Mistral · Open weights

Mistral Medium 3.5 Thinking

Added Apr 30, 2026Open weights

Mistral Medium 3.5 with reasoning enabled by default (reasoning_effort=high), for complex coding, agentic, and multi-step reasoning prompts.

Reasoning
Tools
Vision
Structured output

Input: Text, Images
Output: Text
Reasoning effort: none · high
Discovery tier: Open weights

Pricing

USD per 1M tokens

Input: $1.50
Output: $7.50

Reference prices as published by the model provider. API example

Specifications

Context window: 256K
Max output: 32.8K

Side by side

Mistral Medium 3.5 Thinking compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Limits
	Mistral Medium 3.5 ThinkingMistralThis model	DeepSeek R1 Qwen AbliteratedDeepSeekRemove
Provider	Mistral	DeepSeek
Discovery tier	Open weights	Open weights
Added	Apr 30, 2026	Jan 1, 2024
Context window	256KBest	16.38K
Max output	32.77KBest	8.19K
Average output	—	200 tokens
Pricing, USD per 1M tokens
Input	$1.50	$1.40Best
Output	$7.50	$1.40Best
Performance
Throughput	—	14.8 tok/s
Time to first token	—	14.0 s
Request success (24h)	—	57.8%
Capabilities
Reasoning	Yes	Yes
Tools	Yes	No
Vision	Yes	No
Structured output	Yes	No
Reasoning effort	none, high	—

Public evaluations

Benchmarks

There are no public benchmark results for these models yet.

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart

curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/mistral-medium-3.5:thinking",
    "reasoning_effort": "none",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'

import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="mistralai/mistral-medium-3.5:thinking",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

Mistral

Other Mistral models, starting with the same family.