Mistral Medium 3 vs Mistral Small 3
Benchmarks, API Token Pricing, Context Window & Speed Comparison
Related topics (12)
Mistral Medium 3 by Mistral AI and Mistral Small 3 by Mistral AI represent two of the frontier AI models analyzed in our comprehensive 2026 AI benchmark and LLM comparison. In this head-to-head evaluation, we examine API token pricing, context window specifications, inference speed (tokens per second), and empirical reasoning performance. From a pure economic perspective, Mistral Small 3 holds a notable pricing advantage for token ingestion. On output generation, Mistral Small 3 is more economical per million generated tokens. In data-heavy architectures requiring extensive repository or document analysis, Mistral Medium 3 provides an expanded memory horizon with 131K tokens. In latency-sensitive production environments, Mistral Small 3 leads in tokens-per-second throughput, making it ideal for real-time conversational agents and high-concurrency workflows. Below is the complete empirical head-to-head breakdown across cost, speed, context, and capability matrices.
Switch & Compare Any Models
Select any AI models from our verified benchmark database to generate live side-by-side matrices.
Mistral Medium 3
Enterprise BalancedBalanced enterprise model featuring 131K context, multimodal vision, robust tool calling, and attractive $0.40/$2.00 pricing.
$0.40 / 1M
$2.00 / 1M
131.1K tokens
40.5%
Mistral Small 3
Efficient SmallHigh-efficiency 24B open foundation model delivering fast latency, low memory footprint, and enterprise-grade instruction adherence.
$0.10 / 1M
$0.30 / 1M
32K tokens
31.5%
Key Differences at a Glance
- Mistral Small 3 is 5.2x cheaper for API usage (input + output tokens combined).
- Mistral Medium 3 has a larger context window (131K vs 32K tokens).
- Mistral Small 3 is faster at 105 tok/s vs 85 tok/s.
- Mistral Medium 3 leads on SWE-bench coding (40.5% vs 31.5%).
| Feature | Mistral Medium 3 | Mistral Small 3 |
|---|---|---|
Intelligence Index Composite reasoning & knowledge score (0-100) | 47 | 41 |
Provider | Mistral AI | Mistral AI |
Input Price Cost per million input tokens | $0.40 / 1M | $0.10 / 1M |
Output Price Cost per million output tokens | $2.00 / 1M | $0.30 / 1M |
Blended Price Weighted 7:2:1 cache:input:output per 1M | $0.35 / 1M | $0.09 / 1M |
Context Window Maximum input + output tokens | 131.1K tokens~197 A4 pages of text | 32K tokens~48 A4 pages of text |
Max Output Tokens Per single request | 16K | 8K |
Throughput Speed Tokens generated per second | 85 tok/s | 105 tok/s |
SWE-bench Verified Real-world software engineering | 40.5% | 31.5% |
GPQA Diamond Graduate-level reasoning | 57.5% | 46.5% |
Cached Input Price Prompt caching discount per 1M tokens | $0.10 / 1M | $0.05 / 1M |
Who Wins Where?
At-a-glance decision frameworkEmpirical Head-to-Head Benchmark Scores
Official evaluation metrics verified by independent third-party research labs.
Industry benchmark evaluating real-world GitHub issue resolution and multi-file debugging.
Challenging questions created by domain experts to test complex PhD-level reasoning.
Hardened reasoning and academic knowledge benchmark with reduced lucky-guess probability.
Crowdsourced human preference evaluation based on blind, head-to-head model battles.
Autonomous multi-step tasks executed inside a real command-line terminal environment.
American Invitational Mathematics Examination — multi-step Olympiad-level reasoning.
Accuracy when reasoning over very large inputs that fill the model context window.
Tokens emitted per second during active generation streaming.
Latency & Response Time
Time to first token (TTFT) and estimated end-to-end response time for a typical 500-token response.
Real-Time Interactive Token Cost Simulator
Adjust sliders to calculate projected monthly cloud API spending with prompt caching discounts.
