Inkling (Deep Infra)
Databricks · inkling
Multimodal MoE reasoning model (975B total, 41B active) for text, image, and audio
Specification
databricks listing
Context
1M
Max output
1M
Released
2026-07-15
Knowledge cutoff
—
Retires
2026-10-30
Open weights
yes
Input
text, image, audio
Output
text
Price
US dollars per million tokens · databricks list price
Input
$1.00
Output
$4.05
Cache read
$0.17
Cache write
$1.00
Batch and priority prices
US dollars per million tokens · per listing
| Price | Listing | $/M |
|---|---|---|
| Priority input | fireworks_ai | $1.00 |
| Priority output | fireworks_ai | $4.05 |
Quality
7 benchmarks · 2 sources
Composite
53rd
percentile of 344 scored models
Rank
163 / 344
±0.08 sd
Evidence
7 × 2
3 or more benchmarks, from 2 or more sources
Effort range
—
one configuration only
reasoning72nd2/4 bench
math43rd3/7 bench
knowledge42nd1/1 bench
general29th1/1 bench
Every score
one row per source and configuration — nothing averaged away
| Benchmark | Score | Configuration | Source | Run |
|---|---|---|---|---|
| GPQA diamond | 88.3 ±1.9 | xhigh | Epoch AI | 2026-08-05 |
| OTIS Mock AIME 2024-2025 | 88.9 ±3.9 | xhigh | Epoch AI | 2026-08-05 |
| SimpleQA Verified | 40.3 ±1.6 | xhigh | Epoch AI | 2026-08-27 |
| LiveBench | 72.9 | xhigh · 23 runs | LiveBench | 2026-06-25 |
| Chess Puzzles | 21.0 ±4.1 | xhigh | Epoch AI | 2026-10-13 |
| FrontierMath-Tiers-1-3-v2 | 33.3 ±2.8 | xhigh | Epoch AI | 2026-08-06 |
| FrontierMath-Tier-4-v2 | 4.9 ±3.4 | xhigh | Epoch AI | 2026-08-06 |
The leading figure for a benchmark is the median across its configurations, so one heroic high-effort run cannot set the number.
Available from 27 hosts
| Host | In $/M | Out $/M | Cache rd | Cache wr | Context | Output | Retires |
|---|---|---|---|---|---|---|---|
| databricksvendor | $1.00 | $4.05 | $0.17 | $1.00 | 1M | — | 2026-10-30 |
| openrouter · free | free | free | — | — | 1M | 262K | — |
| deepinfra | $0.95 | $4.05 | $0.16 | — | 524K | 524K | — |
| deepinfra · thinkingmachines | $0.95 | $4.05 | $0.16 | — | 524K | 1M | — |
| edenai | $0.95 $1.00 | $4.05 | $0.16 $0.17 | — | 524K 1M | 1M | — |
| baseten | $1.00 | $4.05 | $0.17 | — | 1M | 33K | 2026-10-16 |
| commandcode · thinkingmachines | $1.00 | $4.05 | $0.17 | — | 256K | 256K | — |
| fireworks_ai | $1.00 | $4.05 | $0.17 | — | 1M | 1M | 2026-11-07 |
| fireworks-ai · accounts | $1.00 | $4.05 | $0.17 | — | 1M | 1M | — |
| huggingface · thinkingmachines | $1.00 | $4.05 | — | — | 1M | 1M | — |
| kilo · thinkingmachines | $1.00 | $4.05 | $0.17 | — | 524K | 472K | — |
| merge-gateway · thinkingmachines | $1.00 | $4.05 | $0.17 | — | 1M | 32K | — |
| nano-gpt · thinking | $1.00 | $4.05 | $0.17 | — | 1M | 33K | — |
| nano-gpt · thinkingmachines | $1.00 | $4.05 | $0.17 | — | 1M | 33K | — |
| neon | $1.00 | $4.05 | $0.17 | — | 1M | 66K | — |
| openrouter · thinkingmachines | $1.00 | $4.05 | $0.17 | — | 524K | 472K | — |
| thinkingmachines · peft:262144:sampling-nvfp4 | $1.00 | $4.05 | $0.17 | — | 262K | 262K | — |
| together_ai | $1.00 | $4.05 | $0.17 | — | 524K | 524K | 2026-11-06 |
| togetherai · thinkingmachines | $1.00 | $4.05 | $0.17 | — | 524K | 131K | — |
| vercel · thinkingmachines | $1.00 | $4.05 | $0.17 | — | 256K | 256K | — |
| aimlapi · thinkingmachines | $1.058 | $4.2849 | $0.1799 | — | 1M | 1M | — |
| hyper | $1.0888 | $4.4096 | $0.1851 | — | 1M | 66K | — |
| impossibl · thinkingmachines | $1.87 | $4.68 | $0.374 | — | 66K | 66K | — |
| llmtr · thinkingmachines | $1.87 | $4.68 | $0.374 | — | 262K | 262K | — |
| requesty | $1.87 | $4.68 | $0.374 | — | 66K | 33K | — |
| thinkingmachines · thinkingmachines | $1.87 | $4.68 | $0.374 | — | 66K | 66K | — |
| abacus · thinkingmachines | $3.74 | $9.36 | $0.748 | — | 262K | 131K | — |
Price history
append-only observations · a listing writes a row only when its price moves
| Date | Host | Field | $/M |
