Mistral Large 4 vs DeepSeek V4 Pro 0813 vs Inkling Small
Too close to call on our weighted score (Inkling Small 68, Mistral Large 4 67, DeepSeek V4 Pro 0813 67). The right pick depends on what you value most.
Mistral AIMistral Large 4
67/100- ECI150.6
- Price$0.70 / $2.10
- Context1.05M
DeepSeekDeepSeek V4 Pro 0813
67/100- ECI155.9
- Price$0.66 / $1.98
- Context1M
Thinking MachinesInkling Small
68/100- ECI150.5
- Price$0.58 / $1.44
- Context1.05M
Too close to call
It is close. Our weighted score puts them within 1 points (Inkling Small 68/100, Mistral Large 4 67/100, DeepSeek V4 Pro 0813 67/100), so choose by what matters most for your work: DeepSeek V4 Pro 0813 for raw capability and Inkling Small on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
- CapabilityDeepSeek V4 Pro 0813Capabilities Index (ECI): DeepSeek V4 Pro 0813 155.9 · Mistral Large 4 150.6 · Inkling Small 150.5
- Lowest priceInkling SmallInkling Small $0.795 · DeepSeek V4 Pro 0813 $0.99 · Mistral Large 4 $1.05 per 1M tokens (3:1 blend)
- Longest contextMistral Large 4 and Inkling SmallMistral Large 4 1,048,576 · Inkling Small 1,048,576 · DeepSeek V4 Pro 0813 1,000,000 tokens
- Widest inputsInkling SmallMistral Large 4: Text, Images · DeepSeek V4 Pro 0813: Text · Inkling Small: Text, Images, Audio
- Self-hostingDeepSeek V4 Pro 0813 and Inkling SmallPublishes downloadable weights (MIT and Apache-2.0)
| Measure | Weight | Mistral Large 4 | DeepSeek V4 Pro 0813 | Inkling Small |
|---|---|---|---|---|
| CapabilityCapabilities Index (ECI) | 50% | 77 | 84 | 77 |
| Price | 25% | 47 | 48 | 52 |
| Inputs & features | 15% | 70 | 45 | 70 |
| Context window | 10% | 61 | 60 | 61 |
| Overall | 100% | 67/100 | 67/100 | 68/100 |
Every spec in one table
Highlighted cells lead their row. Dashes mean the data is not published.
| Specification | Mistral Large 4Mistral AI | DeepSeek V4 Pro 0813DeepSeek | Inkling SmallThinking Machines |
|---|---|---|---|
| Capability | |||
| Capabilities Index (ECI) | 150.6 | 155.9 (best) | 150.5 |
| ECI rank | #57 of 165 | #35 of 165 (best) | #58 of 165 |
| GPQA DiamondGraduate-level science questions | 88.1% | 91.7% (best) | 88.5% |
| FrontierMath Tiers 1–3Research-level mathematics | 58.6% | 64.6% (best) | 46.3% |
| OTIS Mock AIME 2024–2025Competition mathematics | 98.3% | 98.6% (best) | 90.0% |
| SimpleQA VerifiedShort factual questions | 20.0% | 52.9% (best) | 19.1% |
| Price per million tokens | |||
| Input | $0.70 | $0.66 | $0.58 (best) |
| Output | $2.10 | $1.98 | $1.44 (best) |
| Cached input | $0.07 | $0.022 (best) | $0.116 |
| Blended (3:1) | $1.05 | $0.99 | $0.795 (best) |
| Long-context rate | Same rate | Same rate | Same rate |
| Price source | Official Mistral API | Official DeepSeek API | Official Thinking Machines API |
| Limits | |||
| Context window | 1,048,576 tokens (best) | 1,000,000 tokens | 1,048,576 tokens (best) |
| Max output | 262,144 tokens | 384,000 tokens | 1,048,576 tokens (best) |
| Inputs and features | |||
| Text | Yes | Yes | Yes |
| Images | Yes | No | Yes |
| PDFs | No | No | No |
| Audio | No | No | Yes |
| Video | No | No | No |
| Reasoning | Yeslow · medium · high | Yeslow · high · max | Yeslow · medium · high · xhigh · max |
| Tool calling | Yes | Yes | Yes |
| Structured output | Yes | Yes | No |
| Availability | |||
| Weights | Proprietary | OpenMIT | OpenApache-2.0 |
| API model ID | mistral-large-4 | deepseek-v4-pro | thinkingmachines/Inkling-Small |
| API providers | 15 | 40 (best) | 12 |
| Released | Oct 6, 2026 | Aug 13, 2026 | Jul 30, 2026 |
| Knowledge cutoff | — | — | — |
What would a month cost?
Enter your expected volume in millions of tokens. List prices only; caching and batch discounts would lower these.
