Cheapest API Models with Tool Calling
As of October 21, 2026, among LiteLLM's active models with a 32K-token context window or more, offered by at least two providers or by their own lab, the cheapest of the models with tool calling is Qwen2.5 Coder 7B, at $0.015 per 1M tokens (blended), from Nebius AI Studio.
Top 20
Sorted by blended price: 3 input tokens for every output token, at each model's headline price (its own lab's API where it sells it, otherwise its cheapest provider). Only models that list function calling. Only active models with a 32K-token context window or more, offered by at least two providers or by their own lab. Free models are left out.
| # | Model | Lab | Blended price per 1M tokens | Price per 1M (in / out) | Context | Providers | Price from |
|---|---|---|---|---|---|---|---|
| 1 | Qwen2.5 Coder 7B | Alibaba | $0.015 | $0.01 / $0.03 | 32K | 3 | Nebius AI Studio |
| 2 | Llama3.2 11B Vision Instruct | Meta | $0.0175 | $0.015 / $0.025 | 128K | 5 | Lambda |
| 3 | Llama3.2 3B Instruct | Meta | $0.0175 | $0.015 / $0.025 | 128K | 8 | Lambda |
| 4 | Llama 3.2 1B Instruct | Meta | $0.02 | $0.02 / $0.02 | 131K | 5 | Novita AI |
| 5 | Mistral Nemo Instruct | Mistral AI | $0.02175 | $0.019 / $0.03 | 128K | 5 | DeepInfra |
| 6 | Llama 3.1 8B Instruct Turbo | Meta | $0.025 | $0.02 / $0.04 | 128K | 2 | DeepInfra |
| 7 | GPT OSS 20B | OpenAI | $0.02838 | $0.0145 / $0.07 | 128K | 16 | Darkbloom |
| 8 | Llama 3.1 8B | Meta | $0.035 | $0.03 / $0.05 | 128K | 5 | LlamaGate |
| 9 | Llama 3.2 3B | Meta | $0.05 | $0.04 / $0.08 | 128K | 3 | LlamaGate |
| 10 | Qwen2.5 7B Instruct | Alibaba | $0.055 | $0.04 / $0.10 | 32K | 3 | DeepInfra |
| 11 | Mistral Small 24B Instruct | Mistral AI | $0.0575 | $0.05 / $0.08 | 32K | 3 | DeepInfra |
| 12 | Nova Micro | Amazon | $0.06125 | $0.035 / $0.14 | 128K | 2 | Amazon Bedrock |
| 13 | Nova Micro V1 | Amazon | $0.06125 | $0.035 / $0.14 | 128K | 1 | Amazon Nova |
| 14 | Gemma 3 12B IT | $0.0625 | $0.05 / $0.10 | 128K | 4 | Novita AI | |
| 15 | GPT OSS 120B | OpenAI | $0.065 | $0.03 / $0.17 | 131K | 24 | Weights & Biases |
| 16 | Qwen3 8B | Alibaba | $0.065 | $0.04 / $0.14 | 32K | 3 | LlamaGate |
| 17 | Command R7B | Cohere | $0.06562 | $0.0375 / $0.15 | 128K | 1 | Cohere |
| 18 | Nvidia Nemotron Nano 9B V2 | NVIDIA | $0.07 | $0.04 / $0.16 | 128K | 3 | DeepInfra |
| 19 | Mistral Nemo | Mistral AI | $0.0725 | $0.04 / $0.17 | 60K | 3 | Novita AI |
| 20 | Nemotron 3 Nano 30B A3B | NVIDIA | $0.0875 | $0.05 / $0.20 | 256K | 2 | DeepInfra |