DeepSeek V4.1 Flash vs Inkling Small
At a Glance
| Compare |  DeepSeek V4.1 FlashDeepSeek |  Inkling SmallThinking Machines Lab |
|---|---|---|
| Intelligence, Cost, and Efficiency | ||
| IntelligenceHigher is better · MM Intelligence v4.4 | #8 of 5783.3 score · 2/3 sources · provisional · missing LMArena Text · full-core range 55.5–88.8 | #31 of 5735.2 score · 2/3 sources · provisional · missing LiveBench · full-core range 23.5–56.8 |
| CostLower is better · Published-token output estimate | #6 of 27$0.022 per LiveBench case | UnrankedNot in the 27-model eligible cohort |
| EfficiencyHigher is better · MM Efficiency v1.9 | #1 of 2771.7 score · 2/3 sources · provisional · missing LMArena Text · full-core range 57.8–74.5 | UnrankedNot in the 27-model eligible cohort |
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $0.15DeepSeek ↗ · Sep 10, 2026 | $0.45Deepinfra ↗ · Oct 19, 2026 |
| Output priceFrom · USD / 1M tokens | $0.60Deepinfra ↗ · Oct 19, 2026 | $1.20Deepinfra ↗ · Oct 19, 2026 |
| Context windowMaximum documented tokens | 1,049K | 1,049K |
| Model facts checked | Sep 10, 2026View model evidence → | Sep 25, 2026View model evidence → |
Token prices are the lowest available sourced USD rates; input and output may use different providers. Cost ranking estimates output spend on LiveBench, not a full request bill. Ranking methodology →
Available Benchmarks
| Benchmark | DeepSeek-V4.1-Flash | Inkling-Small |
|---|---|---|
| ARC-AGI-1verified-v1-613c385b0c93 · verified_score · leader | 94.50100% of row best · percent · DeepSeek V4.1 Flash (Max) | 84.0089% of row best · percent · Inkling Small (XHigh) |
| ARC-AGI-2verified-v2-be40992860f9 · verified_score · leader | 72.92100% of row best · percent · DeepSeek V4.1 Flash (Max) | 40.1455% of row best · percent · Inkling Small (XHigh) |
| Overall ResultCounted from the protocol-matched rows above | 2 benchmark winsNo overall winner | 0 benchmark winsNo overall winner |
Third-party benchmark Only like-for-like primary-publisher results are shown; raw scores, relative scores, configuration, and token spend remain visible.
Side-by-Side Facts
| Field | DeepSeek-V4.1-Flash | Inkling-Small |
|---|---|---|
| Developer | DeepSeek | Thinking Machines Lab |
| Family | Deepseek V4 1 | Inkling |
| Model | DeepSeek-V4.1-Flash | Inkling-Small |
| Version | DeepSeek-V4.1-Flash | Inkling-Small |
| Lifecycle | active | active |
| Released | 2026-09-10 | 2026-07-30 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text, Image | Text, Image, Audio |
| Output modalities | Text | Text |
| Context window | 1,049K | 1,049K |
| Total parameters | 763.2B | 276B |
| Active parameters | Unknown | 12B |
| License | mit | apache-2.0 |
| Open weights | Yes | Yes |
| API available | Yes | Yes |
| Self-hostable | Yes | Yes |
| Provider access | DeepSeek (Standard), Deepinfra (Standard), Together Ai (Standard) | Deepinfra (Standard), Openrouter (Standard) |
| Capabilities | agents, chat, fim, generation, reasoning, responses, structured_outputs, tools, vision | agents, chat, coding, generation, reasoning, tools, vision |
| Architecture design | Causal Encoder-Decoder (20 encoder + 20 decoder layers) | Unknown |
| Backbone parameters | 552000000000 parameters | Unknown |
| Active parameters during decode | 16000000000 parameters | Unknown |
| Active parameters during prefill | 8000000000 parameters | Unknown |
| Pre-training corpus | 45000000000000 tokens | Unknown |
| Reasoning effort range | 1–100 | Unknown |
| Routed experts per MoE layer | 384 experts | Unknown |
| Routed experts per token | 6 experts | Unknown |
