// ranked · November 2026
Cheapest LLMs with Tool Calling
Every paid model that supports tool (function) calling, ranked by blended list price — 3:1 input:output per 1M tokens. Free tiers are on their own page.
gpt-oss-120b is the cheapest paid model with tool calling, at $0.022 per 1M tokens blended. Ling 3.0 Tiny follows at $0.022.
gpt-oss-120b vs Ling 3.0 Tiny, head to headTop 10
| # | Model | Blended / 1M | Context | LiveBench | Capabilities |
|---|---|---|---|---|---|
| 1 | gpt-oss-120b openai/gpt-oss-120b | $0.022 | 131K | — | reasoningtools |
| 2 | Ling 3.0 Tiny inclusionai/ling-3.0-tiny | $0.022 | 262K | — | reasoningtools |
| 3 | Mistral Nemo mistralai/mistral-nemo | $0.029 | 131K | — | tools |
| 4 | Ling 3.0 Flash inclusionai/ling-3.0-flash | $0.032 | 262K | — | reasoningtools |
| 5 | Qwen3.7 Flash qwen/qwen3.7-flash | $0.055 | 1M | — | reasoningtoolsvision |
| 6 | gpt-oss-20b openai/gpt-oss-20b | $0.055 | 131K | — | reasoningtools |
| 7 | Llama 3.1 8B Instruct meta-llama/llama-3.1-8b-instruct | $0.057 | 131K | — | tools |
| 8 | Nova Micro 1.0 amazon/nova-micro-v1 | $0.061 | 128K | — | tools |
| 9 | Command R7B (12-2024) cohere/command-r7b-12-2024 | $0.066 | 128K | — | tools |
| 10 | Ling 3.1 Flash inclusionai/ling-3.1-flash | $0.068 | 1M | — | reasoningtools |
275 more models qualify — see the full leaderboard.
FAQ
What is the cheapest LLM with tool calling in November 2026?
gpt-oss-120b is the cheapest paid model with tool calling, at $0.022 per 1M tokens blended. Ling 3.0 Tiny follows at $0.022.
How is this ranking produced?
Every paid model that supports tool (function) calling, ranked by blended list price — 3:1 input:output per 1M tokens. Free tiers are on their own page.
Other rankings
How this ranking is produced
- One metric, stated above — nothing here is weighted or scored by us. Scores come from LiveBench release 2026-10-25; models without a published run don't appear in score-based rankings.
- Price, context and capabilities — live from OpenRouter, refreshed every 15 minutes.
- Ties — scores less than a point apart are called a tie; effort settings alone move a LiveBench score by more than that.
A public benchmark is someone else's workload. Before committing, see LLM & agent evaluation.