Devstral 2 Mistral AI
$0.002975
Total Cost
Vision/Images
✗ Not Available
Audio Processing
✗ Not Available
Video Analysis
✗ Not Available
Tool Usage
✓ Available
OCR Support
✗ Not Available
Batch API
✓ Available
Caching
✓ Available
90% savings
💰 Total Cost Calculation (from Plugin)
Base Cost (No Optimizations)
$0.005225 (rounded ~ $0.01)
Input: $0.005000 (rounded ~ $0.01)
Output: $0.000225
Output: $0.000225
Optimized Cost
$0.002975
Input: $0.005000 (rounded ~ $0.01)
Output: $0.000225
Unit: $0.000000
Fees: $0.000000
Output: $0.000225
Unit: $0.000000
Fees: $0.000000
Total Savings
$0.002250
43.1% discount
Advanced Cost Breakdown (from Plugin)
📊 Batch API
50.0% off
Asynchronous processing discount
Detailed Cost Analysis (from Plugin)
For 50,000 input tokens and 1,000 output tokens:
- Input Cost: $0.005000 (rounded ~ $0.01)
- Output Cost: $0.000225
- Total Cost: $0.002975
- Cost per 1K tokens: $0.000058
- Tokens per dollar: 17,142,857 tokens
- Context Window: 256000 tokens
Speed & Performance Analysis
With a processing speed of 450 tokens per second and 180ms time to first token:
- Processing Time: 1 minute, 55.78 seconds
- Latency: 180 milliseconds to first token
- Base Throughput: 450 tokens/second
- Effective Throughput: 441 tokens/second (temperature-adjusted)
Best Use Cases
Enterprise agentic coding workflows where repository awareness and long-term architectural consistency are prioritized.
Want this applied to YOUR actual stack?
This calculator shows the math for Devstral 2. Your decision needs more — current infrastructure, compliance requirements, actual workload patterns, volume tiers — that change which model is right for you.
Get a $39 personalized AI Architecture Audit. PDF tailored to your stack, delivered in under 60 seconds. 7-day no-questions-asked refund.
Get my instant AI audit — $39 →✨ Market Recommendations AI Model Registry
← Back to Devstral 2
📋 Active Input Parameters
Input Tokens:
50,000
Output Tokens:
1,000
Batch API:
Enabled (50% discount)
Cached Tokens:
50%
Tools:
Enabled
| Rank | AI Model & Provider | Total Cost | vs Devstral 2 |
|---|---|---|---|
| 🏆 |
Mistral Small 3
Mistral AI
|
$0.000763 Best Value | ↓ 74.4% cheaper |
| 🥈 |
Gemini 3.1 Flash Lite
Google
|
$0.002094 | ↓ 29.6% cheaper |
| 🥉 |
Gemini 3.5 Flash-Lite
Google
|
$0.002688 | ↓ 9.7% cheaper |
| #4 |
Gemini 2.5 Flash
Google
|
$0.002688 | ↓ 9.7% cheaper |
| #5 |
Mistral Large 3
Mistral AI
|
$0.003813 | ↑ 28.2% more |
| #6 |
Gemini 3.8 Flash
Google
|
$0.006094 (rounded ~ $0.01) | ↑ 104.8% more |
| #7 |
GPT-5.4 mini
OpenAI
|
$0.006281 (rounded ~ $0.01) | ↑ 111.1% more |
| #8 |
o4-mini Deep Research
OpenAI
|
$0.007875 (rounded ~ $0.01) | ↑ 164.7% more |
| #9 |
Claude Haiku 4.5
Anthropic
|
$0.008125 (rounded ~ $0.01) | ↑ 173.1% more |
| #10 |
Gemini 3.1 Flash
Google
|
$0.008375 (rounded ~ $0.01) | ↑ 181.5% more |
| #11 |
GPT-5.6 Luna
OpenAI
|
$0.008375 (rounded ~ $0.01) | ↑ 181.5% more |
| #12 |
o4-mini
OpenAI
|
$0.008663 (rounded ~ $0.01) | ↑ 191.2% more |
| #13 |
Gemini 3.6 Flash
Google
|
$0.012188 (rounded ~ $0.01) | ↑ 309.7% more |
| #14 |
Gemini 3.5 Flash
Google
|
$0.012563 (rounded ~ $0.01) | ↑ 322.3% more |
| #15 |
GPT-5.3 Codex Spark
OpenAI
|
