OpenAI's flagship model — excellent across all task types.
| Provider | Role | Context | Price · in / out | p50 | p95 | Uptime |
|---|---|---|---|---|---|---|
| ggroqNo trainingNo training on your data. Zero-retention available | Primary | 131K | $0.22 / $0.45/MToksame price, any rail | 193ms | 320ms | 100% |
Collecting — charts appear after two days.
curl https://www.ninjachat.ai/api/v1/chat/completions \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "gpt-oss-20b",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'OpenAI's compact open-weight reasoning model on three independently operated inference rails.
GPT-OSS 20B costs $0.22/M input tokens and $0.45/M output tokens.
GPT-OSS 20B accepts text and returns text.
POST /api/v1/chat/completions with `"model": "gpt-oss-20b"`.
GPT-5, GPT-5 Mini, GPT-5.4, GPT-5.4 Pro, GPT-5.6 Luna, GPT-5.6 Sol, GPT-5.6 Terra, GPT-OSS 120B, O3 Mini.
| 131K |
| — |
| — |
| — |
| ddeepinfraNo trainingNo training on your data | Emergency | 131K | — | — | — |
routing.strategyproviders.onlyproviders.excludeproviders.ordermax_cost_usddata_policydocs →OpenAI's latest flagship — the most capable GPT for hard reasoning and code.
OpenAI's highest-effort GPT-5.4 variant for the most demanding tasks.
OpenAI's high-volume GPT-5.6 model with 1.05M context and full tool support.