Chat API
Every chat model in the catalogue, on one OpenAI-compatible endpoint. One OpenAI-compatible endpoint, one API key, per-token pricing, and at least 30% below the provider's list price.
Every chat model in the catalogue, on one OpenAI-compatible endpoint.
The endpoint
POST https://api.aetherapi.dev/v1/chat/completionsWhat this gives you
- One endpoint for chat, with the OpenAI request and response format unchanged
- Per-token pricing, billed against prepaid credits that never expire
- Spend limits per key, so one runaway loop cannot spend the whole balance
Models for this endpoint
| Model | Context | Price |
|---|---|---|
| Claude Fable 5 | 1M | $7/M input | $35/M output |
| Claude Haiku 5.5 | 1M | $0.07/M input | $0.35/M output |
| Claude Haiku 4.5 20251001 | 200K | $0.7/M input | $3.5/M output |
| Claude Opus 4.1 20250805 | 200K | $10.5/M input | $52.5/M output |
| Claude Opus 4.5 20251101 | 200K | $3.5/M input | $17.5/M output |
| Claude Opus 4.6 | 1M | $3.5/M input | $17.5/M output |
| Claude Opus 4.7 | 1M | $3.5/M input | $17.5/M output |
| Claude Opus 4.8 | 1M | $3.5/M input | $17.5/M output |
| Claude Opus 5 | 1M | $3.5/M input | $17.5/M output |
| Claude Sonnet 4.5 | 200K | $2.1/M input | $10.5/M output |
| Claude Sonnet 4.6 | 200K | $2.1/M input | $10.5/M output |
| Claude Sonnet 5 | 1M | $1.4/M input | $7/M output |
| Deepseek V4.1 Flash Latest | 1M | $0.084/M input | $0.336/M output |
| Deepseek V4 Pro Latest | 1M | $0.304/M input | $0.6/M output |
| Gemini 2.5 Flash | 1M | $0.4375/M input | $1.75/M output |
| Gemini 2.5 Flash Image | — | $0.2/M input | $1.75/M output |
| Gemini 2.5 Flash Lite | 1M | $0.0525/M input | $0.21/M output |
| Gemini 2.5 Pro | 1M | $0.875/M input | $7/M output |
| Gemini 3 Flash Preview | 1M | $0.35/M input | $2.1/M output |
| Gemini 3 Pro Image | 131K | $1.4/M input | $8.4/M output |
| Gemini 3.1 Flash Image | 1M | $0.35/M input | $2.1/M output |
| Gemini 3.1 Flash Lite | 1M | $0.17/M input | $1/M output |
| Gemini 3.1 Flash Lite Image | 1M | $0.17/M input | $1/M output |
| Gemini 3.1 Pro Preview | 1M | $1.4/M input | $8.4/M output |
| Gemini 3.5 Flash | 1M | $1/M input | $6.3/M output |
| Gemini 3.5 Flash Lite | 1M | $0.21/M input | $1.75/M output |
| Gemini 3.6 Flash | 1M | $1/M input | $5.25/M output |
| Gemini 3.7 Flash | 1M | $0.2625/M input | $1.3125/M output |
| Gemma 4 26b A4b It | 131K | $0.1/M input | $0.28/M output |
| Gemma 4 26b A4b It Free | 131K | Free |
| Gemma 4 31b It | 131K | $0.1/M input | $0.28/M output |
| Gemma 4 31b It Free | 131K | Free |
| GLM 5.2 | 1M | $1.1/M input | $3.5/M output |
| GLM 5.3 | 1M | $0.1/M input | $2.45/M output |
| GPT 4.1 | 1M | $1.4/M input | $5.6/M output |
| GPT 4.1 Mini | 1M | $0.28/M input | $1.12/M output |
| GPT 4o | 131K | $1.75/M input | $7/M output |
| GPT 4o Mini | 131K | $0.105/M input | $0.42/M output |
| GPT 5 | 400K | $0.875/M input | $7/M output |
| GPT 5 Mini | 400K | $0.175/M input | $1.4/M output |
| GPT 5 Nano | 400K | $0.035/M input | $0.28/M output |
| GPT 5.1 | 400K | $0.875/M input | $7/M output |
| GPT 5.2 | 400K | $1.225/M input | $9.8/M output |
| GPT 5.3 Codex | 400K | $1.2/M input | $9.8/M output |
