text model comparison
DeepSeek-V4.1-Flash vs Inkling 2 Small
DeepSeek-V4.1-Flash and Inkling 2 Small are both current text models, from DeepSeek and Thinking Machines Lab. Both cost $0.30 per 1M input tokens. In Thinking Machines Lab's Inkling 2 Small model card, DeepSeek-V4.1-Flash scores 77.0% on DeepSWE v1.1 and Inkling 2 Small 72.1%. DeepSeek-V4.1-Flash has the larger context window, 1,000,000 vs 262,144 tokens.
- Longer context window
- DeepSeek-V4.1-Flash1M tokens against 262K tokens
- Newer release
- Inkling 2 SmallNov 2026 against Sep 2026
Data verified November 6, 2026 · Dataset 2026-11-06
Side by side
DeepSeek-V4.1-Flash and Inkling 2 Small, line by line
Prices in effect today, compared at the same tier wherever both list one. The better value in each row is highlighted.
| Fact | DeepSeek-V4.1-Flash | Inkling 2 Small |
|---|---|---|
| Price | ||
| Price per 1M input tokens | $0.30 | $0.30 |
| Price per 1M output tokens | $1.20 | $1 (better) |
| Independent benchmarks | ||
| Arena Text | 1476 Elo (#22 of 52) | Not measured |
| Arena WebDev | 1665 Elo (#13 of 46) | Not measured |
| GPQA Diamond | 93.2% (#16 of 41) | Not measured |
| FrontierMath Tiers 1-3 (v2) | 71.2% (#23 of 41) | Not measured |
| SimpleQA Verified | 42.5% (#27 of 38) | Not measured |
| Specs | ||
| Provider | DeepSeek | Thinking Machines Lab |
| Release date | September 10, 2026 | November 5, 2026 |
| Access | API and open weights | API only |
| Context window | 1,000,000 tokens | 262,144 tokens |
| Max output | 384,000 tokens | Not reported |
| Input | text, image | text, image |
| Output | text | text |
No independent benchmark has scored both models yet. Each rank counts the current models scored on that benchmark.
Provider results
What the labs report
Results tables a lab published with one of its models, where it lists both DeepSeek-V4.1-Flash and Inkling 2 Small. These are the lab's own figures, not independent measurements, and each table is read on its own: labs run benchmarks with different harnesses and budgets.
Thinking Machines Lab, Inkling 2 Small model card, November 5, 2026Thinking Machines Lab · 2026-11-06
| Benchmark | DeepSeek-V4.1-Flash | Inkling 2 Small |
|---|---|---|
| DeepSWE v1.1 | 77.0% (better) | 72.1% |
| Vibe Code Bench v1.1 | 87.7% (better) | 81.6% |
| SWE-Marathon v1.1 | 40.0% (better) | 38.8% |
| SWE-bench Multilingual | 82.9% (better) | 81.2% |
| SWE-bench Verified | 84.6% (better) | 82.2% |
| PostTrainBench v1.2 | 30.5% | 31.9% (better) |
| MCP Atlaspublic set | 83.2% | 85.0% (better) |
| Finance Agent v2.1 | 62.9% | 67.5% (better) |
| Excel Modeling Benchmark v1.1 | 69.2% | 69.5% (better) |
| Tax Agent Bench | 74.9% (better) | 65.8% |
| APEX-Accounting v1.1pass@1 | 12.5% | 14.5% (better) |
| APEX-Accounting v1.1mean score | 59.3% | 62.0% (better) |
| Diligence Benchbest harness | 50.4% | 58.1% (better) |
| Harvey LAB v1.1 | 14.2% | 21.7% (better) |
| Legal Research Bench | 45.2% | 46.6% (better) |
| PerceptionBench | 47.7% | 64.7% (better) |
| BabyVisionwith Python | 92.5% | 93.7% (better) |
| CharXiv (RQ) | 77.0% | 85.6% (better) |
| CharXiv (RQ)with Python | 85.6% | 87.7% (better) |
| Chartography | 17.9% | 36.7% (better) |
| Chartographywith Python | 83.0% (better) | 80.4% |
| GPQA-Diamond | 92.2% | 93.0% (better) |
| LongBench v2 | 69.0% | 70.6% (better) |
| ComplexConstraints v1.0 | 50.4% (better) | 44.5% |
| PatchEval | 80.4% (better) | 79.6% |
Thinking Machines' table from the Inkling 2 Small model card, run at effort 0.99 (xhigh) with a 1M-token trajectory limit; where a benchmark's owner publishes scores (Datacurve, Scale AI, Surge, Mercor, Thoughtful, Vals), Thinking Machines uses them. DeepSeek-V4.1-Flash is the 1017 build. Left out here: the Artificial Analysis and Vals indexes, the rows Artificial Analysis ran (FrontierCode, Terminal-Bench, GDP.pdf, MMMU-Pro, HLE, CritPt, AA-LCR, AA-Omniscience, AutomationBench, EnterpriseOps-Gym, Tau 3 Banking), Arena and DesignArena ratings, PMPP-Hard (not a percentage), the safety rows, and JobBench, DAYJOB and Humanity's Sixth Sense, which we could not confirm are public.
