Model
Inkling
Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
Compare providers (sorted by listed input price)
20 of 21 providers publish a price for Inkling. The cheapest full-context option is NanoGPT at $1/$4.05 per M — 31% below Thinking Machines's own price. Deep Infra lists lower but caps context at 524K.
Best price history
Daily lowest published price across live providers. A lower line is better for the buyer.
- Best input /M
- $0.95unchanged
- Best output /M
- $4.05unchanged
- Provider coverage
- 26
- 24 at the start · 24 snapshots
Published best prices are unchanged.
24 daily snapshots collected from Aug 21, 2026 through Sep 14, 2026. A price chart will appear after the first real move.
Price badge
https://www.vaanalytics.in/badge/thinkingmachines/inkling.svgLive SVG, regenerated on every hourly sync — paste it into a README to always show the current cheapest listed price. Updates when prices change; no build step needed on your side.
Recent changes
Changelog →- contextvia openrouter · Sep 13, 2026
- output: 33K → 472K tokens
- contextvia kilo · Sep 13, 2026
- context: 1.05M → 524K tokens
- output: 33K → 472K tokens
- contextvia openrouter · Sep 10, 2026
- output: 472K → 33K tokens
- contextvia kilo · Sep 10, 2026
- context: 524K → 1.05M tokens
- output: 472K → 33K tokens
- capabilityvia edenai · Sep 7, 2026
- name: Inkling → Inkling (Fireworks AI)
- capabilityvia edenai · Sep 7, 2026
- name: Inkling → Inkling (Deep Infra)
Weights
Standard open-source terms. Commercial use without additional conditions. Weights download without an access request.
licence and gating from the Hugging Face model card ↗ — the card is authoritative, this is a summary
Prices are per million tokens (USD). “—” means the provider does not publicly list a price for this model. Data from models.dev; verify with the provider before purchasing.