Best AI model for a chat assistant.
Prices checked
gpt-oss-20b at TrustedRouter costs you 5.4¢ per 1,000 conversations, the cheapest of 325 models that can do this job, checked .
Cheapest 10
all 392 models- 1
gpt-oss-20b
Resells
TrustedRouter · $0.01 in · $0.05 out5.4¢per 1,000 conversations - 2
Llama 3.1 8B Instruct
Runs it themselves
Helicone · $0.02 in · $0.03 out7.5¢per 1,000 conversations - 3
Mistral Nemo
Lower precision (fp8)
Eden AI · $0.02 in · $0.03 out8.4¢per 1,000 conversations - 4
Ling 3.0 Flash
Same as maker
OpenRouter · $0.02 in · $0.06 out9.5¢per 1,000 conversations - 5
Qwen3.7 Flash
Regional priceEden AI · $0.02 in · $0.08 out$0.10per 1,000 conversations - 6
Granite 4.0 H Micro
Same as maker
Cloudflare Workers AI · $0.02 in · $0.11 out$0.11per 1,000 conversations - 7
Ministral 3 3B
Runs it themselves
Azure Cognitive Services · $0.04 in · $0.04 out$0.14per 1,000 conversations - 8
DeepSeek V4.1 Flash 1017
Runs it themselvesEngy · $0.03 in · $0.12 out
$0.15per 1,000 conversations - 9
Qwen3.5-9B
Regional priceEden AI · $0.04 in · $0.07 out$0.15per 1,000 conversations - 10
Nemotron 3.5 Lightning
Resells
NanoGPT · $0.05 in · $0.01 out$0.15per 1,000 conversations
Other ways to pick
What matters
- Tool calling required
- An assistant that can only talk is a search box with extra steps. Tool calling is what lets it check an order or book a slot.
- Input grows with the chat
- Each turn resends the conversation so far, so a ten-turn chat reads its own history nine times. Ask your provider about cached input before you scale it.
- Latency is not on this page
- Price is measured here; speed is not. For a live assistant, test the two or three cheapest rows for how fast the first token arrives.
How we count
An assistant in your product, holding a conversation and calling your API when it needs to. Every turn re-reads the whole conversation, so the input bill grows with the chat. We count only models with 32k of context or more and tool calling, and 325 of the 392 we track qualify. The cheapest of them costs 5.4¢ per 1,000 conversations at TrustedRouter. They are ranked by what the work costs, not by the price per million tokens, because a model that is cheap to prompt and dear to answer looks different once you know the shape of the job.
A conversation of about ten turns is 3,000 tokens in and 500 out in total. A cost per 1,000 conversations is that multiplied out at the row's own input and output rate, so it says what the work costs; the price per million tokens under each name says what the model costs.
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.
- Same as maker
- Sold by someone else at the price the maker charges.
- Regional price
- A price list for one region, lower than the international one. A region, not a deal.
Frequently asked
- What is the cheapest model for a chat assistant?
- gpt-oss-20b at TrustedRouter, 5.4¢ per 1,000 conversations at $0.01 in and $0.05 out per million tokens, read on 31 Oct 2026.
- How is the cost per unit worked out?
- A conversation of about ten turns is 3,000 tokens in and 500 out in total. Multiply that by 1,000 and price it at each row's own input and output rate. Nothing else is counted: no cache discount, no batch rate, no free tier.
- Why do only 325 models qualify?
- The job needs 32k of context or more, tool calling. Models that fall short are still in the index, they just cannot do this job as described.
- How current are these prices?
- Prices are read every 3 days from 237 providers' public catalogs and this ranking recomputes with them. Last refresh: 31 Oct 2026.
Related jobs