Developer Catalog169+ Served Models · Zero Markup

Multi-Model Directory

Deploy, benchmark, and route across 70+ frontier LLMs, vision, and reasoning models through a single OpenAI-compatible API key. Live pricing updated with prompt caching discounts.

BenchmarksArena LadderboardCost EstimatorPlayground
169+Served Models
·
6 MajorHosting Clouds
·
0% Markup(Rule #28 Flat List Price)
·
Up to 90%Prompt Cache Savings
·
< 150msMedian TTFT
Quick filters:
169models available
Docs

Featured

Flagship models from top providers, benchmarked for production workloads.

OpenAI

Gpt 5.5

gpt-5.5

by OpenAI

OpenAI multimodal model supporting text and image inputs with a 1.05M token context window, 128K max output tokens, and knowledge cutoff of December 2025.

VisionCode
Input

$5.00/M

Output

$30.00/M

Mistral AI

Mistral Medium 2505

mistral-medium-2505

by Mistral AIhosted on Azure Foundry

mistral-medium-2505 is a high-performance chat foundation model with automated multi-cloud failover and guardrails on nRouter.

ChatCode
Input

$0.40/M

Output

$2.00/M

Anthropic

Claude Opus 5 5

claude-opus-5-5

by Anthropic

Anthropic claude-opus-5-5 is a high-performance chat foundation model featuring a 1M context window, with automated multi-cloud failover and guardrails on nRouter.

ChatVisionCode1M
Input

$5.00/M

Output

$25.00/M

DeepSeek

Deepseek V4.1 Flash

deepseek-v4.1-flash

by DeepSeekhosted on Alibaba US

deepseek-v4.1-flash is a high-performance chat foundation model with automated multi-cloud failover and guardrails on nRouter.

ChatCode
Input

$0.25/M

Output

$2.00/M

Google

Gemini 2.5 Pro

gemini-2.5-pro

by Googlehosted on Google Vertex AI

Gemini 2.5 Pro is Google's reasoning foundation model featuring adaptive thinking and a one million token context window, built for complex coding, STEM reasoning, and document analysis.

ChatVisionCode1.0M
Input

$1.25/M

Output

$10.00/M

N

Auto

nrouter/auto

by NRouter

nRouter's managed auto model: send the model name nrouter/auto and nRouter picks the model that serves each request. It is covered by the monthly usage allowance of the Starter, Pro and Max plans; every other model is paid from pay-as-you-go credits.

ChatCode
Input

$0.30/M

Output

$2.50/M

All models

Mistral AI

Mistral Medium 2505

mistral-medium-2505

by Mistral AIhosted on Azure Foundry

mistral-medium-2505 is a high-performance chat foundation model with automated multi-cloud failover and guardrails on nRouter.

ChatCode
Input

$0.40/M

Output

$2.00/M

Anthropic

Claude Opus 5 5

claude-opus-5-5

by Anthropic

Anthropic claude-opus-5-5 is a high-performance chat foundation model featuring a 1M context window, with automated multi-cloud failover and guardrails on nRouter.

ChatVisionCode1M
Input

$5.00/M

Output

$25.00/M

OpenAI

Gpt 5.5 2026 04 23

gpt-5.5-2026-04-23

by OpenAI

Fixed snapshot of GPT-5.5 dated April 23, 2026, providing stable reasoning outputs and 1.05 million token context limits for production pipelines.

VisionCode
Input

$5.00/M

Output

$30.00/M

DeepSeek

Deepseek V4.1 Flash

deepseek-v4.1-flash

by DeepSeekhosted on Alibaba US

deepseek-v4.1-flash is a high-performance chat foundation model with automated multi-cloud failover and guardrails on nRouter.

ChatCode
Input

$0.25/M

Output

$2.00/M

Google

Gemini 2.5 Pro

gemini-2.5-pro

by Googlehosted on Google Vertex AI

Gemini 2.5 Pro is Google's reasoning foundation model featuring adaptive thinking and a one million token context window, built for complex coding, STEM reasoning, and document analysis.

ChatVisionCode1.0M
Input

$1.25/M

Output

$10.00/M

N

Auto

nrouter/auto

by NRouter

nRouter's managed auto model: send the model name nrouter/auto and nRouter picks the model that serves each request. It is covered by the monthly usage allowance of the Starter, Pro and Max plans; every other model is paid from pay-as-you-go credits.

ChatCode
Input

$0.30/M

Output

$2.50/M

Mistral AI

Mistral Small 2503

mistral-small-2503

by Mistral AIhosted on Azure Foundry

mistral-small-2503 is a high-performance chat foundation model with automated multi-cloud failover and guardrails on nRouter.

ChatCode
Input

$0.10/M

Output

$0.30/M

Anthropic

Claude Sonnet 5 5

claude-sonnet-5-5

by Anthropic

Anthropic claude-sonnet-5-5 is a high-performance chat foundation model featuring a 1M context window, with automated multi-cloud failover and guardrails on nRouter.

ChatVisionCode1M
Input

$2.00/M

Output

$10.00/M

OpenAI

Gpt 5.5

gpt-5.5

by OpenAI

OpenAI multimodal model supporting text and image inputs with a 1.05M token context window, 128K max output tokens, and knowledge cutoff of December 2025.

