Inkling (256K): API pricing, providers and specs
Inkling (256K) is a text model by Thinking Machines. 11 providers serve it, from $1.50 to $4.68 /1M; the lowest price is at Venice AI.
How Inkling (256K) compares
Against the 737 text models on the site priced the same way.
- Mid-priced: its lowest price is $1.50 /1M against a median of $1.10; 58% of comparable models cost less.
- Its 256K-token context window is larger than 38% of them (median 262K), about 380 pages of text.
- On LMArena's Text board it ranks #12 of the 120 comparable models scored there.
- 11 providers serve it; 78% of comparable models have fewer.
Inkling (256K) prices by provider
Every provider's list price, read from its own price page or API. A price marked “from” changes with context length, resolution or mode.
| Provider | Input | Output | Prompt caching | Context |
|---|---|---|---|---|
 Together AI | — | $0.001/1K chars | $0.17/1K chars | — |
 Venice AI | $0.563/1M | $1.50/1M | $0.125/1M | — |
 Hugging Face | $0.95/1M | From$4.05/1M | — | — |
| Vercel AI Gateway | $1/1M | $4.05/1M | $0.17/1M | 256K |
| OpenRouter | $1/1M | From$4.05/1M | $0.17/1M | 524K |
 Poe | $1.01/1M | $4.09/1M | $0.172/1M | 256K |
| AI/ML API | $1.06/1M | $4.28/1M | $0.18/1M | — |
 Charm Hyper | $1.09/1M | $4.41/1M | $0.185/1M | — |
 Azure | $1.10/1M | From$4.46/1M | $0.19/1M | — |
 Requesty | $1.87/1M | From$4.68/1M | $0.374/1M | 66K |
 Impossibl | $1.87/1M | $4.68/1M | $0.374/1M | — |
- Venice AI$1.50
- Vercel AI Gateway$4.05
- Hugging FaceFrom$4.05
- OpenRouterFrom$4.05
- Poe$4.09
- AI/ML API$4.28
- Charm Hyper$4.41
- AzureFrom$4.46
- Impossibl$4.68
- RequestyFrom$4.68
Specs
- Type
- Text
- Maker
- Thinking Machines
- Inputs
- Image, Text
- Outputs
- Text
- Context
- 256K≈ 380 pages of text
- Max output
- 256K
- Capabilities
- Prompt caching, Reasoning, Tool calling, Vision
- Released
- Jul 15, 2026
- License
- proprietary
- Open weights
- No, API only
- Arena score
- 1442Text
Alternatives to Inkling (256K)
Same kind of model from other makers, at a similar price.
| Model | Lowest price | Context | Arena | Providers |
|---|---|---|---|---|
| Inkling (256K)this model | $1.50/1M | 256K | 1442 | 11 |
 GLM-5.3 | $1.10/1M | 1.05M | 1623 | 49 |
 Qwen3.8 2.4T A95B | $4.11/1M | 1M | — | 22 |
 Gemini 3 Flash | $2.40/1M | 1.05M | 1466 | 5 |
 Mistral Large 4 | $2.09/1M | 1.05M | 1543 | 13 |
 Muse Spark 1.3 | $4.25/1M | 1.05M | 1657 | 11 |
| Qwen3.8 27B | $0.50/1M | 262K | 1591 | 33 |
 Sonar | $1/1M | 127K | — | 9 |
| GLM-5.2 | $1.80/1M | 1M | 1604 | 44 |
More from Thinking Machines
Inkling (256K) FAQ
The lowest price for Inkling (256K) is $1.50 /1M, at Venice AI.
Venice AI, at $1.50 /1M. 11 providers serve Inkling (256K); the table above lists every one with its price.
Inkling (256K) reads up to 256K tokens per request and writes up to 256K.
No. Inkling (256K) is only available through an API; Thinking Machines does not publish its weights.
11 API providers serve Inkling (256K). Compare their prices above, or open a provider to see everything it offers.
Can't find what you're looking for? Contact us