$0.015531 (rounded ~ $0.02) | ↑ 422.1% more |
| #16 |
GPT-5.3 Instant
OpenAI
|
$0.015531 (rounded ~ $0.02) | ↑ 422.1% more |
| #17 |
Claude Sonnet 5
Anthropic
|
$0.016250 (rounded ~ $0.02) | ↑ 446.2% more |
| #18 |
GPT-5.6 Terra
OpenAI
|
$0.020938 | ↑ 603.8% more |
| #19 |
Gemini 2.5 Pro
Google
|
$0.022188 (rounded ~ $0.02) | ↑ 645.8% more |
| #20 |
Claude Sonnet 4.6
Anthropic
|
$0.024375 (rounded ~ $0.02) | ↑ 719.3% more |
| #21 |
Grok 4.3
xAI
|
$0.029500 | ↑ 891.6% more |
| #22 |
Grok 4.20 Beta
xAI
|
$0.029500 | ↑ 891.6% more |
| #23 |
Gemini 3.1 Pro
Google
|
$0.033500 (rounded ~ $0.03) | ↑ 1026.1% more |
| #24 |
Claude Opus 4.7
Anthropic
|
$0.040625 | ↑ 1265.5% more |
| #25 |
Claude Opus 5
Anthropic
|
$0.040625 | ↑ 1265.5% more |
| #26 |
Claude Opus 4.8
Anthropic
|
$0.040625 | ↑ 1265.5% more |
| #27 |
Claude Opus 4.6
Anthropic
|
$0.040625 | ↑ 1265.5% more |
| #28 |
GPT-5.4
OpenAI
|
$0.041875 (rounded ~ $0.04) | ↑ 1307.6% more |
| #29 |
GPT-5.4 Thinking
OpenAI
|
$0.041875 (rounded ~ $0.04) | ↑ 1307.6% more |
| #30 |
GPT-5.5 Instant
OpenAI
|
$0.041875 (rounded ~ $0.04) | ↑ 1307.6% more |
| #31 |
GPT-5.6 Sol
OpenAI
|
$0.041875 (rounded ~ $0.04) | ↑ 1307.6% more |
| #32 |
Claude Fable 5.1
Anthropic
|
$0.076563 (rounded ~ $0.08) | ↑ 2473.5% more |
| #33 |
Claude Mythos 5.1
Anthropic
|
$0.076563 (rounded ~ $0.08) | ↑ 2473.5% more |
| #34 |
o3 Deep Research
OpenAI
|
$0.078750 (rounded ~ $0.08) | ↑ 2547.1% more |
| #35 |
Claude Fable 5
Anthropic
|
$0.081250 (rounded ~ $0.08) | ↑ 2631.1% more |
| #36 |
Claude Mythos 5
Anthropic
|
$0.081250 (rounded ~ $0.08) | ↑ 2631.1% more |
| #37 |
GPT-5.5
OpenAI
|
$0.083750 (rounded ~ $0.08) | ↑ 2715.1% more |
| #38 |
o3 Pro
OpenAI
|
$0.157500 (rounded ~ $0.16) | ↑ 5194.1% more |
| #39 |
GPT-6 Astra
OpenAI
|
$0.162500 (rounded ~ $0.16) | ↑ 5362.2% more |
| #40 |
GPT-5.2 Pro
OpenAI
|
$0.186375 (rounded ~ $0.19) | ↑ 6164.7% more |
| #41 |
GPT-5.2 Pro
OpenAI
|
$0.186375 (rounded ~ $0.19) | ↑ 6164.7% more |
🏆
Mistral Small 3
Mistral Small 3 Mistral AI
$0.000763
vs Devstral 2:
↓ 74.4%
🥈
Gemini 3.1 Flash Lite
Gemini 3.1 Flash Lite Google
$0.002094
vs Devstral 2:
↓ 29.6%
🥉
Gemini 3.5 Flash-Lite
Gemini 3.5 Flash-Lite Google
$0.002688
vs Devstral 2:
↓ 9.7%
#4
Gemini 2.5 Flash
Gemini 2.5 Flash Google
$0.002688
vs Devstral 2:
↓ 9.7%
#5
Mistral Large 3
Mistral Large 3 Mistral AI
$0.003813
vs Devstral 2:
↑ 28.2%
#6
Gemini 3.8 Flash
Gemini 3.8 Flash Google
$0.006094 (rounded ~ $0.01)
vs Devstral 2:
↑ 104.8%
#7
GPT-5.4 mini
GPT-5.4 mini OpenAI
$0.006281 (rounded ~ $0.01)
vs Devstral 2:
↑ 111.1%
#8
o4-mini Deep Research
o4-mini Deep Research OpenAI
$0.007875 (rounded ~ $0.01)
vs Devstral 2:
↑ 164.7%
#9
Claude Haiku 4.5
Claude Haiku 4.5 Anthropic
$0.008125 (rounded ~ $0.01)
vs Devstral 2:
↑ 173.1%
#10
Gemini 3.1 Flash
Gemini 3.1 Flash Google
$0.008375 (rounded ~ $0.01)
vs Devstral 2:
↑ 181.5%
#11
GPT-5.6 Luna
GPT-5.6 Luna OpenAI
$0.008375 (rounded ~ $0.01)
vs Devstral 2:
↑ 181.5%
#12
o4-mini
o4-mini OpenAI
$0.008663 (rounded ~ $0.01)
vs Devstral 2:
↑ 191.2%
#13
Gemini 3.6 Flash
Gemini 3.6 Flash Google
$0.012188 (rounded ~ $0.01)
vs Devstral 2:
↑ 309.7%
#14
Gemini 3.5 Flash
Gemini 3.5 Flash Google
$0.012563 (rounded ~ $0.01)
