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.
| Model | Price |
|---|---|
| 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 |
| Model | Price |
|---|---|
| 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 |
| Model | Price |
|---|---|
| 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 |
| Model | Price |
|---|---|
| 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 |
| Model | Price |
|---|---|
| Clairic ZDR | $0.10 in · free out per 1M tokens · served on /v1/extractions |
Use ModelRelay's Responses API directly, or point an existing OpenAI or Anthropic SDK at the compatible endpoints.
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.
Open to everyone. Sign in with GitHub or Google to get started.