google/gemini-4-argon
estimated usage cost
$7.00
1,000 requests × (1,000 uncached input × $2.00 + 500 output × $10.00) / 1,000,000 = $7.00
base rates; no context pricing tiers are published.
Gemini 4 Argon vs GPT OSS 20B
rates, context and capabilities side by side on the impossibl api, and what the same workload costs on each.
| specification | Gemini 4 Argon google/gemini-4-argon | GPT OSS 20B openai/gpt-oss-20b |
|---|---|---|
| input · usd / 1m tok | $2.00 | $0.075 |
| output · usd / 1m tok | $10.00 | $0.30 |
| context window | 1.05mtokens | 128ktokens |
| modalities · in → out | takes text, image, audio and video in, gives text out | takes text in, gives text out |
pricing
| base api rates · usd per 1m tokens | Gemini 4 Argon google/gemini-4-argon | GPT OSS 20B openai/gpt-oss-20b |
|---|---|---|
| input | $2.00 | $0.075 |
| output | $10.00 | $0.30 |
| cache read | $0.10 | $0.0375 |
the estimate below prices one workload at these rates on every model.
specifications
| as published | Gemini 4 Argon google/gemini-4-argon | GPT OSS 20B openai/gpt-oss-20b |
|---|---|---|
| creator | OpenAI | |
| model type | Text generation | Text generation |
| context window | 1,048,576tokens | 128,000tokens |
| input | takes text, image, audio and video in, gives text out | takes text in, gives text out |
| output | text | text |
| tool calling | not verified | not verified |
| released | sep 30, 2026 | aug 5, 2025 |
| 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 4 Argon google/gemini-4-argon high | GPT OSS 20B openai/gpt-oss-20b |
|---|---|---|
| intelligence index · gateway rank | 52.6#6 of 113 | 10.0#103 of 113 |
| omniscience | 42.4#2 of 90 | not measured |
| humanity’s last exam | 57.1%#1 of 93 | not measured |
| coding index | not measured | 20.7#59 of 66 |
| agentic index | not measured | 1.2#53 of 54 |
| aa-lcr | 79.7% | not measured |
| automationbench partial | 77.5% | not measured |
| scicode | 61.8% | not measured |
| analystagent | 48.8% | not measured |
| critpt | 27.1% | not measured |
| gdp.pdf all-pass | 21.8% | not measured |
| multilingual lcr | 13.9% | not measured |
| harvey lab | 3.9% | not measured |
Gemini 4 Argon source ↗GPT OSS 20B source ↗
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 2026-10-22.
estimate your cost
one token workload, priced on every model at the published rates, in usd. change the numbers to match yours.
openai/gpt-oss-20b
estimated usage cost
$0.225
1,000 requests × (1,000 uncached input × $0.075 + 500 output × $0.30) / 1,000,000 = $0.225
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 4 Argon and GPT OSS 20B are available through the Impossibl API. they share the /v1/chat/completions endpoint; the model identifier selects the model for a request.
Gemini 4 Argon is created by Google. It has a 1,048,576-token context window. Base API pricing (USD): $2.00 per million input tokens; $10.00 per million output tokens.
GPT OSS 20B is created by OpenAI. It has a 128,000-token context window. Base API pricing (USD): $0.075 per million input tokens; $0.30 per million output tokens.
this page compares Gemini 4 Argon vs GPT OSS 20B 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 →