Models

All models

Every model ModelRelay serves, grouped by what it does. Nothing here is ranked: text, speech-to-text and text-to-speech metrics share no units.

ModelPrice
Abliterated Large Flash
Abliterated
ZDR
$1.00 in · $2.00 out per 1M tokens
Abliterated Large v2
Abliterated
ZDR
$3.00 in · $5.00 out per 1M tokens
Abliterated Model
Abliterated
ZDR
$1.00 in · $3.00 out per 1M tokens
Claude Fable 5.1
Retained
$10.00 in · $50.00 out per 1M tokens
Claude Opus 5.5
Retained
$4.00 in · $20.00 out per 1M tokens
Claude Sonnet 5.5
Retained
$2.00 in · $10.00 out per 1M tokens
DeepSeek V4.1 Flash
ZDR available
$0.30 in · $1.20 out per 1M tokens
DeepSeek V4.1 Flash 1017
ZDR
$0.30 in · $1.20 out per 1M tokens
GLM 5.3
ZDR available
$0.19 in · $4.40 out per 1M tokens
GLM 5.3 Flash
ZDR available
$0.15 in · $0.50 out per 1M tokens
GPT-6 Astra
Retained
$10.00 in · $50.00 out per 1M tokens
GPT-6 Luna
Retained
$0.10 in · $0.50 out per 1M tokens
GPT-6.1 Sol
Retained
$2.00 in · $10.00 out per 1M tokens
Gemini 3.8 Flash
Retained
$0.75 in · $3.75 out per 1M tokens
Gemini 4 Argon
Retained
$2.00 in · $10.00 out per 1M tokens
Grok 4.7
ZDR
$2.00 in · $6.00 out per 1M tokens
Kimi K3
ZDR
$3.00 in · $15.00 out per 1M tokens
Mercury 3
Retained Trains on prompts
$0.10 in · $0.35 out per 1M tokens
MiniMax M3.1 Flash
ZDR
$0.15 in · $0.60 out per 1M tokens
Muse Spark 1.3
Retention unknown
$1.25 in · $4.25 out per 1M tokens
Muse Spark 1.3 Contributor
Retention unknown Trains on prompts
$0.10 in · $0.20 out per 1M tokens
Muse Spark Open
ZDR
$1.25 in · $4.25 out per 1M tokens
Muse Wonder
Retention unknown
$4.00 in · $20.00 out per 1M tokens
Qwen 3.8 Max
ZDR
$2.00 in · $6.00 out per 1M tokens
Qwen3.8 27B
ZDR available
$0.225 in · $1.98 out per 1M tokens
ModelPrice
Grok Voice Transcribe 2.0
ZDR
$0.10/audio-hour billed per ms of input audio
Whisper Large v3 Turbo
ZDR
$0.04/audio-hour billed per ms of input audio, minimum 10 s per request
ModelPrice
Gemini 3.8 Flash TTS
Retained
$9.00/1M audio tokens + $0.50/1M text tokens in, $0.00225 per 10 s of audio
Gemini 3.8 Flash-Lite TTS
Retained
$6.00/1M audio tokens + $0.50/1M text tokens in, $0.0015 per 10 s of audio

Decision models

ModelPrice
Jev 1.13
Retained
$0.042 in · free out per 1M tokens · served on /v1/decisions
Jev 1.14 (preview)
Retained
$0.042 in · free out per 1M tokens · served on /v1/decisions

Extraction models

ModelPrice
Clairic
ZDR
$0.10 in · free out per 1M tokens · served on /v1/extractions
One integration

One API, with drop-in compatibility.

Use ModelRelay's Responses API directly, or point an existing OpenAI or Anthropic SDK at the compatible endpoints.

Call a model
ModelRelay · POST /api/v1/responses Drop-in · OpenAI /v1/responses · Anthropic /v1/messages
curl https://api.modelrelay.ai/api/v1/responses \
-H "Authorization: Bearer $MODELRELAY_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"claude-sonnet-5-5","input":"Hello"}'

Change the model. Keep everything else.

Build across models without rebuilding your stack.

Open to everyone. Sign in with GitHub or Google to get started.

Get started