Llama 4 MaverickChat
Meta's 128-expert multimodal Llama 4 model with a full 1M-token context and a conformant tool-use rail.
1.3sp50100%up3 rails1M ctx$0.003typical$0.40 → $1.04 /MTok
Playground
Providers
| Provider | Context | Price · in / out | p50 | p95 | Uptime |
|---|---|---|---|---|---|
| ddeepinfraNo trainingNo training on your data | 131K | $0.25 / $0.47/MTok | 1.8s | 2.5s | 100% |
Routing controls
routing.strategyproviders.onlyproviders.excludeproviders.ordermax_cost_usddata_policydocs →Performance
Collecting — charts appear after two days.
Pricing
- Typical
- $0.002/req
- Input
- $0.25/M tok
- Cached input
- $0.16/M tok
- Output
- $0.47/M tok
API
POST/api/v1/chat/completionsOpenAI-compatible
llama-3.3-70b
curl https://www.ninjachat.ai/api/v1/chat/completions \
-H "Authorization: Bearer $NINJACHAT_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "llama-3.3-70b",
"messages": [{ "role": "user", "content": "Hello!" }],
"stream": true
}'messagestemperaturemax_completion_tokenstop_pstopfrequency_penaltypresence_penaltyseedstreamuserroutingtoolstool_choice
FAQ
What is Llama 3.3 70B Instruct Turbo?
Meta's popular multilingual 70B instruct model on DeepInfra's accelerated low-cost Turbo endpoint.
How much does Llama 3.3 70B Instruct Turbo cost?
Llama 3.3 70B Instruct Turbo costs $0.25/M input tokens and $0.47/M output tokens.
What inputs and outputs does Llama 3.3 70B Instruct Turbo support?
Llama 3.3 70B Instruct Turbo accepts text and returns text.
How do I call Llama 3.3 70B Instruct Turbo?
POST /api/v1/chat/completions with `"model": "llama-3.3-70b"`.
What other Llama models are on NinjaChat?
Llama 4 Maverick, Llama 4 Scout.