Charts
Against every current text model
Where DeepSeek-V4.1-Flash and Inkling 2 Small land among the current models of their task, on every independent benchmark, on price and on context.
Where each stands
Only DeepSeek-V4.1-Flash has a current Arena Text score: #22 of 52. Each bar is the share of current models it beats.
Independent benchmarks
Arena Text
DeepSeek-V4.1-Flash:#22of 52
1,476 Elo · ahead of 57%
Inkling 2 Small: Not scored
Arena WebDev
DeepSeek-V4.1-Flash:#13of 46
1,665 Elo · ahead of 73%
Inkling 2 Small: Not scored
GPQA Diamond
DeepSeek-V4.1-Flash:#16of 41
93.2% · ahead of 63%
Inkling 2 Small: Not scored
FrontierMath Tiers 1-3 (v2)
DeepSeek-V4.1-Flash:#23of 41
71.2% · ahead of 45%
Inkling 2 Small: Not scored
SimpleQA Verified
DeepSeek-V4.1-Flash:#27of 38
42.5% · ahead of 30%
Inkling 2 Small: Not scored
Price and context
Price per 1M input tokens
DeepSeek-V4.1-Flash:#11of 58
$0.30 · cheaper than 75%
Inkling 2 Small:#11of 58
$0.30 · cheaper than 75%
Price per 1M output tokens
DeepSeek-V4.1-Flash:#11of 58
$1.20 · cheaper than 77%
Inkling 2 Small:#10of 58
$1 · cheaper than 84%
Context window
DeepSeek-V4.1-Flash:#27of 67
1M tokens · longer than 24%
Inkling 2 Small:#57of 67
262K tokens · longer than 12%
Quality against price
DeepSeek-V4.1-Flash scores 1,476 at $0.525 (blended price per 1M tokens). The line joins the current models no other beats on both price and Arena Text score; hover any point to name it.
Quality against price: the data
| Model | Provider | Blended price per 1M tokens | Arena Text (Elo) |
|---|---|---|---|
| Gemini 4 Carbon | $4 | 1,528 | |
| Gemini 4 Argon | $4 | 1,520 | |
| Claude Opus 5.5 | Anthropic | $8 | 1,509 |
| Muse Wonder | Meta | $8 | 1,507 |
| Claude Fable 5 | Anthropic | $20 | 1,504 |
| Claude Fable 5.1 | Anthropic | $20 | 1,504 |
| Gemini 3.8 Flash | $1.50 | 1,496 | |
| Muse Spark 1.3 | Meta | $2 | 1,495 |
| Claude Opus 5 | Anthropic | $10 | 1,492 |
| Kimi K3 | Moonshot Kimi | $6 | 1,488 |
| GPT-5.6 Sol | OpenAI | $8 | 1,485 |
| Gemini 3.6 Flash | $3 | 1,483 | |
| GPT-5.5 | OpenAI | $11 | 1,482 |
| Claude Opus 4.8 | Anthropic | $10 | 1,482 |
| Qwen3.8-Max | Alibaba Qwen | $3 | 1,482 |
| GPT-6.1 Sol | OpenAI | $4 | 1,481 |
| GLM-5.3 | Z.ai | $2.15 | 1,481 |
| MiMo-V2.6-Pro | Xiaomi MiMo | $0.54 | 1,480 |
| Claude Sonnet 5.5 | Anthropic | $4 | 1,477 |
