Inkling: Benchmarks, Pricing & Context Window
Inkling is a language model from Unknown Organization, released in July 2026, with multimodal input, a 524K-token context window, and pricing from $0.950/M input, $0.160/M cached input, $4.05/M output.
Inkling is a general-purpose multimodal model that accepts text, image and audio inputs and generates text outputs.
Inkling benchmarks
Capability tiers
Standing within each category, adjusted for leaderboard depth.
Real tasks performance
High-confidence performance for Inkling across real-world prompt categories. Only 95% intervals at most 4 points wide are shown.
Performance by conversation depth
How Inkling holds up as conversations get longer.
Quality Tracker
Inkling Performance Across Datasets
Scores sourced from the model's scorecard, paper, or official blog posts
llm-stats.com - Wed Sep 09 2026Inkling pricing
Providers
Inkling starts at $0.950 per million input tokens and $4.05 per million output tokens via DeepInfra. Reused prompt prefixes cost $0.160 per million cached input tokens.
| Provider | Input $/M | Cached input $/M | Output $/M | Context in / out | TTFT p95 s | Output p5 c/s | Modalities in / out |
|---|---|---|---|---|---|---|---|
 DeepInfra | $0.950 | $0.160 | $4.05 | 524.3K/524.3K | — | — | / |
Cached input is the discounted price for prompt tokens served from a provider cache. TTFT is time to first token. Output is characters per second; p5 is the sustained floor exceeded by 95% of observed requests.
Inkling model size
Inkling has 975 billion parameters. See how it compares to other models in the same parameter range.
Inkling context window
Input and output token limits for Inkling, plus how it ranks on long-context understanding.
Try now
huggleMake it with
Inkling.
Inkling latency
Inkling time to first token, sustained output throughput, and failed-request rate from live model usage over the trailing 7 days.
Inkling examples
Recent arena outputs from Inkling, picked from the highest-ranked matchups.
Inkling license
Inkling is released under the Apache 2.0 license, which permits commercial use, has 975.0B parameters.
- License
- Apache 2.0
- Commercial use allowed
- Parameters
- 975.0B
Apache License 2.0 - allows commercial use
Inkling resources
Official sources for Inkling: provider documentation, model weights.
Inkling vs other models
The most-compared alternatives to Inkling are Nova 2 Pro, Gemma 4 26B-A4B, Qwen3.7-Plus. Open any pair side-by-side for benchmarks, pricing, context, and latency.
Models like Inkling
Models ranked just above and below Inkling by LLM Stats score.
FAQ
Common questions about Inkling.