Sign in

Models and endpoints

Set model to the id in the table below. Ids are lowercase letters, digits and dashes, with no dots.

Model ids

Model idModelEndpoint
deepseek-flashDeepSeek V4.1 Flash/v1/chat/completions
gpt-6-astraGPT-6 Astra/v1/chat/completions
gpt-6-1-solGPT-6.1 Sol/v1/chat/completions
gpt-6-1-terraGPT-6.1 Terra/v1/chat/completions
gpt-6-lunaGPT-6 Luna/v1/chat/completions
kimi-k3-1-proKimi K3.1 Pro/v1/chat/completions
kimi-k3-1-pro-highspeedKimi K3.1 Pro Highspeed/v1/chat/completions
gpt-image-2-5-sunburstGPT Image 2.5 Sunburst/v1/images/generations
gpt-image-2-5-flareGPT Image 2.5 Flare/v1/images/generations
gpt-4o-mini-ttsGPT-4o Mini TTS/v1/audio/speech
fish-s2-1-proFish S2.1 Pro/v1/audio/speech
fish-s2-1-pro-freeFish S2.1 Pro Free/v1/audio/speech
gpt-4o-mini-transcribeTranscription Fast/v1/audio/transcriptions
gpt-4o-transcribeTranscription Accurate/v1/audio/transcriptions
fish-transcribe-1-proFish Transcribe 1 Pro/v1/audio/transcriptions
text-embedding-3-smallText Embeddings/v1/embeddings

An id that isn’t on your key returns HTTP 404 with the code not_found_runtime_route.

List the models your key can call

GET /v1/models returns only the models your key can call. Each entry has the id to send and its supported_endpoints.

curl

curl https://api.airuntime.dev/v1/models \
  -H "Authorization: Bearer $TOKENS_PAY_KEY"

Endpoints

EndpointFor
/v1/chat/completionsDeepSeek V4.1 Flash, GPT-6 Astra, GPT-6.1 Sol, GPT-6.1 Terra, GPT-6 Luna, Kimi K3.1 Pro, Kimi K3.1 Pro Highspeed
/v1/images/generationsGPT Image 2.5 Sunburst, GPT Image 2.5 Flare
/v1/audio/speechGPT-4o Mini TTS, Fish S2.1 Pro, Fish S2.1 Pro Free
/v1/audio/transcriptionsTranscription Fast, Transcription Accurate, Fish Transcribe 1 Pro
/v1/embeddingsText Embeddings

Each model page has a ready-to-run request for its endpoint in curl, Python and Node. Request bodies are limited to 2 MiB.

Get a key, then make your first call.

From $5, plus a 5% top-up fee (minimum $0.79). No subscription; paid credit never expires.

Add credit