← All modelsReka

Reka Flash 3

21B reasoning LLM — chat, coding, instruction-following — 64K context.

Reka$0.10 in · $0.20 out / 1M tokens (≤64K ctx)llmrekaopen-weights
Capabilities
llmrekaopen-weights
Pricing
Context bandMax tokensInput / M tokOutput / M tok
≤64K65,536$0.10$0.20
API

Wire it up.

EndpointPOST https://api.tryinfer.com/v1/chat/completions
request
curl https://api.tryinfer.com/v1/chat/completions \
-H "Authorization: Bearer $INFER_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "reka-flash-3",
"messages": [{ "role": "user", "content": "Hello!" }]
}'

OpenAI-compatible — point your SDK at Infer with a bearer token. Get an API key →