Cheapest Reasoning API Models
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 reasoning models is GPT OSS 20B, at $0.02838 per 1M tokens (blended), from Darkbloom.
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 reasoning support. 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 | GPT OSS 20B | OpenAI | $0.02838 | $0.0145 / $0.07 | 128K | 16 | Darkbloom |
| 2 | GPT OSS 120B | OpenAI | $0.065 | $0.03 / $0.17 | 131K | 24 | Weights & Biases |
| 3 | Qwen3 8B | Alibaba | $0.065 | $0.04 / $0.14 | 32K | 3 | LlamaGate |
| 4 | DeepSeek R1 Distill Qwen 14B | DeepSeek | $0.07 | $0.07 / $0.07 | 128K | 4 | Nscale |
| 5 | Nemotron 3 Nano 30B A3B | NVIDIA | $0.0875 | $0.05 / $0.20 | 256K | 2 | DeepInfra |
| 6 | Qwen Turbo | Alibaba | $0.0875 | $0.05 / $0.20 | 126K | 3 | Alibaba Cloud Model Studio |
| 7 | Ling 3.0 Flash | – | $0.09 | $0.06 / $0.18 | 256K | 2 | Novita AI |
| 8 | GPT OSS Safeguard 20B | OpenAI | $0.1025 | $0.07 / $0.20 | 128K | 4 | Amazon Bedrock |
| 9 | Qwen3.5 9B | Alibaba | $0.1125 | $0.10 / $0.15 | 256K | 3 | DeepInfra |
| 10 | Qwen3 30B A3B | Alibaba | $0.1175 | $0.09 / $0.20 | 128K | 9 | Pinstripes |
| 11 | Qwen3 32B | Alibaba | $0.1175 | $0.08 / $0.23 | 32K | 11 | OVHcloud |
| 12 | Qwen3 4B | Alibaba | $0.12 | $0.08 / $0.24 | 32K | 3 | Nebius AI Studio |
| 13 | GPT-5 Nano | OpenAI | $0.1375 | $0.05 / $0.40 | 272K | 7 | OpenAI |
| 14 | Qwen3.6 35B A3B | Alibaba | $0.1375 | $0.05 / $0.40 | 256K | 8 | Sail |
| 15 | DeepSeek V4.1 Flash | DeepSeek | $0.1425 | $0.09 / $0.30 | 1M | 14 | Sail |
| 16 | DeepSeek R1 Distill Qwen 32B | DeepSeek | $0.15 | $0.15 / $0.15 | 80K | 5 | Nscale |
| 17 | Mistral Small | Mistral AI | $0.15 | $0.10 / $0.30 | 32K | 6 | Mistral AI |
| 18 | Gemini 2.5 Flash Lite | $0.175 | $0.10 / $0.40 | 1M | 3 | Google AI Studio | |
| 19 | Gemini 2.5 Flash Lite Preview | $0.175 | $0.10 / $0.40 | 1M | 1 | Google Vertex AI | |
| 20 | Mimo V2.6 Flash | Xiaomi | $0.175 | $0.14 / $0.28 | 1M | 1 | Xiaomi MiMo |