Discover

271 models, one API key for all of them. Compare by price, capability and measured performance.

All models

Why use us

  • Official access, verifiable source

    Requests reach each model’s official API, and a third-party signed receipt lets you verify which model answered.

  • Usage-based billing

    You’re billed for the usage the provider reports, and 92 models cost less than official prices. Every request has an itemized receipt.

  • Multi-provider failover

    If a provider becomes unavailable, requests fail over to another; provider uptime is published.

  • One key, native protocols

    Native OpenAI, Anthropic and Gemini APIs; Claude Code and Codex connect by changing the base URL.

Leaders

OpenAI’s GPT-6 Astra is the most capable model, 0.7 points ahead of Anthropic’s Claude Opus 5.5. Capability scores from Epoch AI; usage, speed and success rate measured here over the last 7 days.

Capability vs price

Capability score vs. input price per 1M tokens, 89 models
Full rankings
  • Better value: more capable, lower price
  • Pareto frontier

Capability scores are from Epoch AI’s Epoch Capabilities Index (CC BY 4.0, as of 2026-11-02), which combines dozens of benchmarks with GPT-5 set at 150. epoch.ai/eci

Price: our current input price per 1M tokens in USD, lowest across channels. Dated snapshots and resold copies of the same model are merged into one point; free models are not shown.

Shaded area: capability above and price below the median of all models. Pareto frontier: no other model is both cheaper and more capable.

Latest model from each lab

The newest model from every lab, newest first.
ModelReleased
OhMyGPT Mockohmygpt
Oct 30
GPT-6.1 Terra-10%OpenAI
Oct 26
Kimi K3.1 ProMoonshot AI
Oct 23
DeepSeek V4.1 Flash 1017-95%DeepSeek
Oct 17
Gemini 4 Argon-10%Google
Oct 13

Cheapest LLM APIs

Paid models by price per 1M tokens, lowest first.
ModelInput
GLM-5.3-Flash-95%Z.ai
$0.0075
DeepSeek V4.1 Flash 1017-95%DeepSeek
$0.015
GLM-4.6V-FlashXZ.ai
$0.024092
Doubao Seed 2.0 Mini (260215)ByteDance
$0.0292
Nova Microamazon
$0.0385

Longest context window models

Largest context window first.
ModelContext
Grok 4.20 (0309, Non-Reasoning)xAI
2M
Grok 4.20 (0309, Reasoning)xAI
2M
Grok 4.20 Multi-Agent (0309)xAI
2M
GPT-6.1 Terra-10%OpenAI
1.1M
GPT-6.1 Sol-10%OpenAI
1.1M

Models served by the most providers

More providers means a request can fail over to another one.
ModelProviders
Claude Sonnet 4.6Anthropic
8
Claude Opus 4.7Anthropic
7
Claude Opus 4.6Anthropic
7
GPT OSS 120BOpenAI
5
DeepSeek V4.1 Flash 1017-95%DeepSeek
4

Free LLM models

No charge.
ModelPrice
OhMyGPT Mockohmygpt
Free
GLM-4.6V-FlashZ.ai
Free
GLM-4.7-FlashZ.ai
Free

Image

Newest first.
ModelReleased
GPT Image 2.5 Flare-10%OpenAI
Sep 8
GPT Image 2.5 Sunburst-10%OpenAI
Sep 8
GPT Image 2-10%OpenAI
Apr 21
GPT Image 1.5-10%OpenAI
Dec 16
GPT Image 1 Mini-10%OpenAI
Oct 7

Video

Newest first.
ModelReleased
Sora 2-10%OpenAI
Mar 25
Sora 2 Pro-10%OpenAI
Mar 25

Audio

Newest first.
ModelReleased
GPT-4o Mini TTS-10%OpenAI
Mar 20
GPT-4o Mini Transcribe-10%OpenAI
Mar 14
GPT-4o Transcribe-10%OpenAI
Mar 14
Azure TTS-1Microsoft
Feb 17
Whisper-8%OpenAI
Feb 17

Embeddings

Newest first.
ModelReleased
Rerank v4.0 Fastcohere
Jun 1
Rerank v4.0 Procohere
Jun 1
Embed v4.0cohere
Apr 1
Rerank English v3.0cohere
Apr 1
Rerank Multilingual v3.0cohere
Apr 1

Tools

Newest first.
ModelReleased
Jevtypesafe
Sep 15
Mistral OCRmistral
Mar 1
Omni Moderation (2024-09-26)OpenAI
—
Omni Moderation LatestOpenAI
—
Text Moderation 007OpenAI
—