Skip to content
OhMyGPT

Search

Search pages and models…

Use 291 AI models with one API key

Native OpenAI, Anthropic and Gemini APIs. Point Claude Code or Codex at a new base URL and go. With TEE proof on, you can check which provider handled your requests.

All models

New releases

The latest models to go live, newest first.

View all

  • GPT Image 2.6 Flare

    Image output
    $27.00list $30.00-10%per 1M tokens
    Context
    128K
    Max output
    —
    Capability
    —
    AcceptsTextImageReturnsImageImage generation

    OpenAI's fast image model for interactive generation and editing, with animated GIF and SVG output.

  • GPT Image 2.6 Sunburst

    Image output
    $27.00list $30.00-10%per 1M tokens
    Context
    128K
    Max output
    —
    Capability
    —
    AcceptsTextImageReturnsImageImage generation

    OpenAI's image model for detailed compositions that stay consistent across edits, with animated GIF and SVG output.

  • GPT Live Transcribe

    Transcription
    $0.000256list $0.000284-10%per second
    Context
    128K
    Max output
    —
    Capability
    —
    AcceptsAudioSpeech to text

    Live transcription model for streaming audio, with multiple language hints.

  • GPT Realtime Whisper

    Transcription
    $0.000256list $0.000284-10%per second
    Context
    128K
    Max output
    —
    Capability
    —
    AcceptsAudioSpeech to text

    Streaming speech-to-text model for live audio, delivering transcripts as the speaker talks.

Strongest from each lab

Each lab’s highest-scoring model on Epoch AI’s ECI, strongest first.

View all

  • GPT-6 Astra

    Ranked 1 by capability
    -10%
    Input
    from $9.00list $10.00
    Output
    from $45.00list $50.00
    Context
    1.1M
    Max output
    128K
    Capability
    169
    AcceptsTextImage

    OpenAI's most capable model, built for the hardest end-to-end work: complex reasoning, coding, computer use, research, and document creation.

  • Claude Opus 5.5

    Ranked 3 by capability
    Input
    from $4.40
    Output
    from $22.00
    Context
    1M
    Max output
    128K
    Capability
    168
    AcceptsTextImagePDF

    Anthropic's Claude Opus 5.5 for long-running agentic coding and knowledge work, priced below Opus 5 with adaptive thinking always on.

  • Gemini 4 Argon

    Ranked 6 by capability
    -10%
    Input
    $1.80list $2.00
    Output
    $9.00list $10.00
    Context
    1M
    Max output
    66K
    Capability
    166
    AcceptsTextImageAudioVideoPDF

    Google's flagship reasoning model for complex software engineering, deep mathematical and scientific problem solving, autonomous multi-step agents, and long decode up to 1M tokens.

  • DeepSeek V4.1 Flash 1017

    Ranked 17 by capability
    -55%
    Input
    from $0.0657list $0.146
    Output
    from $0.2628list $0.584
    Context
    1M
    Max output
    384K
    Capability
    159
    AcceptsTextImage

    DeepSeek V4.1 Flash 1017: natively multimodal vision understanding, with stronger coding and agentic performance than the 0910 release, 1M context and 384K max output.

Cheapest LLM APIs

Paid models by price per 1M tokens, lowest first.

View all
ModelInput
GLM-4.6V-FlashXZ.ai
$0.024092
Doubao Seed 2.0 Mini (260428)ByteDance
$0.0292
Command R7B (12-2024)cohere
$0.041252
Tencent Hy-MT2-LiteTencent
$0.0438
Voxtral Mini 3B 2507mistral
$0.044

Cheaper than official prices

97 models cost less here than at the official API. Popular ones below, priced per million tokens, blended 3 input : 1 output.

Why OhMyGPT

TEE proof of which provider answered
Turn on TEE confidential computing proof for a key, and responses that pass through VeriRelay carry a signed receipt with the provider host (such as api.anthropic.com) and what it sent back. You can check the receipt on VeriRelay. The signing key exists only inside an AMD SEV-SNP confidential VM. Learn more
Automatic failover
Each model has several providers. If one errors or is rate limited, the request moves to the next before any output starts. Provider uptime is public. Learn more
Billed on actual usage
You pay for the usage the provider reports, with cache priced separately. Failed requests are free, and every request has an itemized receipt. Learn more
Native APIs, no code changes
Native OpenAI Chat Completions and Responses, Anthropic Messages and Gemini APIs. Claude Code and Codex connect by changing the base URL. Learn more
Your providers, your order
Pick which providers to use per request, set their order, or exclude one. Without a choice, OhMyGPT picks for you and fails over to the next. Learn more
Payment and invoices
Pay with Alipay, cards and more. Invoices are available.

Latest announcements

All announcements

Quick start

Point your OpenAI, Anthropic or Gemini SDK at this base URL and add your API key.
Docs
Base URL
https://api.ohmygpt.com/v1
Try it
curl https://api.ohmygpt.com/v1/chat/completions \
  -H "Authorization: Bearer sk-…" \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-oss-120b", "messages": [{"role": "user", "content": "Hello"}]}'