VisionCode
Input

$5.00/M

Output

$30.00/M

DeepSeek

Deepseek V4 Pro

deepseek-v4-pro

by DeepSeekhosted on Alibaba US

DeepSeek-V4-Pro is a text model with a 1,048,576-token context window, 393,216 max output tokens, evaluated at 87.5 on MMLU-Pro, 90.1 on GPQA Diamond, and 80.6 on SWE-bench Verified.

ChatCode
Input

$2.40/M

Output

$4.80/M

Google

Gemini 2.5 Flash

gemini-2.5-flash

by Googlehosted on Google Vertex AI

Gemini 2.5 Flash is Google's multimodal reasoning model supporting text, image, audio, and video inputs with a one million token context window and configurable thinking budgets.

ChatVisionCode1.0M
Input

$0.30/M

Output

$2.50/M

xAI

Grok 4 1 Fast Non Reasoning

grok-4-1-fast-non-reasoning

by xAIhosted on Azure Foundry

xAI grok-4-1-fast-non-reasoning is a high-performance reasoning foundation model with automated multi-cloud failover and guardrails on nRouter.

Code
Input

$0.20/M

Output

$0.50/M

Anthropic

Claude Fable 5 1

claude-fable-5-1

by Anthropic

Anthropic claude-fable-5-1 is a high-performance chat foundation model featuring a 1M context window, with automated multi-cloud failover and guardrails on nRouter.

ChatVisionCode1M
Input

$10.00/M

Output

$50.00/M

OpenAI

Gpt 5.4 2026 03 05

gpt-5.4-2026-03-05

by OpenAI

Deterministic snapshot of GPT-5.4 from March 5, 2026, featuring a 1,050,000-token context window and 128,000 max output tokens. It processes text and image inputs with an August 2025 knowledge cutoff.

VisionCode
Input

$2.50/M

Output

$15.00/M

DeepSeek

Deepseek V4 Pro 0813

deepseek-v4-pro-0813

by DeepSeekhosted on Alibaba US

DeepSeek-V4-Pro-0813 is the production release of the DeepSeek-V4-Pro architecture, pairing 1.6T MoE parameters with a DSpark speculative decoding engine for accelerated agentic execution, full-stack software engineering, and deep logical reasoning.

ChatCode
Input

$1.60/M

Output

$6.40/M

Google

Gemini 2.5 Flash Lite

gemini-2.5-flash-lite

by Googlehosted on Google Vertex AI

Gemini 2.5 Flash-Lite is Google's lightweight multimodal model designed for high-frequency workflows, supporting input contexts up to one million tokens across text, audio, video, image, and PDF.

ChatCode1.0M
Input

$0.075/M

Output

$0.30/M

xAI

Grok 4 1 Fast Reasoning

grok-4-1-fast-reasoning

by xAIhosted on Azure Foundry

xAI grok-4-1-fast-reasoning is a high-performance reasoning foundation model with automated multi-cloud failover and guardrails on nRouter.

Code
Input

$0.20/M

Output

$0.50/M

Anthropic

Claude Opus 5

claude-opus-5

by Anthropic

Claude Opus 5 is a multimodal foundation model supporting text and image inputs with a 1,000,000-token context window and 128,000 max output tokens. It has a May 2026 knowledge cutoff for multi-stage software engineering.

ChatVisionCode1M
Input

$5.00/M

Output

$25.00/M

OpenAI

Gpt 5.4

gpt-5.4

by OpenAI

High-efficiency OpenAI reasoning model with an expanded 1.05M token context window, suited for extensive codebases, deep reasoning, and computer-use tasks.

VisionCode
Input

$2.50/M

Output

$15.00/M

DeepSeek

Deepseek V4 Flash

deepseek-v4-flash

by DeepSeekhosted on Alibaba US

DeepSeek-V4-Flash is a high-efficiency Mixture-of-Experts model with 284B total and 13B activated parameters supporting up to a 1M-token context window. Optimized for low latency, it features hybrid sparse attention and dual-mode reasoning capabilities.

ChatCode
Input

$0.20/M

Output

$0.40/M

Meta

Llama 4 Scout 17B 16E Instruct

Llama-4-Scout-17B-16E-Instruct

by Metahosted on Azure Foundry

Meta Llama-4-Scout-17B-16E-Instruct is a high-performance chat foundation model with automated multi-cloud failover and guardrails on nRouter.

ChatCode
Input

$0.20/M

Output

$0.78/M

Anthropic

Claude Fable 5

claude-fable-5

by Anthropic

Claude Fable 5 is a multimodal foundation model supporting text and image inputs with a 1,000,000-token context window and 128,000 max output tokens. It features a January 2026 knowledge cutoff for agentic workflows.

ChatVisionCode1M
Input

$10.00/M

Output

$50.00/M

OpenAI

Gpt 5.4 Mini 2026 03 17

gpt-5.4-mini-2026-03-17

by OpenAI

Specific snapshot of GPT-5.4 Mini from March 17, 2026, delivering balanced reasoning performance and 400K context capacity at reduced inference latency.

VisionCode
Input

$0.75/M

Output

$4.50/M

DeepSeek

Deepseek V4 Flash 0731

deepseek-v4-flash-0731

by DeepSeekhosted on Alibaba US

DeepSeek-V4-Flash-0731 is the production release of DeepSeek-V4-Flash, incorporating an integrated speculative decoding module. It delivers enhanced agentic performance, tool execution, and code synthesis across a 1M-token context window.

ChatCode
Input

$0.20/M

Output

$0.40/M

Showing 24 of 169 models

Browse all model detail pages (168)