DeepSeek V4.1 Flash vs gpt-oss-120b.
model vs model · prices as of
DeepSeek V4.1 Flash takes 2 of 5 rounds against gpt-oss-120b. It is also the cheaper of the two to run, at $0.21 per million tokens against $0.24.
DeepSeekwins 2 roundsDeepSeek V4.1 Flash
$0.21/M tokens
cheapest we can explain, at TrustedRouter · $0.0304 per 1,000 pages
1M context · tool calling · reads images · open weights
OpenAIgpt-oss-120b
$0.24/M tokens
cheapest we can explain, at LLM Gateway · $0.0276 per 1,000 pages
131k context · tool calling · open weights
List price in (lower wins)
$0.15/M
$0.15/M
List price out (lower wins)
$0.60/M
$0.60/M
Cheapest we can explain (lower wins)
$0.21/M at TrustedRouter
$0.24/M at LLM Gateway
Standard price (lower wins)
$1.05/M
$1.05/M
Cost per 1,000 pages (lower wins)
$0.0304
$0.0276
Context
1M tokens
131k tokens
Open weights
yes
yes
Tool calling
yes
yes
Structured output
yes
yes
Reads images
yes
no
Reasoning
yes
yes
Released
10 Sept 2026
5 Aug 2025
Providers selling it
61
68
Price we measure against
the maker's own
OpenRouter
Trains on your prompts (no is better)
not stated
not stated
Providers selling both · 29
TrustedRouter$0.21 / $0.27
Nous Portal$0.91 / $0.26
LLM Gateway$1.05 / $0.24
DeepInfra$1.20 / $0.28
Merge Gateway$1.05 / $0.63
FastRouter$1.20 / $0.63
OpenRouter$1.05 / $1.05
Kilo Gateway$2.10 / $0.26
DeepSeek V4.1 Flash then gpt-oss-120b, per million tokens · showing the 8 cheapest of 29
Go further
Add a third or fourth model, or switch the weighting, in the tool.
What moved in the last seven days
- DeepSeek V4.1 FlashDeepSeek$0.30 / $1.20 $0.15 / $0.6050% cheaper ·
- DeepSeek V4.1 Flash
io.net Intelligence$0.31 / $1.22 $0.28 / $1.0810% cheaper · - DeepSeek V4.1 FlashDeepSeekDeepSeek's list price, in and out per million tokens$0.30 / $1.20 $0.15 / $0.6050% cheaper ·
- DeepSeek V4.1 FlashNous Portal$0.15 / $0.59 $0.13 / $0.5212% cheaper ·
- DeepSeek V4.1 FlashOpenRouter$0.30 / $1.20 $0.15 / $0.6050% cheaper ·
- DeepSeek V4.1 Flash
Relace$0.15 / $0.60 $0.13 / $0.5213% cheaper · - DeepSeek V4.1 Flash
Requesty$0.50 / $1.50 $0.22 / $0.6656% cheaper · - gpt-oss-120bDeepInfra$0.15 / $0.60 $0.04 / $0.1773% cheaper ·
- gpt-oss-120b
Eden AI$0.17 / $0.75 $0.17 / $0.740.2% cheaper · - DeepSeek V4.1 Flash
Novita$0.30 / $1.20 $0.28 / $1.145% cheaper · - DeepSeek V4.1 Flash
Wafer$0.30 / $1.20 $0.20 / $0.6043% cheaper · - gpt-oss-120bio.net Intelligence$0.18 / $0.68 $0.17 / $0.637% cheaper ·
- gpt-oss-120b
Mancer$20,000 / $160,000 $20,000 / $120,00018% cheaper · - gpt-oss-120bMancer$0.05 / $0.40 $0.05 / $0.3018% cheaper ·
- gpt-oss-120bOpenRouterOpenRouter's list price, in and out per million tokens$0.04 / $0.17 $0.15 / $0.60274% dearer ·
- gpt-oss-120bOpenRouter$0.04 / $0.17 $0.15 / $0.60274% dearer ·
- gpt-oss-120bRequesty$0.03 / $0.14 $0.15 / $0.60345% dearer ·
- DeepSeek V4.1 Flash
Charm Hyper$0.33 / $1.31 $0.30 / $1.208% cheaper · - DeepSeek V4.1 FlashEden AI$0.50 / $1.50 $0.30 / $1.2030% cheaper ·
- DeepSeek V4.1 Flash
Vercel AI Gateway$0.15 / $0.60 $0.30 / $1.20100% dearer · - DeepSeek V4.1 Flash
GMI Cloud$0.30 / $1.20 $0.28 / $1.145% cheaper · - DeepSeek V4.1 Flash
Kenari$0.35 / $0.70 $0.01 / $0.0396% cheaper · - DeepSeek V4.1 FlashTrustedRouter$0.16 / $0.63 $0.04 / $0.0881% cheaper ·
- gpt-oss-120bCharm Hyper$0.17 / $0.66 $0.18 / $0.684% dearer ·
- gpt-oss-120b
DigitalOcean Gradient$0.06 / $0.39 $0.06 / $0.429% dearer · - gpt-oss-120bNous Portal$0.02 / $0.14 $0.03 / $0.1725% dearer ·
Frequently asked
- Which is cheaper, DeepSeek V4.1 Flash or gpt-oss-120b?
- DeepSeek V4.1 Flash, at $0.21 per million tokens against $0.24 for gpt-oss-120b, three parts input to one part output, read on 19 Sept 2026.
- Where is each one cheapest?
- DeepSeek V4.1 Flash: $0.21 at TrustedRouter. gpt-oss-120b: $0.24 at LLM Gateway.
- Can I buy both from one provider?
- Yes. 29 providers sell both: TrustedRouter, Nous Portal, LLM Gateway, DeepInfra, Merge Gateway, FastRouter, and more. The cheapest of them for the two together is TrustedRouter.
- Which holds more context?
- DeepSeek V4.1 Flash, at 1M tokens against 131k.
Prices exclude tax and are per million tokens, read 19 Sept 2026 from each provider's own catalog. The standard price blends three parts input to one part output; a page is 600 tokens in and 60 out. Bars are scaled to the larger value in each row.