Skip to content

Mistral Nemo

text → textHugging Face OpenRouter Cost calculator →

Best price · blended / 1M

$0.0178

at Io Net

Input / output
$0.0166 / $0.0216
Providers
5
Spread
7.7×
7 days
0%
30 days
0%
Context
128K
Prices per 1M tokens, blended: Io Net $0.0178, DekaLLM $0.021, DeepInfra (fp8/flex) $0.0234, DeepInfra $0.0293, Parasail $0.03, Mistral (eu) $0.15.

Providers

  • Io NetCheapest
    $0.0178
    $0.0166 in · $0.0216 out
    −8.2% vs ref
    125K ctx100% uptimefp16·−28% discount
  • $0.021
    $0.018 in · $0.03 out
    +8.2% vs ref
    128K ctx89.9% uptimefp8
  • fp8/flex
    $0.0234
    $0.0232 in · $0.024 out
    +21% vs ref
    128K ctx98.1% uptimefp8
  • $0.0293
    $0.029 in · $0.03 out
    +51% vs ref
    128K ctx100% uptimefp8
  • $0.03
    $0.03 in · $0.03 out
    +55% vs ref
    128K ctx84.0% uptimefp8
  • $0.15
    $0.15 in · $0.15 out
    +673% vs ref
    128K ctx100% uptime
Blended = (3 × input + output) / 4. Ref $0.0194 = median of cheapest 20%.

Price history

USD per 1M tokens · each step is a price change

Prices in USD / 1M tokens.

Other pricing

Offered byCache read
Io Net$0.0108
Mistral (eu)$0.015

Changes

  • Discount price,
    33%→28%−15.2%
  • Cache read price,
    $0.0101→$0.0108+7.5%
  • Output price,
    $0.0201→$0.0216+7.5%
  • Input price,
    $0.0154→$0.0166+7.5%
  • Discount price,
    28%→33%+17.9%
  • Cache read price,
    $0.0108→$0.0101−6.9%
  • Output price,
    $0.0216→$0.0201−6.9%
  • Input price,
    $0.0166→$0.0154−6.9%
  • Now served,
    Listed
  • Discount price,
    20%→28%+40.0%
  • Cache read price,
    $0.012→$0.0108−10.0%
  • Output price,
    $0.024→$0.0216−10.0%
  • Input price,
    $0.0184→$0.0166−10.0%
  • Discount price,
    10%→20%+100%
  • Cache read price,
    $0.0135→$0.012−11.1%

About

The cheapest provider for Mistral Nemo is Io Net at $0.0178 per 1M tokens (blended), charging $0.0166 per 1M input and $0.0216 per 1M output tokens. 5 providers serve it; the most expensive charges 7.7× the typical price. Context window: 128K tokens. Prices tracked since Oct 3, 2026.

A 12B parameter model with a 128k token context length built by Mistral in collaboration with NVIDIA. The model is multilingual, supporting English, French, German, Spanish, Italian, Portuguese, Chinese, Japanese,...
Released
Jul 19, 2024
First tracked
Oct 3, 2026
Canonical slug
mistralai/mistral-nemo
Weights
mistralai/Mistral-Nemo-Instruct-2407