Last refreshed 2026-06-15. Next refresh: weekly.
Why use Mistral Small 3.1 24B Instruct on Together AI?
Together AI offers Mistral Small 3.1 24B Instruct with pay-as-you-go pricing at $0.10/1M input tokens. Together AI is a platform for running open-source and proprietary LLMs with fast serverless and dedicated endpoints at competitive inference pricing.
Compare Mistral Small 3.1 24B Instruct across 7 providers to find the best fit for your use caseInput / 1M
$0.10
Output / 1M
$0.30
Cache
Not sourced
Batch
Not sourced
Setup recipe
Python + curlInstall
pip install togetherAuth
export TOGETHER_API_KEY=...Call
from together import Together
client = Together() # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
model="mistral-small-3.1-24b-instruct",Model ID
mistral-small-3.1-24b-instructRequest example
from together import Together
client = Together() # reads TOGETHER_API_KEY from env
response = client.chat.completions.create(
model="mistral-small-3.1-24b-instruct",
messages=[{"role": "user", "content": "Hello"}]
)
print(response.choices[0].message.content)Gotchas
- Together uses "organization/model-name" format, e.g. "meta-llama/Llama-4-Scout-17B-16E-Instruct" or "Qwen/QwQ-32B". See the Together model catalog for the exact ID.
- The examples expect TOGETHER_API_KEY; rename it only if your application config maps the new variable.
Compare Mistral Small 3.1 24B Instruct Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| Cloudflare Workers AI | $0.35 | $0.56 |
| OpenRouter | $0.35 | $0.56 |
| Fireworks AI | $0.90 | $0.90 |
| NVIDIA NIM | — | — |
| Together AI | $0.10 | $0.30 |
Pricing
| Type | Price (per 1M) |
|---|---|
| Input tokens | $0.10 |
| Output tokens | $0.30 |
Capabilities
VisionMultimodalStructured Outputs
About Mistral Small 3.1 24B Instruct
Mistral's Small 3.1 24B model with multimodal vision understanding capabilities. Optimized for cost-efficient deployment with 128K token context window. Available on Cloudflare Workers AI.
Get Started
Model Specs
Released2025-12-15
Parameters24B
Context128k
ArchitectureDecoder Only
Knowledge cutoff2023-10