google/gemini-3.8-flash
estimated usage cost
$2.625
1,000 requests × (1,000 uncached input × $0.75 + 500 output × $3.75) / 1,000,000 = $2.625
base rates; no context pricing tiers are published.
Gemini 3.8 Flash vs Inkling Small
rates, context and capabilities side by side on the impossibl api, and what the same workload costs on each.
| specification | Gemini 3.8 Flash google/gemini-3.8-flash | Inkling Small thinkingmachines/inkling-small |
|---|---|---|
| input · usd / 1m tok | $0.75 | $0.58 |
| output · usd / 1m tok | $3.75 | $1.44 |
| context window | 1.05mtokens | 65.54ktokens |
| modalities · in → out | takes text, image, audio and video in, gives text out | takes text and image in, gives text out |
pricing
| base api rates · usd per 1m tokens | Gemini 3.8 Flash google/gemini-3.8-flash | Inkling Small thinkingmachines/inkling-small |
|---|---|---|
| input | $0.75 | $0.58 |
| output | $3.75 | $1.44 |
| cache read | $0.075 | $0.116 |
the estimate below prices one workload at these rates on every model.
specifications
| as published | Gemini 3.8 Flash google/gemini-3.8-flash | Inkling Small thinkingmachines/inkling-small |
|---|---|---|
| creator | Thinking Machines | |
| model type | Text generation | Text generation |
| context window | 1,048,576tokens | 65,536tokens |
| input | takes text, image, audio and video in, gives text out | takes text and image in, gives text out |
| output | text | text |
| tool calling | not verified | not verified |
| released | sep 2, 2026 | not published |
| endpoint | /v1/chat/completions | /v1/chat/completions |
unknown means the public catalog does not establish that fact. a model's documented capabilities can differ from what a particular api supports. see the model documentation for integration details.
benchmarks
| primary configuration | Gemini 3.8 Flash google/gemini-3.8-flash high | Inkling Small thinkingmachines/inkling-small no benchmarks yet |
|---|---|---|
| intelligence index · gateway rank | 41.2#13 of 90 | not measured |
| coding index | 76.3#8 of 60 | not measured |
| agentic index | 41.1#23 of 49 | not measured |
| omniscience | 29.6#7 of 86 | not measured |
| gpqa | 95.3%#2 of 88 | not measured |
| humanity’s last exam | 47.8%#9 of 89 | not measured |
| terminal-bench v2.1 | 87.6%#7 of 57 | not measured |
| mmmu-pro | 85.6% | not measured |
| aa-lcr | 81.3% | not measured |
| automationbench partial | 59.9% | not measured |
| scicode | 56.6% | not measured |
| tau banking | 44.9% | not measured |
| multilingual lcr | 21.7% | not measured |
| gdp.pdf all-pass | 21.0% | not measured |
| terminal-bench v4.0 | 19.7% | not measured |
| critpt | 18.3% | not measured |
each column describes the tested configuration named under the model; performance and costs can differ on impossibl. a score one model was not measured on is left blank rather than scored zero. indices are ranked against every model on the gateway with one. last checked 2026-09-11.
estimate your cost
one token workload, priced on every model at the published rates, in usd. change the numbers to match yours.
thinkingmachines/inkling-small
estimated usage cost
$1.30
1,000 requests × (1,000 uncached input × $0.58 + 500 output × $1.44) / 1,000,000 = $1.30
base rates; no context pricing tiers are published.
estimates use published impossibl api usage rates. configured billing adjustments, funding fees, taxes, and custom workspace rates are excluded and may change the final amount.
image and audio usage, cache creation, and additional tool charges are excluded. reasoning tokens count as billable output, even when they are not visible in the response.
summary
Gemini 3.8 Flash and Inkling Small are available through the Impossibl API. they share the /v1/chat/completions endpoint; the model identifier selects the model for a request.
Gemini 3.8 Flash is created by Google. It has a 1,048,576-token context window. Base API pricing (USD): $0.75 per million input tokens; $3.75 per million output tokens.
Inkling Small is created by Thinking Machines. It has a 65,536-token context window. Base API pricing (USD): $0.58 per million input tokens; $1.44 per million output tokens.
Gemini 3.8 Flash →Inkling Small →
this page compares Gemini 3.8 Flash vs Inkling Small as listed by the impossibl public api. prices and availability come from that catalog, refreshed here every five minutes. this is an impossibl offering, not a comparison of independent hosting-provider quotes.
view the source catalog ↗comparison as markdown ↗report a correction →