| GLM-5.3-Flash | Z.ai | $0.24 | 1,477 |
| GPT-6 Astra | OpenAI | $20 | 1,476 |
| DeepSeek-V4.1-Flash | DeepSeek | $0.52 | 1,476 |
| GPT-5.4 | OpenAI | $5.63 | 1,475 |
| Gemini 3 Flash Preview | $1.13 | 1,473 | |
| Grok 4.20 | xAI | $1.56 | 1,472 |
| GPT-5.6 Terra | OpenAI | $4.50 | 1,467 |
| Grok 4.5 | xAI | $3 | 1,465 |
| DeepSeek-V4-Pro | DeepSeek | $1.98 | 1,465 |
| Claude Sonnet 5 | Anthropic | $4 | 1,462 |
| GPT-6 Sol | OpenAI | $4 | 1,458 |
| Gemini 3.5 Flash-Lite | $0.85 | 1,456 | |
| Grok 4.6 | xAI | $3 | 1,455 |
| GPT-5.6 Luna | OpenAI | $0.45 | 1,453 |
| MiMo-V2.6-Flash | Xiaomi MiMo | $0.18 | 1,448 |
| Step 5 Preview | StepFun | $1.43 | 1,448 |
| Grok 4.3 | xAI | $1.56 | 1,442 |
| GPT-6 Luna | OpenAI | $0.20 | 1,441 |
| Grok 4.7 | xAI | $3 | 1,441 |
| Mistral Large 4 | Mistral AI | $1.05 | 1,432 |
| Claude Haiku 5.5 | Anthropic | $0.20 | 1,425 |
| GPT-4.1 | OpenAI | $3.50 | 1,415 |
| Solar Pro 4 | Upstage | $0.52 | 1,388 |
| GPT-4.1 mini | OpenAI | $0.70 | 1,383 |
| GPT-4.1 nano | OpenAI | $0.18 | 1,322 |
Cost
What each costs
Example workloads at each provider's listed rates, then every other rate either one lists. The cheaper figure in each row is highlighted.
The same work, priced
For 10M input and 2M output tokens, DeepSeek-V4.1-Flash costs 1.1 times as much as Inkling 2 Small, at each provider's listed rates.
10M input and 2M output tokens
DeepSeek-V4.1-Flash costs 1.1× as much
- DeepSeek-V4.1-Flash
- $5.40
- Inkling 2 Small
- $5
The same, with 9M of the input tokens cached
DeepSeek-V4.1-Flash costs 1.1× as much
- DeepSeek-V4.1-Flash
- $2.75
- Inkling 2 Small
- $2.57
| Workload or rate | DeepSeek-V4.1-Flash | Inkling 2 Small |
|---|---|---|
| Example workloads | ||
| 10M input and 2M output tokens | $5.40 | $5 (better) |
| The same, with 9M of the input tokens cached | $2.75 | $2.57 (better) |
| Other listed rates | ||
| 1M input tokens, cached | $0.006 (better) | $0.03 |
| 1M input tokens, off peak | $0.15 | Not listed |
| 1M output tokens, off peak | $0.60 | Not listed |
| 1M input tokens, off-peak, cached | $0.003 | Not listed |
Your own bill will differ. These figures use list prices and example workloads. The AI Model Cost Audit reviews your real usage, shortlists models that score as well for each task for less, and estimates the savings.
