Mistral Small 4: API Pricing, Context Window & Benchmarks
Mistral Small 4 is a language model from Mistral, released in March 2026, with multimodal input, a 256K-token context window, and pricing from $0.150/M input and $0.600/M output.
Mistral Small 4 is Mistral AI's hybrid small model that unifies instruct, reasoning, multimodal understanding, and coding capabilities in a single efficient system. It uses a 119B-parameter Mixture-of-Experts architecture with native image
Mistral Small 4 benchmarks
Rankings
Quality Tracker
Mistral Small 4 Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Tue Aug 04 2026Mistral Small 4 pricing
Providers
Mistral Small 4 starts at $0.150 per million input tokens and $0.600 per million output tokens via Mistral AI.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 Mistral AI | $0.150 | — | $0.600 | 256.0K/256.0K | 0.72 | 374 | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Mistral Small 4 model size
Mistral Small 4 has 119 billion parameters. See how it compares to other models in the same parameter range.
Mistral Small 4 context window
Input and output token limits for Mistral Small 4, plus how it ranks on long-context understanding.
Mistral Small 4 API
Run a request to see the response
Use it in your code
Billed at $0.15 input / $0.60 output per 1M tokens through the LLM Stats gateway.
from openai import OpenAI
client = OpenAI(
api_key="YOUR_API_KEY",
base_url="https://gateway.llm-stats.com/v1"
)
response = client.chat.completions.create(
model="mistral-small-latest",
messages=[
{"role": "user", "content": "What is machine learning?"}
]
)
print(response.choices[0].message.content)Need an API key? Create one above in the playground, or read the API documentation.
Mistral Small 4 latency
Mistral Small 4 time to first token, sustained output throughput, and failed-request rate from live API traffic over the trailing 7 days.
Provider operational metrics
Time to first token, output throughput, and failed-request rate from live API traffic
Mistral Small 4 examples
Recent arena outputs from Mistral Small 4, picked from the highest-ranked matchups.
Mistral Small 4 license
Mistral Small 4 is released under the Apache 2.0 license, which permits commercial use, has 119.0B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 119.0B
Apache License 2.0 - allows commercial use
Mistral Small 4 resources
Official sources for Mistral Small 4: api documentation, official playground, official launch post.
Mistral Small 4 vs other models
The most-compared alternatives to Mistral Small 4 are Ministral 3 (14B Reasoning 2512), QwQ-32B, Qwen3 30B A3B. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Mistral Small 4
Models ranked just above and below Mistral Small 4 by LLM Stats score.
FAQ
Common questions about Mistral Small 4.