Mistral Medium 3 · Strengths & Key Advantages
- Compelling price-to-performance ratio ($0.40 input / $2.00 output)
- Native visual understanding across documents, schematics, and charts
- 131K context window with enterprise-grade function calling
Considerations & Trade-offs
- Trails frontier flagship models on difficult competition mathematics
- Open weights require multi-GPU setups for full precision
Mistral Small 3 · Strengths & Key Advantages
- Extremely low API pricing ($0.10/$0.30) and lightweight local footprint
- Snappy inference speed exceeding 100 tokens/sec
- Reliable function calling and classification precision
Considerations & Trade-offs
- 32K context window limits deep repository scanning
- Text-only with no image input capabilities
Token Use & Task Economics
Estimated cost and token consumption to complete one representative agentic task.
| Metric | Mistral Medium 3 | Mistral Small 3 |
|---|---|---|
Cost per Task Estimated USD to finish one task | $0.35 | $0.08 |
Output Tokens / Task Tokens generated per task | 35K | 25K |
Reasoning Tokens / Task Thinking tokens burned per task | 0K | 0K |
Technical Specifications
Architecture, release timeline, capabilities, and modalities.
| Feature | Mistral Medium 3 | Mistral Small 3 |
|---|---|---|
| Official API Model ID (SDK) | mistral-medium-3-latest | mistral-small-3-latest |
| API Protocol | OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI | OpenAI-Compatible REST / vLLM / SGLang / HuggingFace TGI |
| Release Date | 2025-05 | 2025-01 |
| Knowledge Cutoff | March 2025 | December 2024 |
| Architecture | Enterprise Multimodal Transformer | Compact Dense Transformer |
| Parameters | Confidential (~70B) | 24B |
| Enterprise Rate Limits (RPM / TPM) | Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud | Unlimited (Hardware-bound on self-hosted GPU) / 10,000 RPM Cloud · Unlimited local throughput / 10M+ TPM Managed Cloud |
| Long-Context Tier (>128K/200K) | Flat rate ($0.4/1M in) across full 131K window | Flat rate ($0.1/1M in) across full 32K window |
| Prompt Cache Policy & TTL | Cached input at $0.1/1M tokens | Cached input at $0.05/1M tokens |
| Computer Use / GUI Agent | API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop) | API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop) |
| MCP & Parallel Tool Calling | Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema | Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema |
| Web Search Grounding & Sandbox | Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools | Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools |
| Official Fine-Tuning Support | Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory) | Full Weights SFT, LoRA, QLoRA, DPO & GRPO RL (Unsloth / Axolotl / Llama-Factory) |
| Multimodal Token Billing | Text BPE (~4 chars/token) · Vision (~258–765 tokens per image tile) | Text BPE (~4 chars/token) |
| Quantization & Min GPU VRAM | BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 43 GB VRAM (4-bit Quantized) · 151 GB VRAM (Native BF16) | BF16 / FP16, FP8 Dynamic, INT4 AWQ / GPTQ, GGUF (Q4_K_M / Q8_0) · 15 GB VRAM (4-bit Quantized) · 52 GB VRAM (Native BF16) |
| Safety & Frontier Classification | Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma) | Open-Weights System Card + Customizable Guardrail Layer (Llama Guard / ShieldGemma) |
| Enterprise Compliance (ZDR/HIPAA/SOC2) | 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control | 100% Air-Gapped On-Premises / Private VPC · Full HIPAA, GDPR & SOC2 Control |
| Input Modalities | text, vision | text |
| Output Modalities | text | text |
Mistral Medium 3 vs Mistral Small 3: Quick Answers
Which is more intelligent, Mistral Medium 3 or Mistral Small 3?
Mistral Medium 3 is more intelligent. It scores 47 compared with 41 on the composite Intelligence Index.
Which model is faster?
Mistral Small 3 is faster, generating 105 tokens per second compared with 85 tokens per second.
