14Mistral Small 4+1SpeedFastQualityGoodUS$0.00 - US$5.00 / 1M tokensOutput · Input US$0.04 - US$1.00 / 1M tokens
Prefers smaller models on lower-intensity grids. Estimates are operational inference only — not a carbon-neutral guarantee.
Best For
- Lower-intensity inference
- Efficient coding agents
- Cleaner-grid routing
- Everyday software work
- Input
- US$0.04 - US$1.00 / 1M tokens
- Output
- US$0.00 - US$5.00 / 1M tokens
- Models
- Haiku 4.5 · Jev 1.14 · Mistral Small 4 · Tencent Hy-MT2 30B A3B
- Est. CO2e
- 235.2 g / 1M
- Estimated operational inference electricity using Ember/eGRID location factors. Excludes training, devices, water, and embodied hardware.
Or assign every agent yourself
Professional and Enterprise organisations create their own profiles. Start from any Coroid profile — its agent models, fallbacks, and policies are copied in — then change whatever the work needs. Every active model in the catalogue is available to pick from.
Professional and Enterprise99 models · 8 providers
- Primary model
- The model that role runs by default.
- Fallback model
- Where the work goes if the primary is unavailable. Optional, per role.
- Reasoning effort
- How hard the model works the problem before it answers.
- Whose key pays
- Your own provider key or Coroid credits — each model in the profile says which.
- Delivery
- Architect · Developer · Quality assurance · Reviewer
- Support
- Web tester · Assistant · Attachment inspector · Dependency analyser · Explorer
- Automation
- Hook executor · Developer sub-agent
A few roles narrow the list: the assistant needs a conversational model, and the attachment inspector needs one that can see images.
Owners and admins create and edit profiles. Members choose from them in the work they raise.
One default, overridden where it matters
- Organisation default
- Every piece of work runs on it unless something says otherwise.
- Per task or plan
- Override the profile on a single task or a phased plan before it starts.
- Per automation
- Hooks and schedules can run on a profile of their own — cheap models for routine watching, capable ones when it matters.
- Locked once it runs
- A task keeps the profile it started with, and finished work keeps the profile it ran with, so its cost and evidence stay readable later.
Chosen on merit, not origin
The catalog spans frontier labs and open-weight models from around the world. Profiles draw on both:
- Frontier models: the strongest reasoning, for architecture, security-critical code, and hard debugging.
- Cost-efficient open-weight models: strong coding at a fraction of the price, for routine work at scale. Use the EU Only profile when data residency matters.