LLM Open Weight

Inkling

by Thinking Machines

Prices last updated November 22, 2026

Thinking Machines Lab's Inkling — multimodal model (text, image, audio input) with a 524K-token context window.

Context
524k
Max Output
262k
Providers
7
Cheapest Input
$0.563
Vision Audio Function Calling Streaming Chat / Instruct

Price Comparison

Compare pricing across 7 providers serving Inkling

Provider Input $/1M Output $/1M Context Speed TTFT Status
Venice AI
Venice AI
$0.563 ● $1.50 524k — — Down
DeepInfra
DeepInfra
$0.950 $4.05 524k — — Live
OpenRouter
OpenRouter
$1.00 $4.05 524k — — Live
Fireworks AI
Fireworks AI
$1.00 $4.05 1.0M — — Live
Together AI
Together AI
$1.00 $4.05 524k — — Down
Infron
Infron
$1.00 $4.05 524k — — Live
Modal
Modal NVFP4
$1.20 $5.00 1.0M — — Live
● Cheapest ● Fastest Prices in USD per 1M tokens

Benchmarks

Independent results for Inkling, as each source publishes them. Where a source tested several versions (effort levels, thinking modes, dated snapshots), the best one is shown and named under "As tested". Scores from different sources use different scales and aren't comparable with each other.

BenchmarkScoreRankAs tested
Overall
One score combining a model's results across many benchmarks, on a common scale.
148.4±1.7
#78 of 258
Inkling
Reasoning
GPQA DiamondEpoch AI
Graduate-level multiple-choice questions in biology, physics and chemistry, written to be hard to look up.
88.3%±3.8
#65 of 232
Inkling_xhigh
Aug 2026
Math
Unpublished research-level maths problems with automatically checkable answers.
33.3%±5.5
#73 of 95
Inkling_xhigh
Aug 2026
FrontierMath's hardest tier: problems that take specialist mathematicians days.
4.9%±5.8
#67 of 77
Inkling_xhigh
Aug 2026
Competition maths problems from the OTIS mock AIME exams (2024-2025).
88.9%±7.7
#74 of 215
Inkling_xhigh
Aug 2026
Coding
Text Arena votes on coding prompts only.
1,494±6
14,203 votes
#96 of 421
Inkling
Nov 2026
Human votes on web apps the models build from a prompt.
1,414±6
17,085 votes
#104 of 161
Inkling
Nov 2026
Knowledge
Short factual questions answered without search, measuring what the model knows and whether it makes things up.
40.3%±3.0
#59 of 97
Inkling_xhigh
Aug 2026
Chat
Text ArenaLMArena
Human votes on chat answers across all kinds of prompts (style-controlled).
1,443±4
54,140 votes
#101 of 426
Inkling
Nov 2026

Epoch AI: Epoch runs each benchmark itself on the models it evaluates, with the same harness for every model. The Epoch Capabilities Index combines many benchmarks into one score. Data: Epoch AI, 'Capabilities & benchmarking', epoch.ai/benchmarks (CC BY 4.0).

LMArena: People compare two anonymous models side by side and vote for the better answer; ratings come from those votes (Bradley-Terry, style-controlled for text and vision). Data: LMArena (arena.ai) leaderboard dataset (CC BY 4.0).

Rank is among all models the source ranks, including ones we don't list.

Subscribe to our newsletter

News and updates, 1–2 emails per month. No spam.