| GPT 5.4 | 1M | $1.7/M input | $10/M output |
| GPT 5.4 Mini | 400K | $0.5/M input | $3/M output |
| GPT 5.4 Nano | 400K | $0.14/M input | $0.84/M output |
| GPT 5.5 | 1M | $3.5/M input | $21/M output |
| GPT 5.6 Luna | 1M | $0.28/M input | $1.25/M output |
| GPT 5.6 Sol | 1M | $3.5/M input | $21/M output |
| GPT 5.6 Terra | 1M | $1.4/M input | $10.5/M output |
| GPT Oss 120b | 131K | $0.084/M input | $0.42/M output |
| GPT Oss 120b Free | 131K | Free |
| GPT Oss 20b | 131K | $0.028/M input | $0.098/M output |
| GPT Oss 20b Free | 131K | Free |
| Grok 4.6 | 500K | $1.4/M input | $4.2/M output |
| Kimi K2.6 | 262K | $0.42/M input | $1.96/M output |
| Kimi K2.7 Code | 262K | $0.42/M input | $1.96/M output |
| Kimi K3 | 1M | $2.1/M input | $10.5/M output |
| Mimo V2.5 | 1M | $0.28/M input | $1.4/M output |
| Mimo V2.5 Pro | 1M | $0.7/M input | $2.1/M output |
| Minimax M2.7 | 205K | $0.21/M input | $0.84/M output |
| Minimax M3 | 1M | $0.42/M input | $0.84/M output |
| Mistral Large Latest | 262K | $1.4/M input | $4.2/M output |
| Mistral Medium Latest | 131K | $0.28/M input | $1.4/M output |
| Mistral Small Latest | 131K | $0.07/M input | $0.21/M output |
| O3 | 200K | $7/M input | $21/M output |
| Qwen3.8 35b A3b Free | 41K | Free |
| Qwen3 Max | 262K | $0.7/M input | $4.2/M output |
| Qwen3.5 397b A17b | 262K | $0.28/M input | $1.68/M output |
| Qwen3.6 35b A3b | 262K | $0.098/M input | $0.7/M output |
| Qwen3.6 Max | 262K | $0.7189/M input | $4.3134/M output |
| Qwen3.6 Plus | 262K | $0.5/M input | $2.1/M output |
| Qwen3.7 Max | 1M | $1.75/M input | $5.25/M output |
| Qwen3.7 Plus | 1M | $0.224/M input | $0.896/M output |
| Qwen3.8.2.4t A95b | 1M | $1.4/M input | $4.2/M output |
| Qwen3.8 27b | 1M | $0.315/M input | $2.24/M output |
| Qwen3.8 Max | 1M | $1.75/M input | $5.25/M output |
| Qwen3.6 27b Free | 262K | Free |
| Qwen3.8 27b Free | 1M | Free |
| Qwen3.6 35b A3b Free | 262K | Free |
| Minimax M3 Free | 1M | Free |
| Step 3.7 Flash Free | 262K | Free |
| GLM 5.3 Flash | 1M | $0.105/M input | $0.35/M output |
| Claude Fable 5.1 | 1M | $7/M input | $35/M output |
| Claude Opus 5.5 | 1M | $2.8/M input | $14/M output |
| Claude Sonnet 5.5 | 1M | $1.4/M input | $7/M output |
| Deepseek V4.1 Flash | 1M | $0.024696/M input | $0.3528/M output |
| Gemini 3.8 Flash | 1M | $0.525/M input | $2.625/M output |
| GLM 5.3 Flashx | 1M | $0.259/M input | $0.875/M output |
| GPT 6 Luna | 1M | $0.07/M input | $0.35/M output |
| GPT 6 Sol | 1M | $1.4/M input | $7/M output |
| Grok 4.7 | 500K | $1.4/M input | $4.2/M output |
| Mimo V2.6 Flash | 1M | $0.098/M input | $0.196/M output |
| Mimo V2.6 Pro | 1M | $0.3045/M input | $0.609/M output |
| Qwen3.8 Flash | 1M | $0.105/M input | $0.329/M output |
| Qwen3.8 Max 0902 | 1M | $1.4/M input | $4.2/M output |
| GPT 6 Astra | 1M | $7/M input | $35/M output |
| GPT 6.1 Sol | 1M | $1.4/M input | $7/M output |
Related
See every model on the models page, the credit packages, and the quickstart. Other kinds of work: Image Generation API · Embeddings API · Text to Speech and Transcription API · Video Generation API
Aether API — OpenAI-compatible access to 13+ providers through one API key.