The lowest-cost LLM APIs, ranked by real per-token rate

Most "cheapest LLM" lists rank models by their published input price and stop there. Two problems with that: output tokens usually cost several times more than input, and the model you actually run is rarely the one with the lowest sticker. The table below ranks by blended cost at a 1/3-output workload.

In short: The lowest-priced chat model in our index is gemma2-9b-it at $0.01/$0.01 per 1M input/output tokens, which works out to $0.01 per 1M blended tokens. The gap to a frontier model is roughly 583x. Rates are read from the provider's live rate configuration and checked 2026-09-16.

Twelve lowest blended rates

ModelVendorRate
in / out
Blended
at 1/3 output
Official list
gemma2-9b-itGoogle$0.01 / $0.01$0.01
gemma-3-1b-itGoogle$0.01 / $0.03$0.0167
glm-4.5-flashZhipu$0.01 / $0.04$0.02
gemma-2-2b-itGoogle$0.0125 / $0.0375$0.0208
yi-sparkOther$0.05 / $0.05$0.05
qwen-turboAlibaba$0.025 / $0.1$0.05
glm-4Zhipu$0.0265 / $0.106$0.053
doubao-seed-2-0-mini-260215ByteDance$0.015 / $0.15$0.06
llama-3.3-70bMeta$0.05 / $0.148$0.0827
gpt-5-nanoOpenAI$0.025 / $0.2$0.0833
qwen-flashAlibaba$0.025 / $0.2$0.0833
ernie-3.5-8kBaidu$0.059 / $0.1475$0.0885

USD per 1M tokens, checked 2026-09-16. Blended assumes one third of tokens are output — that is a typical chat or coding-agent mix. "Official list" is the vendor's published US rate where one exists; a dash means the vendor does not publish a comparable single number (tiered or regional pricing).

Check live rates on the platform → Free to sign up · $1 minimum top-up · No prepayment

The cheapest model from each vendor

ModelVendorRate
in / out
Blended
at 1/3 output
Official list
gemma2-9b-itGoogle$0.01 / $0.01$0.01
glm-4.5-flashZhipu$0.01 / $0.04$0.02
yi-sparkOther$0.05 / $0.05$0.05
qwen-turboAlibaba$0.025 / $0.1$0.05
doubao-seed-2-0-mini-260215ByteDance$0.015 / $0.15$0.06
llama-3.3-70bMeta$0.05 / $0.148$0.0827
gpt-5-nanoOpenAI$0.025 / $0.2$0.0833
ernie-3.5-8kBaidu$0.059 / $0.1475$0.0885
deepseek-ocrDeepSeek$0.108 / $0.108$0.108
grok-4-fastxAI$0.1 / $0.25$0.15
MiniMax-M3MiniMax$0.15 / $0.6$0.3
hunyuan-a13bTencent$0.25 / $1$0.5
kimi-k2Moonshot$0.3 / $1.2$0.6
claude-3-5-haiku-20241022Anthropic$0.4 / $2$0.9333$0.8 / $4
Dolphin3.0-R1-Mistral-24BMistral$0.7286 / $1.4572$0.9715

The lowest-priced model available from each vendor. Useful once you have already picked a vendor — for tooling, data-residency or existing-integration reasons — and want the floor of that vendor's range rather than the cheapest model overall. Prices checked 2026-09-16.

How to price a high-volume workload honestly

Cheap per-token rates are where budgets are won and lost, because volume multiplies every small difference. Four things matter, in this order:

Run your own split through the cost calculator rather than using the table above as a budget: the ranking is real, but the totals depend entirely on your mix.

Cheap models compared with the mainstream

For context on what "cheap" means relative to what most teams run: Claude vs Gemini · GPT vs Gemini · DeepSeek vs Claude · all 827 models

Related guides

FAQ

What is the cheapest LLM API available?

Of the models with usable per-token pricing in our index, gemma2-9b-it is the cheapest at $0.01 per 1M blended tokens, with gemma-3-1b-it and glm-4.5-flash close behind. The table lists the twelve lowest; the full catalogue of 827 model IDs is on the pricing page.

Is the cheapest model the cheapest option overall?

Not necessarily. A cheaper per-token rate can cost more in total if it needs retries, a verification pass, or a second attempt on harder inputs. Price the whole task — including retries — rather than the per-token rate alone.

Why do some models not appear in this list?

We exclude models without usable per-token pricing, plus embeddings, rerankers, image, audio and speech models, because they are not billed on the same basis as chat models. Preview and test identifiers are also excluded so the list reflects models you can depend on.

Do these prices include any discount?

These are the current gateway rates, read from the provider's live rate configuration on 2026-09-16. They are not a permanent discount and they move with upstream promotions — which is why we publish dated rates per model rather than a headline percentage.

How do I start using the cheapest model?

Create an account, generate a key, and point your SDK at the endpoint — the model ID is the only thing that changes. The SDK guide has the one-line version.

Create free account