Models & slugs

Use the canonical customer slug and keep it simple.

CorvusLLM may accept additional aliases, but these docs always show one clean slug per model. Copy the slug below instead of guessing variants from memory.

Before choosing a model

No local install is required to read model slugs. To verify a slug, use curl or an OpenAI-compatible SDK against the live models endpoint.

What to installOfficial sourceQuick check
CorvusLLM keyBuy or top up balanceNeeded for model requests.
curlBuilt into most terminals.curl --version
Optional SDK runtimesPython downloads or Node.js downloadUseful after you pick a slug.
Local checks
curl --version

Short answer

Use the public CorvusLLM model slug exactly as listed in the canonical table. The public slug is the value customers paste into SDKs, apps, and Claude-compatible tools. Internal upstream model names and provider-side aliases are implementation details.

One visible slug keeps setup predictable.

A model may have routing rules, provider fallbacks, or internal aliases behind the scenes. Customer docs intentionally expose one recommended slug so tools do not drift across different naming styles.

How to choose a model

Use caseRecommended choiceWhy
Claude Code or Anthropic-native clientsClaude public slugThe Anthropic-native path keeps message semantics, tool calling, and Claude-style settings aligned.
OpenAI SDKs, Open WebUI, scripts, backend appsOpenAI-compatible public slugThe /v1 endpoint is the broadest compatibility path.
Lowest-cost automationSmaller or faster model familyShort prompts, extraction jobs, and simple classification usually do not need premium reasoning models.
Long reasoning or agentic codingPremium reasoning-capable modelHard coding tasks and multi-step analysis benefit from stronger reasoning even when the per-token price is higher.

Slug check flow

  1. List models with the curl command below or copy a slug from the canonical table.
  2. Send one small non-streaming request before configuring a larger app.
  3. If the request fails, check the base URL, the auth header, and the exact model string before changing application code.
List available models
curl https://base.corvusllm.com/v1/models \
  -H "Authorization: Bearer YOUR_CORVUSLLM_KEY"

Canonical model table

Model Customer slug Provider Best path Best environments CorvusLLM pricing

Provider pricing snapshots

These tables use the live public catalog. Each provider block keeps the official prices, source link, verification state, and CorvusLLM customer price in one scan-friendly table.

Common model mistakes

  • Using an official provider model ID when the tool is configured for the CorvusLLM public catalog. Use the customer slug shown here.
  • Using an old slug from a copied chat or screenshot. Recheck the live docs when a model lineup changes.
  • Switching the base URL but leaving a tool's default model selected. Both the base URL and model value must match the CorvusLLM setup.
  • Testing a complex streaming or tool-calling workflow before a small plain chat request succeeds.
Model catalog

Browse the public model-family directory before choosing a slug.

 Claude API models

Review Claude-family rows, use cases, and setup links.

 GPT API models

Review GPT-family rows for OpenAI-compatible workflows.

 Gemini API models

Review Gemini rows, public slugs, and pricing references.

 DeepSeek API models

Review DeepSeek rows for cost-sensitive reasoning and automation workflows.

 Cost calculator

Estimate request cost before using a new model in production.

 Pricing tracker

Check source-linked official-rate comparison context.

Important note

These docs do not list every accepted alias.

They intentionally list the one slug we recommend customers copy into tools and code.

Topic map

Continue with the right source

Open the exact setup, model, billing, and troubleshooting pages instead of guessing configuration values.

docs Set up CorvusLLM without guessing. Overview: The clean start page: base URLs, model overview, environment overview, and where to begin. docs API base URLs and request paths. API Overview: Base URLs, authentication, request formats, OpenAI-compatible vs Anthropic-native paths. docs Most CorvusLLM issues are the same four mistakes. Troubleshooting: Clear fixes for wrong base URLs, bad model slugs, out-of-balance errors, delivery questions. landing Claude API Pricing Comparison CorvusLLM lists public Claude-family rows at 35% of tracked official input, output, cache-read. landing GPT API Pricing Comparison CorvusLLM lists public GPT-family rows through an OpenAI-compatible access layer with public prepaid rates derived from tracke. landing AI API Cache Token Pricing Cache-heavy requests can cost very differently from short prompts because cache read and cache write fields may dominate the b. pricing AI API Pricing Tracker The pricing tracker compares official provider API prices with CorvusLLM public prepaid rates and links the model data used fo. pricing LLM API cost calculator The CorvusLLM cost calculator estimates request cost from input, output, cache read. models AI Models The CorvusLLM model catalog directory helps users find current customer-facing model families, public slugs, pricing context. trust Trust Center The Trust Center explains affiliation, data handling, support, refunds, compatibility evidence, pricing methodology. trust How to Verify CorvusLLM Before You Buy The verification checklist shows how to test CorvusLLM claims, endpoint setup, pricing data, status, legal pages. trust Proof of Operations Proof of Operations collects public evidence assets, published data, operational boundaries. status Checking current status The status page shows customer-facing live checks for website, checkout, customer login, and API compatibility routes. faq Frequently Asked Questions CorvusLLM FAQ and help center with searchable answers about pricing, refunds, delivery, API setup, Cursor, Claude Code.
Browse docs
On this page