vs Devstral 2:
↑ 322.3%
#15
GPT-5.3 Codex Spark
GPT-5.3 Codex Spark OpenAI
$0.015531 (rounded ~ $0.02)
vs Devstral 2:
↑ 422.1%
#16
GPT-5.3 Instant
GPT-5.3 Instant OpenAI
$0.015531 (rounded ~ $0.02)
vs Devstral 2:
↑ 422.1%
#17
Claude Sonnet 5
Claude Sonnet 5 Anthropic
$0.016250 (rounded ~ $0.02)
vs Devstral 2:
↑ 446.2%
#18
GPT-5.6 Terra
GPT-5.6 Terra OpenAI
$0.020938
vs Devstral 2:
↑ 603.8%
#19
Gemini 2.5 Pro
Gemini 2.5 Pro Google
$0.022188 (rounded ~ $0.02)
vs Devstral 2:
↑ 645.8%
#20
Claude Sonnet 4.6
Claude Sonnet 4.6 Anthropic
$0.024375 (rounded ~ $0.02)
vs Devstral 2:
↑ 719.3%
#21
Grok 4.3
Grok 4.3 xAI
$0.029500
vs Devstral 2:
↑ 891.6%
#22
Grok 4.20 Beta
Grok 4.20 Beta xAI
$0.029500
vs Devstral 2:
↑ 891.6%
#23
Gemini 3.1 Pro
Gemini 3.1 Pro Google
$0.033500 (rounded ~ $0.03)
vs Devstral 2:
↑ 1026.1%
#24
Claude Opus 4.7
Claude Opus 4.7 Anthropic
$0.040625
vs Devstral 2:
↑ 1265.5%
#25
Claude Opus 5
Claude Opus 5 Anthropic
$0.040625
vs Devstral 2:
↑ 1265.5%
#26
Claude Opus 4.8
Claude Opus 4.8 Anthropic
$0.040625
vs Devstral 2:
↑ 1265.5%
#27
Claude Opus 4.6
Claude Opus 4.6 Anthropic
$0.040625
vs Devstral 2:
↑ 1265.5%
#28
GPT-5.4
GPT-5.4 OpenAI
$0.041875 (rounded ~ $0.04)
vs Devstral 2:
↑ 1307.6%
#29
GPT-5.4 Thinking
GPT-5.4 Thinking OpenAI
$0.041875 (rounded ~ $0.04)
vs Devstral 2:
↑ 1307.6%
#30
GPT-5.5 Instant
GPT-5.5 Instant OpenAI
$0.041875 (rounded ~ $0.04)
vs Devstral 2:
↑ 1307.6%
#31
GPT-5.6 Sol
GPT-5.6 Sol OpenAI
$0.041875 (rounded ~ $0.04)
vs Devstral 2:
↑ 1307.6%
#32
Claude Fable 5.1
Claude Fable 5.1 Anthropic
$0.076563 (rounded ~ $0.08)
vs Devstral 2:
↑ 2473.5%
#33
Claude Mythos 5.1
Claude Mythos 5.1 Anthropic
$0.076563 (rounded ~ $0.08)
vs Devstral 2:
↑ 2473.5%
#34
o3 Deep Research
o3 Deep Research OpenAI
$0.078750 (rounded ~ $0.08)
vs Devstral 2:
↑ 2547.1%
#35
Claude Fable 5
Claude Fable 5 Anthropic
$0.081250 (rounded ~ $0.08)
vs Devstral 2:
↑ 2631.1%
#36
Claude Mythos 5
Claude Mythos 5 Anthropic
$0.081250 (rounded ~ $0.08)
vs Devstral 2:
↑ 2631.1%
#37
GPT-5.5
GPT-5.5 OpenAI
$0.083750 (rounded ~ $0.08)
vs Devstral 2:
↑ 2715.1%
#38
o3 Pro
o3 Pro OpenAI
$0.157500 (rounded ~ $0.16)
vs Devstral 2:
↑ 5194.1%
#39
GPT-6 Astra
GPT-6 Astra OpenAI
$0.162500 (rounded ~ $0.16)
vs Devstral 2:
↑ 5362.2%
#40
GPT-5.2 Pro
GPT-5.2 Pro OpenAI
$0.186375 (rounded ~ $0.19)
vs Devstral 2:
↑ 6164.7%
#41
GPT-5.2 Pro
GPT-5.2 Pro OpenAI
$0.186375 (rounded ~ $0.19)
vs Devstral 2:
↑ 6164.7%
✨ How recommendations work (v8.6.0): We scan all active models in the registry and only include those that support ALL your current inputs. For token-based models, we check if they can handle your token counts. For special pricing models (OCR, video, audio), we verify they have the correct pricing structure. Features marked requested were in your inputs but not supported by that model. Now using official provider pricing without reseller markups.
For enterprise architects managing large-scale software engineering teams, the choice of an AI model for code review is often a trade-off between reasoning depth and infrastructure control. Devstral 2, with its specialized architecture, represents a strategic pivot toward agentic workflows that require deep repository awareness rather than simple text completion. When analyzing pull requests averaging 50,000 tokens, the model’s ability to maintain context across multi-file dependencies becomes a critical differentiator.