|---|---|---|---|
| 2026-09-02 | edenai | Cache read | $0.16 |
| 2026-09-07 | edenai | Cache read | $0.17 |
| 2026-09-24 | edenai | Cache read | $0.16 |
| 2026-10-19 | edenai | Cache read | $0.17 |
| 2026-10-20 | edenai | Cache read | $0.16 |
| 2026-10-22 | edenai | Cache read | $0.17 |
| 2026-10-24 | edenai | Cache read | $0.17 |
| 2026-10-25 | edenai | Cache read | $0.17 |
| 2026-10-26 | edenai | Cache read | $0.17 |
| 2026-10-28 | edenai | Cache read | $0.10 |
| 2026-10-29 | edenai | Cache read | $0.10 |
| 2026-10-30 | edenai | Cache read | $0.10 |
| 2026-10-31 | edenai | Cache read | $0.16 |
| 2026-11-01 | edenai | Cache read | $0.16 |
| 2026-09-02 | kilo · thinkingmachines | Cache read | $0.16 |
| 2026-10-23 | kilo · thinkingmachines | Cache read | $0.17 |
| 2026-09-02 | nano-gpt · thinking | Cache read | $0.17 |
| 2026-10-19 | nano-gpt · thinking | Cache read | $0.16 |
| 2026-10-23 | nano-gpt · thinking | Cache read | $0.17 |
| 2026-09-02 | nano-gpt · thinkingmachines | Cache read | $0.17 |
| 2026-10-19 | nano-gpt · thinkingmachines | Cache read | $0.16 |
| 2026-10-23 | nano-gpt · thinkingmachines | Cache read | $0.17 |
| 2026-09-02 | openrouter · thinkingmachines | Cache read | $0.17 |
| 2026-10-02 | openrouter · thinkingmachines | Cache read | $0.16 |
| 2026-10-07 | openrouter · thinkingmachines | Cache read | $0.17 |
| 2026-09-02 | venice | Cache read | $0.2125 |
| 2026-10-22 | venice | Cache read | $0.125 |
| 2026-09-02 | edenai | Input | $0.95 |
| 2026-09-07 | edenai | Input | $1.00 |
| 2026-09-24 | edenai | Input | $0.95 |
| 2026-10-19 | edenai | Input | $1.00 |
| 2026-10-20 | edenai | Input | $0.95 |
| 2026-10-22 | edenai | Input | $1.00 |
| 2026-10-31 | edenai | Input | $0.95 |
| 2026-09-02 | kilo · thinkingmachines | Input | $0.95 |
| 2026-10-23 | kilo · thinkingmachines | Input | $1.00 |
| 2026-09-02 | nano-gpt · thinking | Input | $1.00 |
| 2026-10-19 | nano-gpt · thinking | Input | $0.95 |
| 2026-10-23 | nano-gpt · thinking | Input | $1.00 |
| 2026-09-02 | nano-gpt · thinkingmachines | Input | $1.00 |
| 2026-10-19 | nano-gpt · thinkingmachines | Input | $0.95 |
| 2026-10-23 | nano-gpt · thinkingmachines | Input | $1.00 |
| 2026-09-02 | openrouter · free | Input | free |
| 2026-09-19 | openrouter · free | Input | free |
| 2026-10-10 | openrouter · free | Input | free |
| 2026-09-02 | openrouter · thinkingmachines | Input | $1.00 |
| 2026-10-02 | openrouter · thinkingmachines | Input | $0.95 |
| 2026-10-07 | openrouter · thinkingmachines | Input | $1.00 |
| 2026-09-02 | venice | Input | $1.25 |
| 2026-10-22 | venice | Input | $0.5625 |
| 2026-09-02 | openrouter · free | Output | free |
| 2026-09-19 | openrouter · free | Output | free |
| 2026-10-10 | openrouter · free | Output | free |
| 2026-09-02 | venice | Output | $5.0625 |
| 2026-10-22 | venice | Output | $1.50 |
| 2026-09-19 | openrouter | Cache read | $0.17 |
| 2026-10-03 | openrouter | Cache read | $0.16 |
| 2026-10-07 | openrouter | Cache read | $0.17 |
| 2026-09-19 | openrouter | Input | $1.00 |
| 2026-10-03 | openrouter | Input | $0.95 |
| 2026-10-07 | openrouter | Input | $1.00 |
| 2026-09-23 | llmgateway-providers | Cache read | $0.17 |
| 2026-09-24 | llmgateway-providers | Cache read | $0.16 |
| 2026-09-28 | llmgateway-providers | Cache read | $0.16 |
| 2026-09-23 | llmgateway-providers | Input | $1.00 |
| 2026-09-24 | llmgateway-providers | Input | $0.95 |
| 2026-09-28 | llmgateway-providers | Input | $0.95 |
| 2026-10-13 | aimlapi · thinkingmachines | Cache read | $0.2338 |
| 2026-10-23 | aimlapi · thinkingmachines | Cache read | $0.1799 |
| 2026-10-13 | aimlapi · thinkingmachines | Input | $1.3754 |
| 2026-10-23 | aimlapi · thinkingmachines | Input | $1.058 |
| 2026-10-13 | aimlapi · thinkingmachines | Output | $5.5704 |
| 2026-10-23 | aimlapi · thinkingmachines | Output | $4.2849 |
More from Databricks
most-hosted first