Launch price $100, regular price $150
Verdict
When to choose each
DeepSeek-V4.1-Flash
Where it leads
- Larger context window 1,000,000 vs 262,144 tokens
- Open weights you can run yourself
- Cheaper cached input, $0.006 vs $0.03 per 1M tokens
Best for
- High-volume agent and multimodal workloads where per-token cost dominates
- Teams that want a frontier-adjacent model they can also self-host under MIT terms
Watch out for
- The recorded API rates are the peak-hour prices; DeepSeek charges half outside 01:00-04:00 and 06:00-10:00 UTC on weekdays
- Running the open weights moves cost to your own infrastructure, which the token rates here do not represent
- Epoch AI and Arena WebDev scored build 1017, which the API serves; Arena Text has rated only the September build so far
Inkling 2 Small
Where it leads
- Lower price per 1M output tokens, $1 vs $1.20
Best for
- Agentic coding and office, finance and legal work at a low per-token price
- Teams that want to post-train their own variant on Tinker
Watch out for
- Closed weights for now: Thinking Machines says it will publish the full weights under Apache 2.0 the week after launch, once external safety testing ends; until then Tinker is the only way to use it
- Tinker serves it with a 64K or 256K context, although the model card lists up to 1M tokens
- In its lab's own table DeepSeek-V4.1-Flash scores higher on DeepSWE v1.1 (77.0% against 72.1%) and Claude Haiku 5.5 on Vibe Code Bench (90.4% against 81.6%); Thinking Machines also says it is less tuned for chat, and no independent benchmark score is recorded here yet
From benchmark to production
Building on DeepSeek-V4.1-Flash or Inkling 2 Small?
Public scores rarely hold on your own data. We test both models on your real tasks, then build the agent or pipeline around the one that wins.
AI Model Cost AuditLaunch price $100, regular price $150What the audit includes
FAQ
DeepSeek-V4.1-Flash vs Inkling 2 Small FAQ
Which is cheaper, DeepSeek-V4.1-Flash or Inkling 2 Small?
Both cost $0.30 per 1M input tokens. For 10M input and 2M output tokens, DeepSeek-V4.1-Flash costs $5.40 and Inkling 2 Small $5 at standard rates.
Which is cheaper with prompt caching, DeepSeek-V4.1-Flash or Inkling 2 Small?
DeepSeek-V4.1-Flash charges $0.006 per 1M cached input tokens, 98% below its standard input rate, and Inkling 2 Small $0.03, 90% below. With 9M of 10M input tokens cached and 2M output tokens, DeepSeek-V4.1-Flash costs $2.75 and Inkling 2 Small $2.57.
How do DeepSeek-V4.1-Flash and Inkling 2 Small compare in Thinking Machines Lab's own results?
In the Inkling 2 Small model card (November 5, 2026), DeepSeek-V4.1-Flash leads on DeepSWE v1.1, 77.0% to 72.1%; DeepSeek-V4.1-Flash leads on Vibe Code Bench v1.1, 87.7% to 81.6%; DeepSeek-V4.1-Flash leads on SWE-Marathon v1.1, 40.0% to 38.8%. These are Thinking Machines Lab's figures, not independent measurements.
Which has the larger context window, DeepSeek-V4.1-Flash or Inkling 2 Small?
DeepSeek-V4.1-Flash has the larger context window, 1,000,000 vs 262,144 tokens.
Can I run DeepSeek-V4.1-Flash or Inkling 2 Small myself?
DeepSeek-V4.1-Flash is released as open weights you can run yourself; Inkling 2 Small is available through its provider's API only.
Further reading
More on DeepSeek-V4.1-Flash and Inkling 2 Small
Articles on DeepSeek-V4.1-Flash and Inkling 2 Small
- DeepSeek V4.1 Flash 1017: What Changed and Why Chips FellOctober 19, 2026
Related comparisons
- Claude Haiku 5.5 vs DeepSeek-V4.1-Flash
- Claude Haiku 5.5 vs Inkling 2 Small
- DeepSeek-V4.1-Flash vs GPT-6 Luna
- Gemini 3.5 Flash-Lite vs Inkling 2 Small
- DeepSeek-V4.1-Flash vs GPT-6 Sol
- Gemini 3.8 Flash vs Inkling 2 Small
- Claude Sonnet 5 vs DeepSeek-V4.1-Flash
- GLM-5.3-Flash vs Inkling 2 Small
- DeepSeek-V4.1-Flash vs DeepSeek-V4-Pro
- GLM-5.3 vs Inkling 2 Small
- DeepSeek-V4.1-Flash vs Gemini 3.7 Flash
- GPT-6 Luna vs Inkling 2 Small
Production evaluation
Choosing between DeepSeek-V4.1-Flash and Inkling 2 Small?
Public benchmarks narrow the shortlist. We run both on your own tasks, data and cost limits, then build the routing and review controls to run the winner in production.
- A head-to-head evaluation on your real workload
- Routing between models by cost and difficulty