OpenAI GPT API quickstart
Model IDs and access
Use an exact ID returned by your key. The public catalog does not guarantee live capacity or every optional capability.
openai/gpt-5openai/gpt-5-miniopenai/gpt-5-nanoopenai/gpt-5.1openai/gpt-5.4openai/gpt-5.4-miniopenai/gpt-5.4-nanoopenai/gpt-5.4-proopenai/gpt-5.5openai/gpt-5.6openai/gpt-5.6-solopenai/gpt-5.6-terraopenai/gpt-5.6-lunaopenai/gpt-6-astraopenai/gpt-6-solopenai/gpt-6-lunaopenai/gpt-6.1-solopenai/gpt-6.1-terraopenai/gpt-6.2-astraopenai/gpt-6.2-sol
Unprefixed compatibility IDs remain accepted; prefer the namespaced IDs returned by discovery.
export QUOTAFLOW_API_KEY="YOUR_QUOTAFLOW_API_KEY"
curl https://api.quotaflow.ai/openai/v1/models \
-H "Authorization: Bearer $QUOTAFLOW_API_KEY"
First request
OpenAI SDK base URL: https://api.quotaflow.ai/openai/v1. Keep your key on your server.
curl https://api.quotaflow.ai/openai/v1/responses \
-H "Authorization: Bearer $QUOTAFLOW_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "openai/gpt-6.2-sol",
"input": "Design an order-management API and explain its main endpoints.",
"max_output_tokens": 4096,
"stream": false
}'
Read output message items and their output_text content, or use response.output_text in the OpenAI SDK. Do not assume output[0] is text.
Compatibility and output budgets
Use /responses for new coding/agent integrations and combinations of reasoning with tools. GPT-6.2 Sol and Astra are separate model identities, not aliases of GPT-6.1. Chat tool/effort combinations vary by model; do not copy a reasoning_effort: "none" workaround to a model that does not accept it. The public HTTP API does not provide previous_response_id continuation or background execution. See the Responses reference and model-specific compatibility notes.
Use the output cap for the endpoint you call; these fields are not interchangeable. If an answer ends at its output limit, inspect its status/stop reason before increasing the budget within the model limit. For streaming, consume the endpoint-specific events until completion; do not assume a first chunk is the final answer.
401 indicates an authentication problem; check key access on 403. Correct invalid request fields on 400 instead of retrying unchanged. Use bounded backoff for temporary 429/503 capacity failures. Check model access with the same key and base URL; no guide guarantees live supply or a universal price.
See Responses API, Chat Completions and billing.