| Transformer layers | 40 layers | Unknown |
DeepSeek V4.1 Flash Capabilities
Inkling Small Capabilities
Related Comparisons
All image comparisons →| A | Pair | B | Context |
|---|---|---|---|
DeepSeek-V4-FlashDeepSeek | vs | DeepSeek-V4.1-FlashDeepSeek | family variantstext |
 MiniMax-M3MiniMax | vs | DeepSeek-V4.1-FlashDeepSeek | cross-developer peersimage, text |
DeepSeek-V4-Flash-BaseDeepSeek | vs | DeepSeek-V4.1-FlashDeepSeek | family variantstext |
DeepSeek-V4-ProDeepSeek | vs | DeepSeek-V4.1-FlashDeepSeek | family variantstext |
DeepSeek-V4.1-FlashDeepSeek | vs |  GPT-6.1 SolOpenAI | cross-developer peersimage, text |
DeepSeek-V4.1-FlashDeepSeek | vs | Grok 4.7xAI | cross-developer peersimage, text |
DeepSeek-V4.1-FlashDeepSeek | vs |  MiMo-V2.6-ProXiaomi | cross-developer peersimage, text |
 Command A ReasoningCohere | vs | DeepSeek-V4.1-FlashDeepSeek | cross-developer peerstext |
DeepSeek-V4-Flash-Vision-ExpDeepSeek | vs | DeepSeek-V4.1-FlashDeepSeek | family variantsimage, text |
DeepSeek-V4.1-FlashDeepSeek | vs |  Gemma 4 26B-A4BGoogle DeepMind | cross-developer peersimage, text |
DeepSeek-V4.1-FlashDeepSeek | vs |  Kimi-K2.5Moonshot AI | cross-developer peersimage, text |
DeepSeek-V4.1-FlashDeepSeek | vs | GPT-5.4OpenAI | cross-developer peersimage, text |
Primary Evidence
Sources and Freshness
Questions
DeepSeek V4.1 Flash vs Inkling Small FAQs
Is DeepSeek V4.1 Flash or Inkling Small better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both DeepSeek V4.1 Flash and Inkling Small, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, DeepSeek V4.1 Flash or Inkling Small?+
DeepSeek V4.1 Flash is $0.15 and Inkling Small is $0.45 per million tokens, so DeepSeek V4.1 Flash is cheaper on this metric. DeepSeek V4.1 Flash is $0.60 and Inkling Small is $1.20 per million tokens, so DeepSeek V4.1 Flash is cheaper on this metric.
Which has a larger context window, DeepSeek V4.1 Flash or Inkling Small?+
Both models have the same sourced context window: 1,048,576 tokens each.
Which performs better in benchmarks, DeepSeek V4.1 Flash or Inkling Small?+
There is no overall benchmark winner: An overall winner requires at least two decisive benchmarks from at least two original publishers.
Can DeepSeek V4.1 Flash or Inkling Small be self-hosted?+
Both models have the same sourced self-hosting status: supported. DeepSeek V4.1 Flash is open weight; Inkling Small is open weight.
Can DeepSeek V4.1 Flash and Inkling Small understand images?+
DeepSeek V4.1 Flash is documented with image input; Inkling Small is documented with image input. This reflects supported input modalities, not vision quality.
Which can generate longer answers, DeepSeek V4.1 Flash or Inkling Small?+
DeepSeek V4.1 Flash has a sourced maximum output of 393,216 tokens; Inkling Small's maximum output is not reported. A larger limit cannot be determined.
Do DeepSeek V4.1 Flash and Inkling Small support reasoning and tool use?+
DeepSeek V4.1 Flash: reasoning, tool calling, and image input. Inkling Small: reasoning, tool calling, and image input. Feature support does not establish relative quality.
Which is available from more inference providers, DeepSeek V4.1 Flash or Inkling Small?+
DeepSeek V4.1 Flash has 3 sourced provider routes; Inkling Small has 2, so DeepSeek V4.1 Flash has broader tracked availability.
Which offers better value, DeepSeek V4.1 Flash or Inkling Small?+
There is no universal value winner. Compare the input and output prices above with the matched benchmark result for your workload: cheaper tokens can be offset by different quality, token usage, latency, or provider availability.