Cheapest models with 128k context.
Prices checked
gpt-oss-20b at TrustedRouter leads 325 models at $0.02 per M tokens, checked .
Top 10
all 392 models- 1
gpt-oss-20b
Resells
TrustedRouter · 131k context · $0.01 in / $0.05 out$0.02/M tokens - 2
Llama 3.2 3B Instruct
Runs it themselves
Inference · 131k context · $0.02 in / $0.02 out$0.02/M tokens - 3
Llama 3.1 8B Instruct
Runs it themselves
Helicone · 131k context · $0.02 in / $0.03 out$0.02/M tokens - 4
Mistral Nemo
Lower precision (fp8)
Eden AI · 131k context · $0.02 in / $0.03 out$0.02/M tokens - 5
Ling 3.0 Flash
OpenRouter · 262k context · $0.02 in / $0.06 out$0.03/M tokens - 6
Qwen3.7 Flash
Regional priceEden AI · 1M context · $0.02 in / $0.08 out$0.04/M tokens - 7
Ministral 3 3B
Runs it themselves
Azure Cognitive Services · 131k context · $0.04 in / $0.04 out$0.04/M tokens - 8
Nemotron 3.5 Lightning
Resells
NanoGPT · 262k context · $0.05 in / $0.01 out$0.04/M tokens - 9
Granite 4.0 H Micro
Cloudflare Workers AI · 131k context · $0.02 in / $0.11 out$0.04/M tokens - 10
Gemma 3 4B
Promotion
Kilo Gateway · 131k context · $0.04 in / $0.05 out$0.04/M tokens
How we count
128k tokens is roughly a 300-page book in one call, which is the point at which you stop chopping documents into pieces. 325 models hold that much and are sold by 3 providers or more, from $0.02. Prices are per million tokens, blended 3 in : 1 out, at each provider's standard rate.
A price below the maker's is listed only when the provider says why.
- Resells
- The provider sells another company's endpoint, at a margin of its own or at the maker's price.
- Runs it themselves
- The provider runs the open weights on hardware of its own, so the price is its own rather than a resale.
- Lower precision
- The open weights, served at a lower precision than the maker's, so not quite the same product.
- Regional price
- A price list for one region, lower than the international one. A region, not a deal.
- Promotion
- A discount the provider publishes, which may end.
Frequently asked
- What is the cheapest of the models with 128k context right now?
- gpt-oss-20b at TrustedRouter, $0.01 in and $0.05 out per million tokens, read on 31 Oct 2026.
- Which lab shows up most in this ranking?
- Meta trained 2 of the top 10 models here.
- How is this ranked, and how current is it?
- Every row is the cheapest price for that model with an account behind it: the maker's own, a price below it with a published reason, or a price at or above it. A price below the maker's own with nothing to explain it is listed on the model's page and not ranked. Prices are read every 3 days from 237 providers' public catalogs, per million tokens and blended 3 in : 1 out. Last refresh: 31 Oct 2026.