Reka: Flash 3
reka-flash-3
Flash 3 costs $0.137 per million input tokens and $0.273 per million output tokens, supports 66K context, and is available through the OpenAI-compatible API.
21B reasoning model for chat and coding, served directly .
Modalities
Text → Text
Input / output price
$0.137 / $0.273 per 1M
Context
66K · max output 66K
Capabilities
Pricing
Billed per token actually used and deducted from your credits.
| Item | USD per 1M tokens |
|---|---|
| Input | $0.137 |
| Output | $0.273 |
| Cached input | $0.0341 |
Calculator
Drag the sliders to estimate what this model will cost.
- Per request
- $0.00063
- Per day
- $0.3140
- Per month (30 days)
- $9.42
Flash 3: input $0.1365/M · output $0.273/M · cached input $0.0341/M
curl https://api.geniusrelaygpt.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{"model": "reka-flash-3", "max_tokens": 800,
"messages": [{"role": "user", "content": "…"}]}'Code samples
OpenAI-compatible. Set the base URL to https://api.geniusrelaygpt.com/v1 and the model to reka-flash-3.
curl https://api.geniusrelaygpt.com/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "reka-flash-3",
"stream": true,
"messages": [{"role": "user", "content": "Hello"}]
}'Use it in a client: Cursor · Cline · SillyTavern · Codex
Parameters
Common OpenAI parameters can be passed as-is.
temperaturetop_pmax_tokensstreamstoppresence_penaltyfrequency_penaltyseedRelated models
More from Reka
Similar capabilities and price
FAQ
- How is Flash 3 billed?
- Input is $0.137 and output is $0.273 per million tokens; cached input is $0.0341. The charge for every request is listed in Usage Logs in the console.
- How long is the context window?
- 66K tokens. In a long conversation every turn is billed for the full input, so keep the history under control.
- Does it support streaming?
- Yes. Add "stream": true to the request to receive server-sent events in the OpenAI format.