Resolve a model
resolveWhich model to call for a need, on the providers the user has accounts with: the provider's own model id, its price, capabilities and the reason. Give providers and a task or a purpose; add needs, budget, origin and other constraints to narrow it. shape asks for a team or an escalation ladder instead of one model. Counts as one call. An answer of no_candidate names what ruled every model out and the nearest miss. The answer depends on these goals; have the ones that matter in hand from the plan, the repository or the user before calling: cost (optimize, max_price, budget, calls_per_user_month); depth (optimize, quality_margin, min_quality, budget, shape, needs); maker_origin (origin, origin_strict); data_region (regions); languages (languages); data_kind (needs); accounts (providers). Send them as query parameters.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"providers": "<providers>"
},
"name": "resolve"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| task | No | A task, e.g. text.chat. Required unless purpose is given. | |
| hours | No | UTC hours you make your calls in, every day, as HH-HH ranges: 09-17, or 22-06 past midnight, or 00-24. A price with cheaper hours then ranks on its average over these hours instead of over a flat week. Comma-separated. | |
| needs | No | Required capabilities, optionally with a level: "input.pdf:native". Comma-separated. | |
| pages | No | PDF pages per call. | |
| roles | No | Team roles: "name:count" pairs, comma-separated (lead:1,workers:4), or a JSON object of role name to { count, task, needs, min_quality, optimize, distinct_vendor_from, distinct_family, judges }. Overrides and extends the strategy's roles. | |
| shape | No | single (default, or the purpose's), team (with strategy or roles) or escalation (a ladder of length steps, or one model then a team with strategy or roles). | |
| budget | No | Thirds of the market's prices for the task. | |
| images | No | Input images per call. | |
| length | No | Escalation steps, 1–5 (default 3). | |
| origin | No | Model maker countries or groups: "us", "eu", "not:cn". Comma-separated. | |
| exclude | No | Model ids, vendors, or provider:model pairs to leave out. Comma-separated. | |
| license | No | Accepted open-weight licenses. Comma-separated. | |
| purpose | No | A purpose preset id or alias, e.g. read-receipts. | |
| regions | No | Where data may be served, as region codes or their prefixes: "eu", "us", "us-east". It filters only when at least half the offerings on your providers state a region; below that, nothing is removed and the answer warns region_not_filtered. An offering that states no region is kept, with region_unstated. Comma-separated. | |
| currency | No | Adds the typical call converted to this currency, e.g. EUR. | |
| optimize | No | cost (default), quality or value. | |
| strategy | No | A team strategy preset: its roles and their rules. | |
| languages | No | Languages your users write in, as language tags: "en", "de", "pt-BR". With one other than English, the non-English quality signal leads for a purpose that lists it; when the answer could not be compared on it, it warns language_signal_unavailable. Comma-separated. | |
| max_price | No | Hard cap on the typical call, in USD, e.g. 0.002, at the day's highest rate. | |
| providers | Yes | Required. Provider names you have accounts with, in order of preference for ties. Never keys. Comma-separated. | |
| synthesis | No | Add a synthesizer role to the team. | |
| origin_mix | No | Team origin rules: "eu:>=1", "cn:<=0", "us:=2". Comma-separated. | |
| resolution | No | Image resolution key, e.g. "1k". | |
| allow_trial | No | Allow trial offerings, which aren't for production (default false). | |
| max_disk_gb | No | Local runtimes: free disk in GB for the weights. | |
| max_vram_gb | No | Local runtimes: GPU memory in GB, for a full offload. On Apple silicon send the GPU's share of unified memory (macOS allows about 2/3 by default, 3/4 above 36 GB) and the total as max_memory_gb. | |
| min_context | No | Minimum context window in tokens. | |
| min_quality | No | Minimum quality score, 0–1. | |
| allow_closed | No | Allow models the provider has closed to new accounts. Send true only if your account used them before (default false). | |
| input_tokens | No | Expected input tokens per call. | |
| service_tier | No | ||
| allow_preview | No | Allow preview models (default false). | |
| audio_seconds | No | Audio seconds per call. | |
| max_memory_gb | No | Local runtimes: the device's memory in GB (10^9 bytes). A local offering fits when its weights, KV cache at the request's min_context (8,192 tokens when smaller) and runtime overhead fit. Cloud offerings are not limited. | |
| origin_strict | No | Also require a fine-tune's base model maker to match. | |
| output_images | No | Generated images per call. | |
| output_tokens | No | Expected output tokens per call. | |
| prompt_tokens | No | Prompt size, for long-prompt price tiers. | |
| video_seconds | No | Video seconds per call. | |
| provider_terms | No | Your terms per provider: "openrouter:byok", "gemini:free_tier", "openai:discount:0.2". Comma-separated. | |
| quality_margin | No | For optimize=cost: how far below the best score still counts (default 0.05). | |
| released_after | No | YYYY-MM-DD. | |
| providers_distinct | No | Every team member, or escalation step, on a different provider. | |
| cached_input_tokens | No | Input tokens served from the provider's cache. | |
| calls_per_user_month | No | How many calls one user makes in a month. With it, the chosen model's price carries per_user_month and the sum behind it; without it, nothing monthly is returned. |