Which model is cheaper to run?
Mistral Small 3 is cheaper at $0.09 per 1M tokens blended, compared with $0.35 (7:2:1 cache:input:output ratio).
Which model has lower latency?
Mistral Small 3 has lower latency, with a time to first token of 0.38s compared with 0.48s.
Which model has a larger context window?
Mistral Medium 3 has a larger context window, supporting 131.1K tokens compared with 32K tokens.
Verdict
Verdict & Model Selection Recommendation: Choose Mistral Medium 3 if your priority is Enterprise internal assistants, document workflow automation, and multimodal analytics. Its performance in demanding tasks justifies its operational token cost. Choose Mistral Small 3 if your workflow prioritizes High-volume customer support, classification pipelines, and low-latency chatbots. For large-scale batch processing or customer-facing conversational interfaces, its balance of speed and economics delivers superior ROI.
Frequently asked questions
How does Mistral Medium 3 compare to Mistral Small 3 in API token pricing and cost per token?+
Mistral Medium 3 costs $0.40 per 1M input tokens and $2.00 per 1M output tokens, whereas Mistral Small 3 costs $0.10 input and $0.30 output. Overall, Mistral Small 3 is the more cost-effective model for high-volume API pipelines. Both models support prompt caching discounts of up to 90% for repeated prompt prefixes.
Which model has a larger context window: Mistral Medium 3 or Mistral Small 3?+
Mistral Medium 3 supports a context window of 131K tokens (~98k words), while Mistral Small 3 supports 32K tokens (~24k words). Therefore, Mistral Medium 3 can process more textual data and document context in a single prompt.
Which AI model is better for software engineering and coding: Mistral Medium 3 or Mistral Small 3?+
Mistral Medium 3 scores 40.5% on SWE-bench Verified while Mistral Small 3 scores 31.5%. For autonomous software engineering and multi-file debugging, Mistral Medium 3 holds the verified benchmark lead.
What is the difference in reasoning capability and extended thinking between Mistral Medium 3 and Mistral Small 3?+
Mistral Medium 3 is optimized for low-latency direct generation. In contrast, Mistral Small 3 focuses on standard fast inference.
How does inference speed (tokens per second) compare between Mistral Medium 3 and Mistral Small 3?+
Mistral Medium 3 generates approximately 85 tokens per second, while Mistral Small 3 delivers 105 tokens per second. In latency-sensitive production environments, Mistral Small 3 provides faster time-to-first-token (TTFT) and higher streaming response velocity.
Can you implement a tiered LLM routing setup combining Mistral Medium 3 and Mistral Small 3 to optimize costs?+
Yes! High-efficiency architectures route high-frequency routine classification and conversational tasks to Mistral Small 3 to save operational costs, and dynamically escalate complex architectural queries or reasoning tasks to Mistral Medium 3. This tiered routing pattern cuts overall API bills by up to 70%.
Understand key metrics like context window, token pricing, reasoning mode, and SWE-bench scores in our comprehensive AI glossary.
Related reading
- Aya Vision 8B vs Mistral Small 3: Benchmarks, Pricing & Speed ComparisonCompare
- Command R7B Arabic vs Mistral Small 3: Benchmarks, Pricing & Speed ComparisonCompare
- Llama 3.1 Nemotron 70B Instruct vs Mistral Medium 3: Benchmarks, Pricing & Speed ComparisonCompare
- Mistral Small 3.2 vs Mistral Medium 3: Benchmarks, Pricing & Speed ComparisonCompare
- Aion-3.0 vs Aion-Mini: Benchmarks, Pricing & Speed ComparisonCompare
- Aion-3.0 vs Gemini 3.6 Flash: Benchmarks, Pricing & Speed ComparisonCompare
Benchmark scores, token prices, and rate limits evolve rapidly as AI labs release model updates. Always verify current specifications and pricing on the official provider documentation.
Sources: GetInfoUs Independent AI Benchmarks & Official API Specs