Inkling:thinking API
Thinking Machines's Inkling:thinking costs $1 per million input tokens and $4.05 per million output tokens from 1 supplier. Each request through the OpenAI-compatible API goes to the offer with the lowest estimated charge that meets your rules.
- Providers compete for each request. The exchange ranks the offers that meet your rules by estimated charge. It fixes your maximum charge before the first token, and you pay for the tokens that the model uses.
- The OpenAI and Anthropic APIs. Use the OpenAI or Anthropic SDK that you have. Set the base URL and your key, and send inkling:thinking as the model.
- Your data rules. Send x-liquid-retention: none and only offers whose provider does not keep your content compete for the request.
About Inkling:thinking
Inkling:thinking is a language model from Thinking Machines. Its release date is 15 July 2026. Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio. Its weights are open. Its licence is Apache-2.0. It takes text, audio and images and gives text. The largest offer takes 1,040,000 input tokens. It scores 12.5 on the Artificial Analysis Intelligence Index, #48 of 64 scored models on this exchange. It has 1 supplier on this exchange now.
Description, release date and licence: models.dev (https://models.dev/)
Facts
- Model name
- inkling:thinking
- Maker
- Thinking Machines
- Context window
- 1M tokens
- Input price
- $1 per million tokens
- Output price
- $4.05 per million tokens
- Suppliers
- 1 supplier
- Regions
- us
Providers
- Architect: us, declared precision provider-managed, $1 input and $4.05 output per million tokens, $0.17 cache read per million tokens, 1M tokens of context
Scores
- Intelligence: 12.5, #48 of 64
- HLE: 31.9, #102 of 465
- GPQA: 87.2, #82 of 432
- AA-LCR: 77.3, #102 of 409
- SciCode: 47.0, #98 of 178
- SimpleQA Verified: 40.3, #65 of 172
Scores: Artificial Analysis (https://artificialanalysis.ai/)
Scores: Epoch AI, 'Capabilities & Benchmarking' (https://epoch.ai/benchmarks)
Request
curl https://router.inference.ai.exchange/v1/chat/completions \
-H "Authorization: Bearer $LIQUID_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "inkling:thinking",
"messages": [{"role":"user","content":"Say hello."}]
}'Questions
- What is Inkling:thinking?
- Inkling:thinking is a language model from Thinking Machines. Its release date is 15 July 2026. Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio. Its weights are open. Its licence is Apache-2.0.
- How much does Inkling:thinking cost?
- Offers now ask $1 per million input tokens and $4.05 per million output tokens. A job pays for the tokens it uses. The exchange picks the cheapest eligible offer.
- What is the context length of Inkling:thinking?
- The largest offer takes 1,040,000 input tokens. A smaller offer can take less. The exchange skips an offer that cannot take your message.
- What can Inkling:thinking do?
- Its providers list Audio input, Vision, Reasoning effort, JSON object, JSON schema, Frequency penalty, Logit bias, Log probabilities, Min-p sampling, Presence penalty, Repetition penalty, Seed, Stop sequences, Top-k sampling, Top-p sampling, Text, Tools.
- What inputs and outputs does Inkling:thinking support?
- Text · Audio · Images → Text.
- Which providers serve Inkling:thinking?
- It has 1 supplier now, with 1 offer. The table above ranks them by the cost of one agent-mix job.
- How do I call Inkling:thinking?
- Send "inkling:thinking" as the model in an OpenAI or Anthropic request. The API section links to setup steps for each client.
- When was Inkling:thinking released?
- Its creator released it on 15 July 2026.
- When was Inkling:thinking listed?
- The exchange first listed it on 10/10/2026. This is not its release date.