impulse

Mistral Small 3.2 24B Instruct 2506

Open weights

Mistral-Small-3.2-24B-Instruct-2506 is an updated 24B parameter model from Mistral optimized for instruction following, repetition reduction, and improved function calling.

API id Mistral-Small-3.2-24B-Instruct-2506Released 20 Jun 2025 (Jun 2025)
Input / 1M
$0.075
at DeepInfra
Output / 1M
$0.20
at DeepInfra
Context window
128K
tokens
Max output
128K
tokens per reply
Hosts
3
3 listings
Released
Jun 2025
20 Jun 2025

Pricing

List prices at DeepInfra, in US dollars per million tokens.

TierInput / 1MOutput / 1M
Standard$0.075$0.20

What it costs a month

At DeepInfra list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$37.50
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$43.20
  • Coding agent1,000 requests a day, 40K in / 2K out$102
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$228
Use your own numbers

Where to run it

3 hosts serve Mistral Small 3.2 24B Instruct 2506. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
DeepInfraInference
Mistral-Small-3.2-24B-Instruct-2506
$0.075 / $0.20
Mistral-Small-3.2-24B-Instruct-2506
$0.09 / $0.28
+29% vs headline
mistral-small-3.2-24b-instruct-2506
$0.15 / $0.35
+88% vs headline

Capabilities

Core

  • Streaming
  • Function calling
  • JSON mode
  • Structured outputs

Multimodal

  • Vision
  • Image input
  • Audio
  • Image generation
  • Video

Advanced

  • Reasoning
  • Tool calling
  • MCP
  • Prompt caching
  • Batch API
  • Embeddings
Takes in
Text
Produces
Text
Open weights
License: Apache-2.0
Runs in about 57.6 GB of GPU memory

Cheaper alternatives

Current models that cost less and keep most of what this one can do: tools, vision, reasoning, structured output, caching and enough context.

Same model, cheaper host

No host sells it for less than DeepInfra.

Smaller Mistral AI models

No cheaper Mistral AI model keeps its key capabilities.

Other frontier labs

No cheaper match from another frontier lab.

Open-weight picks

  • Nemotron 3.5 Lightning
    NVIDIA · on Nebius AI Studio
    $0.06 / $0.24
    Has every key capability
    1% less
  • MiniMax M3.1 Flash
    MiniMax · on Refuseless
    $0.05 / $0.25
    Has every key capability
    6% less
  • Qwen3.5 9B
    Alibaba Qwen · on EmpirioLabs AI
    $0.09 / $0.13
    Has every key capability
    6% less
  • Ministral 3B 2512
    Mistral AI · on Mistral AI
    $0.10 / $0.10
    Has every key capability
    6% less

Call it

Using DeepInfra's API.

Python
from litellm import completion

response = completion(
    model="deepinfra/Mistral-Small-3.2-24B-Instruct-2506",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Mistral Small 3.2 24B Instruct 2506 cost?

On DeepInfra, Mistral Small 3.2 24B Instruct 2506 costs $0.075 per million input tokens and $0.20 per million output tokens.

Which APIs offer Mistral Small 3.2 24B Instruct 2506?

Mistral Small 3.2 24B Instruct 2506 runs on 3 APIs: DeepInfra, OVHcloud AI Endpoints and Scaleway.

What is Mistral Small 3.2 24B Instruct 2506's context window?

128K tokens, with up to 128K tokens in one reply.

Is Mistral Small 3.2 24B Instruct 2506 being retired?

No retirement date is scheduled for it on any API we track.

What are cheaper alternatives to Mistral Small 3.2 24B Instruct 2506?

Models that cost less and keep most of what it can do: Nemotron 3.5 Lightning on Nebius AI Studio (1% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Mistral Small 3.2 24B Instruct 2506 released?

Mistral AI released it on 20 Jun 2025.

What is Mistral Small 3.2 24B Instruct 2506's API model id?

Use Mistral-Small-3.2-24B-Instruct-2506 with DeepInfra. Other hosts use their own ids: mistral-small-3.2-24b-instruct-2506 on Scaleway.

Sources

Raw catalog entry for Mistral-Small-3.2-24B-Instruct-2506 on DeepInfra
{
  "max_input_tokens": 128000,
  "max_output_tokens": 128000,
  "input_cost_per_token": 7.5e-8,
  "output_cost_per_token": 2e-7,
  "litellm_provider": "deepinfra",
  "mode": "chat",
  "supports_tool_choice": true,
  "supports_function_calling": true
}