Skip to content
RightNow

open models

Built for agents that replay context.

The repeated part of each call hits the cache and bills at the cached input rate.

Sort: List order

1 of 9 models

Reset
Filters
Capabilities
  • Qwen

    Qwen3.8 27B

    Available

    qwen3-8-27b

    Tool calling / JSON mode / Streaming / Image input

    Input
    USD0.10
    per million input tokens
    Cached input
    USD0.01
    per million cached input tokens
    Output
    USD0.40
    per million output tokens
    Cache hit rate
    87.5%
    cache hit rate, last 24 hours

Looking for another model? Request a model

Prices as of 2026-11-12.

Code examples

Pick a model. Copy the call.

Get API key
# Set RUNINFRA_GATEWAY_KEY to your API key before running this example.
curl -X POST "https://api.runinfra.ai/v1/chat/completions" \
  -H "Authorization: Bearer $RUNINFRA_GATEWAY_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek-v4-1-flash","messages":[{"role":"user","content":"Hello"}],"max_tokens":16384}'