Skip to content
ModelCap

Head-to-head comparison

Claude Haiku 4.5 vs Inkling Small

Claude Haiku 4.5 (Anthropic) and Inkling Small (Thinking Machines) compared on the ModelCap Index, API price, context window, provider availability, weight access and every public benchmark board they share. Figures are the same ones shown on the live rankings; nothing here is a hidden score.

Snapshot as of 3 September 2026

As of 3 September 2026, Inkling Small holds the stronger ModelCap Index position (#42 vs #45); Inkling Small is 4.2× cheaper per output token ($1.20/1M vs $5.00/1M); Inkling Small offers the longer context window (1M vs 200K tokens); and Inkling Small ships open weights.

Which should you choose?

Choose Claude Haiku 4.5 if…

  • you want provider choice — 4 listed API providers against 3.
  • Arena coding is your yardstick — 1481 against 1476.

Choose Inkling Small if…

  • you want the stronger overall ModelCap Index position — #42 against #45 (53.9 vs 52.4 points).
  • API cost matters — $1.20/1M output tokens against $5.00/1M, about 4.2× cheaper.
  • your workload is prompt-heavy — input tokens cost $0.45/1M against $1.00/1M.
  • you need the longer context window — 1M tokens against 200K.
  • you want to self-host: Inkling Small ships open weights while Claude Haiku 4.5 is api only.
  • ARC-AGI-2 is your yardstick — 40.1% against 4.0%.
  • you want the more recently listed model — Inkling Small was listed 30 July 2026, Claude Haiku 4.5 15 October 2025.

Claude Haiku 4.5 vs Inkling Small: specs, pricing and context

Specification comparison of Claude Haiku 4.5 and Inkling Small
FieldClaude Haiku 4.5AnthropicInkling SmallThinking Machines
ModelCap Index position#45#42
Index score52.453.9
EvidenceMeasuredMeasured
Input price / 1M tokens$1.00$0.45
Output price / 1M tokens$5.00$1.20
Context window200K tokens1M tokens
Max output tokens64K262K
API providers listed43
Weight accessAPI onlyOpen weights
Input modalitiesText, Image, FileText, Image, Audio
First listed15 October 202530 July 2026
PublisherAnthropicThinking Machines

Evidence: 3 public benchmark observations across 3 boards · 5 public benchmark observations across 5 boards. Prices are the lowest listed API offer per million tokens observed on the OpenRouter catalogue.

Benchmark scores: Claude Haiku 4.5 vs Inkling Small

Public benchmark boards where Claude Haiku 4.5 or Inkling Small has a published result
BoardClaude Haiku 4.5Inkling SmallLeads
Arena codingArena (LMArena)14811476–148514761467–1486Claude Haiku 4.5
LMArena AgentLMArena—-5.3%-7.1%–-3.5%Only one result
ARC-AGI-2ARC Prize Foundation4.0%Thinking40.1%X-HighInkling Small
AA Intelligence IndexArtificial Analysis—41.2intelligence-indexOnly one result
AA Terminal-Bench 2.1Artificial Analysis—55.1%terminal-bench-2.1Only one result
AA Humanity's Last ExamArtificial Analysis—33.3%humanitys-last-examOnly one result

Scores are the sources' own published figures for each model's best evaluated configuration; ModelCap never re-runs a benchmark.

Want a different pairing? Open the interactive comparison tool to swap either model for any current ranked language model.

Claude Haiku 4.5 vs Inkling Small: common questions

Is Claude Haiku 4.5 better than Inkling Small?

Inkling Small ranks higher on the ModelCap Index as of 3 September 2026: #42 against #45. That is a capability ranking built from public benchmark evidence with published uncertainty; whether it is "better" for you also depends on price, context and where you can run it.

Is Claude Haiku 4.5 cheaper than Inkling Small?

Inkling Small is cheaper on output tokens: $1.20/1M against $5.00/1M. Input tokens are $1.00/1M for Claude Haiku 4.5 and $0.45/1M for Inkling Small. Prices are the lowest listed API offer ModelCap observed, in USD per million tokens.

Which has the bigger context window, Claude Haiku 4.5 or Inkling Small?

Inkling Small has the larger context window: 1M tokens against 200K.

Which is better for coding, Claude Haiku 4.5 or Inkling Small?

Arena coding: Claude Haiku 4.5 1481, Inkling Small 1476 — Claude Haiku 4.5 leads.

Are Claude Haiku 4.5 and Inkling Small open-weight models?

Claude Haiku 4.5: API only. Inkling Small: Open weights. Open weights mean the checkpoint can be downloaded and self-hosted under its licence; API-only models are available solely through hosted endpoints.

Where can I run Claude Haiku 4.5 and Inkling Small?

ModelCap currently lists 4 API providers for Claude Haiku 4.5 and 3 for Inkling Small, from the OpenRouter catalogue snapshot the site serves; each model page lists the providers and their prices.

How current is this Claude Haiku 4.5 vs Inkling Small comparison?

Every figure comes from the sealed ModelCap dataset published 3 September 2026; the page re-renders within a minute of each data refresh, and the ModelCap Index positions are the same ones shown on the live rankings.

Explore further