Mistral Large
ActiveMistral's flagship commercial model with tool calling and structured outputs.
Overview
Mistral Large is Mistral AI's top hosted model, supporting long context, tool calling, and structured outputs via the Mistral API.
History
Mistral Large became available via the Mistral AI API on 2024-02-26.
Training & availability
Training data has a knowledge cutoff of 2024-11-30 — information about events after that date is unlikely to appear in the model's responses. Mistral AI has not released the underlying model weights — access is via their hosted API only.
Capabilities
-
Context window: 262K tokens.
-
Max output: 262K tokens.
-
Input modalities: text, image.
Recommended for: vision, agentic, long-context.
Limitations
- The knowledge cutoff is 16 months old — this model will not know about recent events, releases, or API changes.
Pricing
- Input: $0.5000 per 1M tokens
- Output: $1.5000 per 1M tokens
Use the cost calculator above to estimate monthly spend for your workload.
Quick start
Minimal example using the OpenRouter API. Copy, paste, replace the key.
from openai import OpenAI
client = OpenAI(
base_url="https://openrouter.ai/api/v1",
api_key="sk-or-...",
)
resp = client.chat.completions.create(
model="mistral/mistral-large",
messages=[{"role": "user", "content": "Explain quantum computing in one sentence."}],
)
print(resp.choices[0].message.content)Cost calculator
Estimate your monthly bill. Presets are typical workload sizes.
Providers & performance
1 providerMulti-provider inference routes for this model — sorted by throughput. Latency is time-to-first-token; throughput is output tokens per second. Data from OpenRouter, measured over the last 30 minutes.
| Provider | Throughput | Latency (TTFT) | Input $ / 1M | Output $ / 1M | Context | Quant | Supports |
|---|---|---|---|---|---|---|---|
| Mistral | 35tok/s | 472ms | $2 | $6 | 128K | — | tools · json |
Benchmarks
| Benchmark | Score | Source |
|---|---|---|
| MMLUGeneral knowledge | 81.2% accuracy | Self-reported Mistral announcement |
Integrations & tooling support
- Tool calling
- Supported
- Structured outputs
- Supported
Price vs quality
Below-average benchmark performance for the price.
- Quality percentile
- 8.3%
- Effective price
- $1.25/1M
- Pricing breakdown
- $0.5/1M in
$1.5/1M out
Community ratings
Rate Mistral Large
Sign in to rate and review.
Comments
Sign in to leave a comment.