Budget Models
Cheapest LLM APIs in 2026: Under $1 per Million Tokens
Looking for a cheap LLM API? These models cost less than $1 per million input tokens while still delivering solid performance. Perfect for high-volume applications, rapid prototyping, batch processing, and anyone watching their API bill. Sorted by price so you can find the cheapest option that meets your quality needs.
Top Picks
Most Capable
Glm 5.1
xAI
$0.9800/1M input
Largest Context
Llama 4 Scout
Meta
10Mcontext
Related Categories
Coding Models
Top models for code generation, debugging, and software engineering — ranked by LiveBench coding scores and API price.
Writing Models
Models with the highest language and writing scores for content creation, copywriting, marketing, and creative tasks.
Reasoning Models
Models with extended thinking for complex math, logic, and multi-step problem solving — ranked by benchmarks.
Models for AI Agents
Models built for autonomous AI agents — with function calling, large context windows, and competitive pricing for agentic workflows.
Cost per 1M Tokens / Flagship Models
All Budget Models
| Provider | Model | Input $/1M | Output $/1M | Context | Quality |
|---|---|---|---|---|---|
| Inclusionai | Ling 2.6 Flash | $0.0100 | $0.0300 | 262.1K | N/A |
| Ibm-granite | Granite 4.0 H Micro | $0.0170 | $0.1120 | 131K | 36.3Good |
| Meta | Llama 3.1 8b Instruct | $0.0200 | $0.0300 | 131.1K | N/A |
| Mistral | Mistral Nemo | $0.0200 | $0.0300 | 131.1K | N/A |
| Meta | Llama 3.2 1b Instruct | $0.0270 | $0.2010 | 131.1K | N/A |
| OpenAI | GPT Oss 20b | $0.0290 | $0.1400 | 131.1K | N/A |
| Liquid | Lfm 2 24b A2b | $0.0300 | $0.1200 | 128K | N/A |
| Amazon | Nova Micro V1 | $0.0350 | $0.1400 | 128K | N/A |
| Cohere | Command R7b 12 2024 | $0.0375 | $0.1500 | 128K | N/A |
| OpenAI | GPT Oss 120b | $0.0390 | $0.1800 | 131.1K | 47.7Good |
| Qwen | Qwen 2.5 7b Instruct | $0.0400 | $0.1000 | 131.1K | N/A |
| Sao10k | L3 Lunaris 8b | $0.0400 | $0.0500 | 8.2K | N/A |
| Arcee-ai | Trinity Mini | $0.0450 | $0.1500 | 131.1K | N/A |
| Qwen | Qwen3 30b A3b Instruct 2507 | $0.0482 | $0.1931 | 131.1K | 38.2Good |
| Ibm-granite | Granite 4.1 8b | $0.0500 | $0.1000 | 131.1K | N/A |
| NVIDIA | Nemotron 3 Nano 30b A3b | $0.0500 | $0.2000 | 262.1K | N/A |
| OpenAI | GPT 5 Nano | $0.0500 | $0.4000 | 400K | 49.9Good |
| Qwen | Qwen3 8b | $0.0500 | $0.4000 | 131.1K | N/A |
| Gemma 3 4b It | $0.0500 | $0.1000 | 131.1K | N/A | |
| Gemma 3 12b It | $0.0500 | $0.1500 | 131.1K | N/A | |
| Mistral | Mistral Small 24b Instruct 2501 | $0.0500 | $0.0800 | 32.8K | N/A |
| Meta | Llama 3.2 3b Instruct | $0.0509 | $0.3350 | 131.1K | N/A |
| Gemma 4 26b A4b It | $0.0600 | $0.3300 | 262.1K | N/A | |
| xAI | Glm 4.7 Flash | $0.0600 | $0.4000 | 202.8K | N/A |
| Gemma 3n E4b It | $0.0600 | $0.1200 | 32.8K | N/A | |
| Amazon | Nova Lite V1 | $0.0600 | $0.2400 | 300K | N/A |
| Gryphe | Mythomax L2 13b | $0.0600 | $0.0600 | 4.1K | N/A |
| Tencent | Hy3 Preview | $0.0630 | $0.2100 | 262.1K | N/A |
| Qwen | Qwen3.5 Flash 02 23 | $0.0650 | $0.2600 | 1M | N/A |
| Qwen | Qwen3 Coder 30b A3b Instruct | $0.0700 | $0.2700 | 160K | N/A |
| Microsoft | Phi 4 | $0.0700 | $0.1400 | 16.4K | N/A |
| Inclusionai | Ring 2.6 1t | $0.0750 | $0.6250 | 262.1K | N/A |
| Inclusionai | Ling 2.6 1t | $0.0750 | $0.6250 | 262.1K | N/A |
| Bytedance-seed | Seed 1.6 Flash | $0.0750 | $0.3000 | 262.1K | N/A |
| OpenAI | GPT Oss Safeguard 20b | $0.0750 | $0.3000 | 131.1K | N/A |
| Mistral | Mistral Small 3.2 24b Instruct | $0.0750 | $0.2000 | 128K | N/A |
| Microsoft | Phi 4 Mini Instruct | $0.0800 | $0.3500 | 131.1K | N/A |
| Qwen | Qwen3 Vl 8b Instruct | $0.0800 | $0.5000 | 256K | N/A |
| Qwen | Qwen3 30b A3b Thinking 2507 | $0.0800 | $0.4000 | 131.1K | 38.2Good |
| Qwen | Qwen3 32b | $0.0800 | $0.2800 | 131.1K | 42.2Good |
| Gemma 3 27b It | $0.0800 | $0.1600 | 131.1K | N/A | |
| DeepSeek | Deepseek V4 Flash | $0.0900 | $0.1800 | 1.0M | 68.9Frontier |
| NVIDIA | Nemotron 3 Super 120b A12b | $0.0900 | $0.4500 | 1M | N/A |
| Stepfun | Step 3.5 Flash | $0.0900 | $0.3000 | 262.1K | N/A |
| Qwen | Qwen3 Next 80b A3b Instruct | $0.0900 | $1.10 | 262.1K | 50.7Strong |
| Qwen | Qwen3 235b A22b 2507 | $0.0900 | $0.1000 | 262.1K | 52.2Strong |
| Qwen | Qwen3 Next 80b A3b Thinking | $0.0975 | $0.7800 | 262.1K | 50.7Strong |
| Poolside | Laguna Xs.2 | $0.1000 | $0.2000 | 262.1K | N/A |
| Rekaai | Reka Edge | $0.1000 | $0.1000 | 16.4K | N/A |
| Qwen | Qwen3.5 9b | $0.1000 | $0.1500 | 262.1K | N/A |
Page 1 of 5
Deploy your AI agent for $33/mo flat.
Managed Telegram bot hosting. We handle the infrastructure.
Any model. Any channel. Zero infrastructure.