AI Models

All models available through CorvusLLM - with listed public rows priced 65% below tracked official API rates. Click any card for detailed specs, use-cases, and setup guidance.

All Models

Supported model catalog

Every model below is available through CorvusLLM's OpenAI-compatible API proxy. You connect once; switch models by changing a single parameter.

Direct answer: use this directory to find the customer-facing model family, current public slug, public pricing context, and the correct next page for setup. For exact machine-readable availability, use data/models.json.
Exact slugs

Use the public catalog rows and model docs. Do not use internal route names, backup labels, or guessed provider IDs.

Cost planning

Use the cost calculator and pricing tracker before long-context, cache-heavy, or bulk usage.

Anthropic - Claude

Anthropic Claude Haiku 4.5

Fast Claude tier for high-throughput automation, summarisation, extraction, and lightweight assistant work.

Official input: $1.00/1M Official output: $5.00/1M Cache read: $0.100/1M
Public slug claude-haiku-4-5
Fast Verified pricing OpenAI-compatible
Open model detail
Anthropic Claude Opus 4.5

Highest-capability Claude tier for deep reasoning, multi-step coding, and long research workflows when quality matters more than speed.

Official input: $5.00/1M Official output: $25.00/1M Cache read: $0.500/1M
Public slug claude-opus-4-5
Max capability Verified pricing OpenAI-compatible
Open model detail
Anthropic Claude Opus 4.6

Highest-capability Claude tier for deep reasoning, multi-step coding, and long research workflows when quality matters more than speed.

Official input: $5.00/1M Official output: $25.00/1M Cache read: $0.500/1M
Public slug claude-opus-4-6
Max capability Verified pricing OpenAI-compatible
Open model detail
Anthropic Claude Opus 4.7

Highest-capability Claude tier for deep reasoning, multi-step coding, and long research workflows when quality matters more than speed.

Official input: $5.00/1M Official output: $25.00/1M Cache read: $0.500/1M
Public slug claude-opus-4-7
Max capability Verified pricing OpenAI-compatible
Open model detail
Anthropic Claude Sonnet 4.5

Balanced Claude tier for day-to-day coding, agent loops, writing, and analysis with a strong quality-to-speed tradeoff.

Official input: $3.00/1M Official output: $15.00/1M Cache read: $0.300/1M
Public slug claude-sonnet-4-5
Balanced Verified pricing OpenAI-compatible
Open model detail
Anthropic Claude Sonnet 4.6

Balanced Claude tier for day-to-day coding, agent loops, writing, and analysis with a strong quality-to-speed tradeoff.

Official input: $3.00/1M Official output: $15.00/1M Cache read: $0.300/1M
Public slug claude-sonnet-4-6
Balanced Verified pricing OpenAI-compatible
Open model detail

OpenAI - GPT

OpenAI GPT 5.4

Flagship GPT tier exposed through CorvusLLM for strong coding, analysis, and general assistant workloads with a familiar OpenAI-compatible shape.

Official input: $2.50/1M Official output: $15.00/1M Cache read: $0.250/1M
Public slug gpt-5.4
Verified pricing OpenAI-compatible
Open model detail
OpenAI GPT 5.5

GPT 5.5 is available through CorvusLLM's shared catalog with the same public slug everywhere the product surfaces it.

Official input: $5.00/1M Official output: $30.00/1M Cache read: $0.500/1M
Public slug gpt-5.5
Verified pricing OpenAI-compatible
Open model detail

Google - Gemini

Gemini tier for multimodal and long-context tasks, especially when you want image-aware reasoning or broad retrieval-heavy prompts.

Official input: $2.00/1M Official output: $12.00/1M Cache read: $0.200/1M
Public slug gemini-3.1-pro
Multimodal Verified pricing OpenAI-compatible
Open model detail

Gemini tier for multimodal and long-context tasks, especially when you want image-aware reasoning or broad retrieval-heavy prompts.

Official input: $3.60/1M Official output: $12.00/1M Cache read: $0.360/1M
Public slug gemini-3.1-pro-high
Multimodal Verified pricing OpenAI-compatible
Open model detail

DeepSeek

DeepSeek DeepSeek V4 Pro

DeepSeek V4 Pro is available through CorvusLLM's shared catalog with the same public slug everywhere the product surfaces it.

Official input: $1.74/1M Official output: $3.48/1M Cache read: $0.015/1M
Public slug deepseek-v4-pro
Verified pricing OpenAI-compatible
Open model detail

DeepSeek V4 Flash is available through CorvusLLM's shared catalog with the same public slug everywhere the product surfaces it.

Official input: $0.140/1M Official output: $0.280/1M Cache read: $0.003/1M
Public slug deepseek-v4-flash
Verified pricing OpenAI-compatible
Open model detail

Model comparisons

Use these static comparison pages for crawlable side-by-side checks before choosing a default model row.

Interactive directory

Topic map

Continue with the right source

Move from model selection to exact slugs, cost estimates, billing behavior, and service limits without relying on old screenshots.

docs Use the canonical customer slug and keep it simple. Models & Slugs: Every customer-facing model with one customer slug, provider family, pricing. 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. landing OpenAI-Compatible AI API Proxy CorvusLLM provides an independent OpenAI-compatible AI API proxy for buyers who need prepaid balance, setup docs. landing AI API for Cursor CorvusLLM can be used in Cursor builds that expose custom provider fields; this page explains the commercial fit. landing Claude, GPT, Gemini & DeepSeek API CorvusLLM offers one independent endpoint for supported Claude, GPT, Gemini, and DeepSeek access. landing Bulk AI API Access The bulk AI API page is for teams, agencies, and automation buyers who can describe expected usage, model families, key needs. landing OpenRouter Alternative for Prepaid AI API Access The OpenRouter alternative page compares CorvusLLM with broader AI gateways by fit, model breadth, billing style, setup. landing AI API for Coding Agents CorvusLLM can fit coding-agent workflows when the user wants one prepaid key. landing AI API for Open WebUI Teams CorvusLLM can fit Open WebUI teams that need a custom OpenAI-compatible backend, a prepaid balance model. landing AI API for n8n Automation CorvusLLM can fit n8n automation when workflows need explicit HTTP request configuration, prepaid usage, public model slugs. landing AI API for App Prototyping CorvusLLM can fit app prototyping when the goal is to test an AI feature quickly with OpenAI-compatible SDKs. landing AI API for Cost-Sensitive Workloads CorvusLLM can fit cost-sensitive workloads when the user can estimate token volume, avoid sensitive data. landing AI API for Multi-Model Routing CorvusLLM can fit multi-model routing when the user wants one prepaid key for supported public catalog model families.