Llama 4 Maverick 17B 128E Instruct vs Inkling Small
At a Glance
| Compare |  Inkling SmallThinking Machines Lab | |
|---|---|---|
| Intelligence, Cost, and Efficiency | ||
| IntelligenceHigher is better · MM Intelligence v4.4 | #43 of 570.0 score · 1/3 sources · single-source provisional · missing LiveBench, ARC-AGI-2 · full-core range 0.0–66.7 | #31 of 5735.2 score · 2/3 sources · provisional · missing LiveBench · full-core range 23.5–56.8 |
| Pricing and Limits | ||
| Input priceFrom · USD / 1M tokens | $0.1875Openrouter ↗ · Oct 19, 2026 | $0.45Deepinfra ↗ · Oct 19, 2026 |
| Output priceFrom · USD / 1M tokens | $0.6525Openrouter ↗ · Oct 19, 2026 | $1.20Deepinfra ↗ · Oct 19, 2026 |
| Context windowMaximum documented tokens | 1,000K | 1,049K |
| Model facts checked | Aug 28, 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 | Llama-4-Maverick-17B-128E-Instruct | Inkling-Small |
|---|---|---|
| LMArena Text Arenatext-2026-10-15-a64ca3b12b6e · arena_rating · leader | 1,287.1991% of row best · rating · llama-4-maverick-17b-128e-instruct; 95% CI [1282.93484207, 1291.44351277]; votes 39450; rank 261 | 1,412.62100% of row best · rating · Inkling Small; 95% CI [1407.97725962, 1417.26957820]; votes 32304; rank 135 |
| LMArena Vision Arenavision-2026-10-09-a64ca3b12b6e · arena_rating · leader | 1,141.6392% of row best · rating · llama-4-maverick-17b-128e-instruct; 95% CI [1132.58229133, 1150.67926500]; votes 6922; rank 120 | 1,235.32100% of row best · rating · Inkling Small; 95% CI [1226.97211879, 1243.66134454]; votes 7472; rank 75 |
| Overall ResultCounted from the protocol-matched rows above | 0 benchmark winsNo overall winner | 2 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 | Llama-4-Maverick-17B-128E-Instruct | Inkling-Small |
|---|---|---|
| Developer | Meta | Thinking Machines Lab |
| Family | Llama 4 Maverick 17b 128e Instruct | Inkling |
| Model | Llama-4-Maverick-17B-128E-Instruct | Inkling-Small |
| Version | Llama-4-Maverick-17B-128E-Instruct | Inkling-Small |
| Lifecycle | active | active |
| Released | 2025-04-05 | 2026-07-30 |
| Knowledge cutoff | Unknown | Unknown |
| Input modalities | Text, Image | Text, Image, Audio |
| Output modalities | Text | Text |
| Context window | 1,000K | 1,049K |
| Total parameters | 401.6B | 276B |
| Active parameters | 17B | 12B |
| License | other | apache-2.0 |
| Open weights | Yes | Yes |
| API available | Yes | Yes |
| Self-hostable | Yes | Yes |
| Provider access | Openrouter (Standard) | Deepinfra (Standard), Openrouter (Standard) |
| Capabilities | chat, generation, tools | agents, chat, coding, generation, reasoning, tools, vision |
Llama 4 Maverick 17B 128E Instruct Capabilities
Inkling Small Capabilities
Related Comparisons
All image comparisons →| A | Pair | B | Context |
|---|---|---|---|
| vs |  Hy4 previewTencent | cross-developer peerstext | |
 DeepSeek-V4-Flash-BaseDeepSeek | vs | cross-developer peerstext | |
DeepSeek-V4-Flash-Vision-ExpDeepSeek | vs | cross-developer peersimage, text | |
| vs | family variantstext | ||
| vs | family variantsimage, text | ||
| vs | family variantsimage, text | ||
| vs |  Mistral Large 3Mistral AI | cross-developer peersimage, text | |
| vs | Mistral-Small-4-119B-2603Mistral AI | cross-developer peersimage, text | |
| vs | cross-developer peerstext | ||
| vs |  GPT-4.1OpenAI | cross-developer peersimage, text | |
| vs | GPT-5.6 SolOpenAI | cross-developer peersimage, text |
Primary Evidence
Sources and Freshness
Questions
Llama 4 Maverick 17B 128E Instruct vs Inkling Small FAQs
Is Llama 4 Maverick 17B 128E Instruct or Inkling Small better for coding?+
This comparison does not currently contain a protocol-matched coding benchmark for both Llama 4 Maverick 17B 128E Instruct and Inkling Small, so Model Markets cannot name a coding leader from pricing, context size, or capability labels alone.
Which is cheaper, Llama 4 Maverick 17B 128E Instruct or Inkling Small?+
Llama 4 Maverick 17B 128E Instruct is $0.1875 and Inkling Small is $0.45 per million tokens, so Llama 4 Maverick 17B 128E Instruct is cheaper on this metric. Llama 4 Maverick 17B 128E Instruct is $0.6525 and Inkling Small is $1.20 per million tokens, so Llama 4 Maverick 17B 128E Instruct is cheaper on this metric.
Which has a larger context window, Llama 4 Maverick 17B 128E Instruct or Inkling Small?+
Inkling Small has the larger sourced context window. Llama 4 Maverick 17B 128E Instruct supports 1,000,000 tokens and Inkling Small supports 1,048,576 tokens.
Which performs better in benchmarks, Llama 4 Maverick 17B 128E Instruct 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 Llama 4 Maverick 17B 128E Instruct or Inkling Small be self-hosted?+
Both models have the same sourced self-hosting status: supported. Llama 4 Maverick 17B 128E Instruct is open weight; Inkling Small is open weight.
Can Llama 4 Maverick 17B 128E Instruct and Inkling Small understand images?+
Llama 4 Maverick 17B 128E Instruct 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, Llama 4 Maverick 17B 128E Instruct or Inkling Small?+
Neither model has a sourced maximum output in this comparison, so a larger limit cannot be determined.
Do Llama 4 Maverick 17B 128E Instruct and Inkling Small support reasoning and tool use?+
Llama 4 Maverick 17B 128E Instruct: 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, Llama 4 Maverick 17B 128E Instruct or Inkling Small?+
Llama 4 Maverick 17B 128E Instruct has 1 sourced provider route; Inkling Small has 2, so Inkling Small has broader tracked availability.
Which offers better value, Llama 4 Maverick 17B 128E Instruct 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.