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

9 models

Filters
Capabilities

  • RightNow decision model

    Available

    Decisions

    Priced per decision

  • Step 5 Preview

    Available

    step-5-preview

    Trending

    Tool calling / JSON mode / Streaming / Image input

    Input
    USD0.90
    per million input tokens
    Cached input
    USD0.09
    per million cached input tokens
    Output
    USD2.43
    per million output tokens
    Cache hit rate
    cache hit rate, not yet published
  • DeepSeek

    DeepSeek V4.1 Flash 1017

    Available

    deepseek-v4-1-flash-1017

    Trending

    Tool calling / JSON mode / Streaming / Image input

    Input
    USD0.15
    per million input tokens
    Cached input
    USD0.01
    per million cached input tokens
    Output
    USD0.60
    per million output tokens
    Cache hit rate
    99.4%
    cache hit rate, last 24 hours

  • GLM 5.3

    Available

    glm-5-3

    Trending

    Tool calling / JSON mode / Streaming

    Input
    USD1.30
    per million input tokens
    Cached input
    USD0.13
    per million cached input tokens
    Output
    USD4.20
    per million output tokens
    Cache hit rate
    97.0%
    cache hit rate, last 24 hours

  • GLM 5.3 Flash

    Available

    glm-5-3-flash

    Trending

    Tool calling / JSON mode / Streaming / Image input

    Input
    USD0.11
    per million input tokens
    Cached input
    USD0.03
    per million cached input tokens
    Output
    USD0.45
    per million output tokens
    Cache hit rate
    99.4%
    cache hit rate, last 24 hours
  • NVIDIA

    Nemotron 3.5 Lightning 30B

    Available

    nemotron-3-5-lightning-30b

    Tool calling / JSON mode / Streaming

    Input
    USD0.05
    per million input tokens
    Cached input
    USD0.01
    per million cached input tokens
    Output
    USD0.15
    per million output tokens
    Cache hit rate
    cache hit rate, not yet published
  • 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
    88.1%
    cache hit rate, last 24 hours
  • Ornith

    Ornith 1.5 35B

    Available

    ornith-1-5-35b

    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
    96.3%
    cache hit rate, last 24 hours
  • DeepSeek

    DeepSeek V4.1 Flash

    Available

    deepseek-v4-1-flash

    Tool calling / JSON mode / Streaming

    Input
    USD0.14
    per million input tokens
    Cached input
    USD0.03
    per million cached input tokens
    Output
    USD0.58
    per million output tokens
    Cache hit rate
    97.8%
    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":"step-5-preview","messages":[{"role":"user","content":"Hello"}],"max_tokens":16384}'