impulse

Mistral Small 24B Instruct 2501

Open weights

Mistral Small 3 is a 24B-parameter language model optimized for low-latency performance across common AI tasks.

API id Mistral-Small-24B-Instruct-2501Released 30 Jan 2025 (Jan 2025)
Input / 1M
$0.05
at DeepInfra
Output / 1M
$0.08
at DeepInfra
Context window
33K
tokens
Max output
33K
tokens per reply
Hosts
3
3 listings
Released
Jan 2025
30 Jan 2025

Pricing

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

TierInput / 1MOutput / 1M
Standard$0.05$0.08

What it costs a month

At DeepInfra list prices, 30 days.

  • Chat assistant5,000 requests a day, 2K in / 0.5K out$21.00
  • RAG over documents2,000 requests a day, 8K in / 0.6K out$26.88
  • Coding agent1,000 requests a day, 40K in / 2K out$64.80
  • Overnight batch20,000 requests a day, 4K in / 0.4K out$139
Use your own numbers

Where to run it

3 hosts serve Mistral Small 24B Instruct 2501. The comparison is on blended price, 3 parts input to 1 part output.

HostIn / out per 1M
DeepInfraInference
Mistral-Small-24B-Instruct-2501
$0.05 / $0.08
Together AIInference
Mistral-Small-24B-Instruct-2501
$0.10 / $0.30
+161% vs headline
Fireworks AIInference
mistral-small-24b-instruct-2501
$0.90 / $0.90
+1465% 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 56.6 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

  • Gemma 3 4B IT
    Google · on Amazon Bedrock
    $0.04 / $0.08
    Has every key capability
    13% less
  • Llama 3.2 3B
    Meta · on LlamaGate
    $0.04 / $0.08
    Has every key capability
    13% less
  • Qwen3.7 Flash Variant1
    Alibaba Qwen · on EmpirioLabs AI
    $0.028 / $0.11
    Has every key capability
    16% less
  • Granite 4.0 H Micro
    IBM · on Cloudflare Workers AI
    $0.017 / $0.112
    Has every key capability
    29% less

Model line

Newer and older versions, at each lab's own price.

  1. Mar 2025Mistral Small 3.1 24B InstructLatest$0.351 / $0.555
  2. Jan 2025Mistral Small 24B Instruct 2501This page$0.05 / $0.08

Call it

Using DeepInfra's API.

Python
from litellm import completion

response = completion(
    model="deepinfra/Mistral-Small-24B-Instruct-2501",
    messages=[{"role": "user", "content": "Hello"}],
)
print(response.choices[0].message.content)

Quick answers

How much does Mistral Small 24B Instruct 2501 cost?

On DeepInfra, Mistral Small 24B Instruct 2501 costs $0.05 per million input tokens and $0.08 per million output tokens.

Which APIs offer Mistral Small 24B Instruct 2501?

Mistral Small 24B Instruct 2501 runs on 3 APIs: DeepInfra, Together AI and Fireworks AI.

What is Mistral Small 24B Instruct 2501's context window?

33K tokens, with up to 33K tokens in one reply.

Is Mistral Small 24B Instruct 2501 being retired?

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

Is there a newer version of Mistral Small 24B Instruct 2501?

Yes. Mistral Small 3.1 24B Instruct is the newest model in this line, released on 17 Mar 2025.

What are cheaper alternatives to Mistral Small 24B Instruct 2501?

Models that cost less and keep most of what it can do: Gemma 3 4B IT on Amazon Bedrock (13% less). Savings are on a mix of 3 input tokens to 1 output token.

When was Mistral Small 24B Instruct 2501 released?

Mistral AI released it on 30 Jan 2025.

What is Mistral Small 24B Instruct 2501's API model id?

Use Mistral-Small-24B-Instruct-2501 with DeepInfra. Other hosts use their own ids: mistral-small-24b-instruct-2501 on Fireworks AI.

Sources

Raw catalog entry for Mistral-Small-24B-Instruct-2501 on DeepInfra
{
  "max_input_tokens": 32768,
  "max_output_tokens": 32768,
  "input_cost_per_token": 5e-8,
  "output_cost_per_token": 8e-8,
  "litellm_provider": "deepinfra",
  "mode": "chat",
  "supports_tool_choice": true,
  "supports_function_calling": true
}