- Mistral Large 4$11.20
- DeepSeek V4 Pro 0813$10.56
- Inkling Small$8.68
Which should you choose?
Which is better: Mistral Large 4, DeepSeek V4 Pro 0813 or Inkling Small?
It is close. Our weighted score puts them within 1 points (Inkling Small 68/100, Mistral Large 4 67/100, DeepSeek V4 Pro 0813 67/100), so choose by what matters most for your work: DeepSeek V4 Pro 0813 for raw capability and Inkling Small on price. The score weighs capability 50%, price 25%, inputs & features 15%, context window 10%.
Which is cheaper, Mistral Large 4, DeepSeek V4 Pro 0813 or Inkling Small?
Inkling Small is cheaper at $0.58 input / $1.44 output per million tokens (official Thinking Machines API price). DeepSeek V4 Pro 0813 costs $0.66 input / $1.98 output per million tokens (official DeepSeek API price); Mistral Large 4 costs $0.70 input / $2.10 output per million tokens (official Mistral API price). At a typical mix of three input tokens to one output token, that is $0.795 per million tokens for Inkling Small versus $0.99 for DeepSeek V4 Pro 0813 (1.2× as much) and $1.05 for Mistral Large 4 (1.3× as much).
Which scores higher on benchmarks?
DeepSeek V4 Pro 0813 scores higher on the Capabilities Index (ECI): DeepSeek V4 Pro 0813 155.9 (#35 of 165), Mistral Large 4 150.6 (#57 of 165) and Inkling Small 150.5 (#58 of 165). Their confidence ranges do not overlap (154.2–158.1 vs 147.4–153.5), so the gap is a real one. On individual benchmarks: GPQA Diamond — DeepSeek V4 Pro 0813 91.7%, Inkling Small 88.5%, Mistral Large 4 88.1%; FrontierMath Tiers 1–3 — DeepSeek V4 Pro 0813 64.6%, Mistral Large 4 58.6%, Inkling Small 46.3%; OTIS Mock AIME 2024–2025 — DeepSeek V4 Pro 0813 98.6%, Mistral Large 4 98.3%, Inkling Small 90.0%; SimpleQA Verified — DeepSeek V4 Pro 0813 52.9%, Mistral Large 4 20.0%, Inkling Small 19.1%.
Which is better for coding?
There are no published SWE-bench Verified results for Mistral Large 4, DeepSeek V4 Pro 0813 and Inkling Small yet, so there is no like-for-like coding score. On overall capability, DeepSeek V4 Pro 0813 leads, which tends to carry over to coding, but test on your own codebase. All three support tool calling for agent workflows.
Which has the bigger context window?
Mistral Large 4 and Inkling Small have the largest context windows (1,048,576 and 1,048,576 tokens), against 1,000,000 for DeepSeek V4 Pro 0813. Maximum output per response: Mistral Large 4 up to 262,144, DeepSeek V4 Pro 0813 up to 384,000, Inkling Small up to 1,048,576 tokens.
Which can read images, PDFs, audio or video?
Mistral Large 4 accepts text and images; DeepSeek V4 Pro 0813 accepts text; Inkling Small accepts text, images and audio. Inkling Small handles the widest range of inputs.
Are any of these open source?
DeepSeek V4 Pro 0813 and Inkling Small publishes its weights (MIT and Apache-2.0) and can be self-hosted; Mistral Large 4 is proprietary.
Which is newer?
Mistral Large 4 is the newest, released Oct 6, 2026. DeepSeek V4 Pro 0813 came out Aug 13, 2026; Inkling Small came out Jul 30, 2026.
How do you decide the winner?
Each model gets a 0–100 score on capability (50%, independent benchmark results); price (25%, blended price per million tokens (3 input : 1 output), log scale); inputs & features (15%, image, PDF, audio and video input, tool calling, structured output and reasoning); context window (10%, maximum tokens per request, log scale). Dimensions missing for any model are dropped and the remaining weights rescaled, so every model is judged on the same evidence. Specs and prices come from public model listings and the labs’ own API pages; capability scores come from independent benchmark runs. Data updated Nov 2, 2026.
Related comparisons
- Mistral Large 4 vs Qwen3.8 27BAlibaba (Qwen) · ECI 151.8
- Mistral Large 4 vs Kimi K2.7 CodeMoonshot AI · ECI 150.2
- DeepSeek V4 Pro 0813 vs Gemini 3.6 FlashGoogle · ECI 154.7
- DeepSeek V4 Pro 0813 vs GLM-5.3Z.ai (Zhipu) · ECI 156.2
- DeepSeek V4 Pro 0813 vs Muse Spark 1.2Meta · ECI 155.2
- DeepSeek V4 Pro 0813 vs Qwen3.8 27BAlibaba (Qwen) · ECI 151.8