Unlike generalist models that may struggle with the nuanced syntax of legacy enterprise codebases, Devstral 2 is designed to explore file structures and Git statuses natively. This makes it particularly effective for teams that need consistent, reproducible reviews without the latency overhead of multi-step reasoning chains. By leveraging its open-weight architecture, engineering leads can deploy a consistent coding assistant across their entire CI/CD pipeline, ensuring that every merge request is evaluated against the same internal coding standards.
For 50-engineer organizations, the decision to standardize on a model like Devstral 2 often hinges on the desire for operational independence. While proprietary models offer rapid iteration, the ability to fine-tune and host Devstral 2 allows for greater control over security and compliance, especially when dealing with proprietary IP. The model is best suited for teams that prioritize long-term architectural consistency and plan to scale their agentic coding workflows to support high-volume, automated development pipelines throughout the year.
Frequently Asked Questions
How accurate are these AI model cost calculations?
Our calculations are based on official pricing from each provider (Google, OpenAI, Anthropic, Meta, xAI, Perplexity, DeepSeek, Mistral) and are updated regularly.
We account for all factors including multimodal inputs, caching discounts, batch API pricing, tool usage multipliers, OCR processing, audio minutes, silence fees, and research mode pricing.
Note: Reseller markups and dedicated instance multipliers have been removed to reflect official provider pricing.
How does prompt caching work?
Caching discounts vary by provider: Google and OpenAI offer 90% discounts on cached input tokens. Anthropic uses write (1.25x) and read (0.10x) multipliers. Savings are applied to the token portion only, not unit-based fees.
How do Market Recommendations work (v8.6.0)?
Our recommendation engine scans the entire model registry and only includes models that support ALL your current input parameters (tokens, images, video, audio, OCR, tools, batch API, etc.). It calculates exact costs with your settings and sorts by price, showing you the best value options that can handle your complete workflow. Special pricing models (OCR, video, audio, image generation) are properly handled and only appear when their specific input types are requested. v8.6.0 removes reseller markups (20% buffer) and dedicated instance multipliers to reflect official provider pricing.
What is the YemHub AI Calculator Tool?
The YemHub AI Calculator is the most comprehensive tool for estimating costs and comparing performance metrics across 50+ AI models. It calculates token-based pricing, analyzes multimodal processing, accounts for state-dependent pricing (context cliffs, tiered tunnels), provides optimization recommendations, and now offers intelligent market matching to find the best alternatives for your specific needs.