Price per 1M logo

Cheapest model for a customer-support bot

Blended cost estimate for a support bot profile: short prompts, medium answers, high volume, heavy prompt reuse.

Current leader: Gemini Exp 1114 (Google Gemini). Refreshed 2026-09-13 13:40 UTC.

#ModelProviderInput $/1MOutput $/1MCached $/1MContext
1Gemini Exp 1114Google Geminifreefree—1.0M
2Gemini Exp 1206Google Geminifreefree—2.1M
3Gemma 3 27b ItGoogle Geminifreefree—131K
4Gemma 4 26b A4b ItGoogle Geminifreefree—262K
5Gemma 4 31b ItGoogle Geminifreefree—262K
6Learnlm 1.5 Pro ExperimentalGoogle Geminifreefree—33K
7Labs Leanstral 1 5Mistral AIfreefree—262K
8Labs Leanstral 1 5 1Mistral AIfreefree—262K
9Anthropic.claude Mythos PreviewAmazon Bedrockfreefree—1M
10Gemma 2b It LoraCloudflare Workers AIfreefree—8K
11Mistral 7b Instruct V0.2 LoraCloudflare Workers AIfreefree—15K
12Llama 2 7b Chat Hf LoraCloudflare Workers AIfreefree—8K
13Gemma 7b It LoraCloudflare Workers AIfreefree—4K
14Codegeex4Ollamafreefree—33K
15CodegemmaOllamafreefree—8K
16CodellamaOllamafreefree—4K
17Deepseek Coder V2 BaseOllamafreefree—8K
18Deepseek Coder V2 InstructOllamafreefree—33K
19Deepseek Coder V2 Lite BaseOllamafreefree—8K
20Deepseek Coder V2 Lite InstructOllamafreefree—33K
21Deepseek V3.1:671b CloudOllamafreefree—164K
22GPT Oss:120b CloudOllamafreefree—131K
23GPT Oss:20b CloudOllamafreefree—131K
24Internlm2 5 20b ChatOllamafreefree—33K
25Llama2Ollamafreefree—4K
26Llama2 UncensoredOllamafreefree—4K
27Llama2:13bOllamafreefree—4K
28Llama2:70bOllamafreefree—4K
29Llama2:7bOllamafreefree—4K
30Llama3Ollamafreefree—8K
31Llama3.1Ollamafreefree—8K
32Llama3:70bOllamafreefree—8K
33Llama3:8bOllamafreefree—8K
34MistralOllamafreefree—8K
35Mistral 7B Instruct V0.1Ollamafreefree—8K
36Mistral 7B Instruct V0.2Ollamafreefree—33K
37Mistral Large Instruct 2407Ollamafreefree—66K
38Mixtral 8x22B Instruct V0.1Ollamafreefree—66K
39Mixtral 8x7B Instruct V0.1Ollamafreefree—33K
40Orca MiniOllamafreefree—4K
41Qwen3 Coder:480b CloudOllamafreefree—262K
42VicunaOllamafreefree—2K
43AutoOpenRouterfreefree—2M
44FreeOpenRouterfreefree—200K
45BodybuilderOpenRouterfreefree—128K
46Nemotron 3.5 Lightning:freeOpenRouterfreefree—1M
47Laguna S 2.1:freeOpenRouterfreefree—262K
48Laguna Xs 2.1:freeOpenRouterfreefree—262K
49Glm 5.2:freeOpenRouterfreefree—256K
50Nemotron 3.5 Content Safety:freeOpenRouterfreefree—128K
51Nemotron 3 Ultra 550b A55b:freeOpenRouterfreefree—1M
52Minimax M3:freeOpenRouterfreefree—1.0M
53Nemotron 3 Nano Omni 30b A3b Reasoning:freeOpenRouterfreefree—256K
54Gemma 4 26b A4b It:freeOpenRouterfreefree—262K
55Gemma 4 31b It:freeOpenRouterfreefree—262K
56Minimax M2.7:freeOpenRouterfreefree—197K
57Nemotron 3 Super 120b A12b:freeOpenRouterfreefree—262K
58Llama 3.3 70B Instruct Turbo FreeTogether AIfreefree——
59Ternary Bonsai 27BTogether AIfreefree—262K
60Qwen2.5 Coder 7BNebius$0.01$0.03—33K

Other use cases

Cheapest chat APIs
Cheapest long-context models
Cheapest vision models
Cheapest tool-calling models
Cheapest reasoning models
Cheapest cached-input pricing
Cheapest embedding models
Cheapest model for summarisation at scale
Cheapest models for code generation

Frequently asked

› Which AI model should a support chatbot use?

Gemini Exp 1114 from Google Gemini currently leads this list, at $0/1M input tokens. Rankings are recomputed from the raw dataset on every refresh, so they track price cuts automatically.

› How are these rankings calculated?

Each use case applies a capability filter (context size, vision, tool calling, cache pricing) and then ranks the surviving models by the blended cost that profile actually pays. See the methodology page for the exact formulas.

› Is the cheapest model always the right choice?

No. Check the capability flags and context window, and benchmark quality on your own data — the cheapest model that fails your evals costs more than the second cheapest that passes them.