Context
1M
Max output
33K
Serving providers
6
Cheapest input
$0.95 /1M
On-demand listed rates, OpenRouter routed quotes and Vercel reseller quotes. Enterprise commitments (committed-use discounts, provisioned throughput, negotiated rates) can be materially lower.
Benchmarks
independent evaluations · source: Artificial Analysis and Hugging Face leaderboardsSpeed & latency
Output speed
186 t/s
tokens / second
Time to first token
1.91s
latency
Headline indices
Individual benchmarks · click a row for effort variants
| Benchmark | Best score | Effort | Cost / task | |||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| Aa Analyst Agent | 0.2 | default | — | |||||||||||||||||
| AIME 2026 | 97% | default | — | |||||||||||||||||
| Automation Bench | 0.0 | default | — | |||||||||||||||||
| CritPt | 5% | default | — | |||||||||||||||||
| EvalComputeProxyFrozen Aug 18, 2026 | 2835.8 | default | — | |||||||||||||||||
| GDPval v2Frozen Aug 18, 2026 | 1238.7 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| GPQA Diamond | 87% | default | — | |||||||||||||||||
| Harvey Lab | 0 | default | — | |||||||||||||||||
| Humanity's Last Exam | 32% | default | — | |||||||||||||||||
| Long-Context Reasoning | 77% | default | — | |||||||||||||||||
| Mlcr OverallFrozen Sep 9, 2026 | 0.1 | default | — | |||||||||||||||||
| MMMU-Pro | 73% | default | — | |||||||||||||||||
| Omniscience | 2 | default | — | |||||||||||||||||
| Omniscience Accuracy | 0.4 | default | — | |||||||||||||||||
| Omniscience Non Hallucination | 0.3 | default | — | |||||||||||||||||
| SciCode | 47% | default | — | |||||||||||||||||
| SWE-bench Pro | 54% | default | — | |||||||||||||||||
| SWE-bench Verified | 78% | default | — | |||||||||||||||||
| Terminal Bench40 | 0.0 | default | — | |||||||||||||||||
| ||||||||||||||||||||
| TerminalBench v2.1 | 55% | default | — | |||||||||||||||||
| ||||||||||||||||||||
| τ-bench Banking | 29% | default | — | |||||||||||||||||
Artificial Analysis last published scores for this benchmark on Sep 9, 2026. Scores here are frozen at that date, and models released since are not on it.
Artificial Analysis last published scores for this benchmark on Aug 18, 2026. Scores here are frozen at that date, and models released since are not on it.
Pricing by serving provider
standard tier · per 1M tokens · click a provider to expandInput pricing runs from $0.95 to $1.00 per 1M tokens across 6 providers, so the dearest route costs 5% more than the cheapest for the same model.
| Serving provider | Input /1M | Output /1M | Endpoints | |||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| DeepInfraCheapest | $0.95 | $4.05 | 1 | |||||||||||||
Standarddeepinfra/thinkingmachines/Inkling
| ||||||||||||||||
| Baseten | $1.00 | $4.05 | 1 | |||||||||||||
Standardbaseten/thinkingmachines/inkling
| ||||||||||||||||
| Fireworks AI | $1.00 | $4.05 | 1 | |||||||||||||
Standardfireworks_ai/accounts/fireworks/models/inkling
| ||||||||||||||||
| OpenRouter | $1.00 | $4.05 | 1 | |||||||||||||
Standardthinkingmachines/inkling
| ||||||||||||||||
| Together AI | $1.00 | $4.05 | 1 | |||||||||||||
Standardtogether_ai/thinkingmachines/Inkling
| ||||||||||||||||
| VercelVercel reseller quote | $1.00 | $4.05 | 1 | |||||||||||||
Standardthinkingmachines/inkling
| ||||||||||||||||
| OpenRouter (batch) | $1.00 | $4.05 | 1 | |||||||||||||
Batchthinkingmachines/inkling:batch
| ||||||||||||||||
| OpenRouter (free) | Free tier only | — | 1 | |||||||||||||
Freethinkingmachines/inkling:free
| ||||||||||||||||
Price history
listed seller prices, input and output per 1M tokens Input Output
Input down 5% since first tracked
Cost calculator
estimate your monthly spend on this model$514
estimated / month
Model IDs
copy the exact identifier for your platformthinkingmachines/inkling:freedeepinfra/thinkingmachines/Inklingthinkingmachines/inkling:batchtogether_ai/thinkingmachines/Inklingfireworks_ai/accounts/fireworks/models/inklingthinkingmachines/inklingthinkingmachines/inklingbaseten/thinkingmachines/inkling
Frequently asked questions
Inkling pricing, context and availabilityHow much does Inkling cost?
Inkling costs $0.95 per 1M input tokens from DeepInfra, and $4.05 per 1M output tokens from Baseten. Across 6 serving providers, input prices range from $0.95 to $1.00 per 1M tokens.
What is the context window of Inkling?
Inkling accepts up to 1M tokens of context and can return up to 33K output tokens.
Which providers serve Inkling?
Inkling is available from 6 serving providers, each with its own pricing and model ID. DeepInfra is currently the cheapest.
What can Inkling do?
Inkling supports image input (vision), tool use, reasoning, prompt caching and structured output.
Other Thinking Machines models
compare pricing across the Thinking Machines lineupPopular comparisons
head-to-head pages featuring Inkling
Inkling vs Claude Fable 5.1side-by-side pricing & benchmarks Inkling vs Claude Opus 5side-by-side pricing & benchmarks
Inkling vs DeepSeek V4.1 Flashside-by-side pricing & benchmarks Inkling vs DeepSeek V4 Pro 0423side-by-side pricing & benchmarks
Inkling vs Gemini 3.7 Flashside-by-side pricing & benchmarks Listed prices from LiteLLM, OpenRouter and Vercel · last checked Oct 14, 2026
Every weekday
AI moves fast. Here's your debrief.
News, analysis, tools, and more.
For people who build with AI