A comprehensive comparison of 4587 AI models across 95 providers. Find the best model for your use case — whether you need the cheapest, the most capable, or the best for a specific task.
The most affordable models per million tokens, excluding aggregator providers.
| Model | Provider | Input $/M | Output $/M | Context | Capabilities |
|---|---|---|---|---|---|
| openai--gpt-image-1-mini | aimlapi | $0.007 | $0.676 | ? | |
| mistralai--Mistral-Nemo-Instruct-2407 | klusterai | $0.008 | $0.001 | 131K | |
| qwen3.5-0.8b | deepinfra | $0.01 | $0.05 | 262K | 🧠 Reason 👁️ Vision |
| ling-2.6-flash | inclusionai | $0.01 | $0.03 | 262K | 🔧 Tool |
| bdc-coder | inferencenet | $0.01 | $0.01 | 131K | 🔧 Tool |
| openai--gpt-image-1-model | aimlapi | $0.012 | $0.175 | ? | |
| klusterai--Meta-Llama-3.1-8B-Instruct-Turbo | klusterai | $0.015 | $0.02 | 131K | 🔧 Tool |
| granite-4.0-h-micro | cloudflare | $0.017 | $0.112 | 131K | 🔧 Tool |
| meta-llama-3.1-8b-instruct-turbo | deepinfra | $0.02 | $0.03 | 131K | |
| meta-llama-3.1-8b-instruct | deepinfra | $0.02 | $0.05 | 131K | |
| mistral-nemo-instruct-2407 | deepinfra | $0.02 | $0.04 | 131K | |
| qwen3.5-2b | deepinfra | $0.02 | $0.1 | 262K | 🧠 Reason 👁️ Vision |
| llama-3.1-8b-instruct--fp-16 | inferencenet | $0.02 | $0.03 | 131K | 🔧 Tool |
| schematron-3b | inferencenet | $0.02 | $0.05 | 131K | 🔧 Tool |
| schematron-v3 | inferencenet | $0.02 | $0.05 | 131K | 🔧 Tool |
81 models available at zero cost. Perfect for testing, prototyping, and learning.
| Model | Provider | Context | Capabilities |
|---|---|---|---|
| openrouter--owl-alpha | openrouter | 1M | 🔧 Tool |
| deepseek--deepseek-v4-flash--free | openrouter | 1M | 🔧 Tool 🧠 Reason |
| google--lyria-3-clip-preview | openrouter | 1M | 👁️ Vision |
| google--lyria-3-pro-preview | openrouter | 1M | 👁️ Vision |
| qwen--qwen3-coder--free | openrouter | 1M | 🔧 Tool |
| nvidia--nemotron-3-super-120b-a12b--free | openrouter | 1M | 🔧 Tool 🧠 Reason |
| gemma-4-26b-a4b-it | auriko | 262K | 🔧 Tool 🧠 Reason 👁️ Vision |
| gemma-4-31b-it | auriko | 262K | 🔧 Tool 🧠 Reason 👁️ Vision |
| arcee-ai--trinity-large-thinking--free | openrouter | 262K | 🔧 Tool 🧠 Reason |
| google--gemma-4-26b-a4b-it--free | openrouter | 262K | 🔧 Tool 🧠 Reason 👁️ Vision |
| google--gemma-4-31b-it--free | openrouter | 262K | 🔧 Tool 🧠 Reason 👁️ Vision |
| codestral | mistral | 256K | |
| nvidia--nemotron-3-nano-omni-30b-a3b-reasoning--free | openrouter | 256K | 🔧 Tool 🧠 Reason 👁️ Vision |
| hunyuan-lite | tencent | 250K | |
| minimax--minimax-m2.5--free | openrouter | 204K | 🔧 Tool 🧠 Reason |
0 models optimized for code generation, completion, and understanding.
| Model | Provider | Input $/M | Output $/M | Context | Capabilities |
|---|
1080 models with both tool calling and reasoning — the key capabilities for building AI agents.
| Model | Provider | Input $/M | Output $/M | Context | Capabilities |
|---|---|---|---|---|---|
| openai--gpt-oss-20b | neuralwatt | $0.03 | $0.16 | ? | 🔧 Tool 🧠 Reason |
| qwen--qwen3-4b-fp8 | novitaai | $0.03 | $0.03 | 128K | 🔧 Tool 🧠 Reason |
| gpt-oss-120b | inferencenet | $0.05 | $0.45 | 131K | 🔧 Tool 🧠 Reason |
| Qwen--Qwen3.6-35B-A3B | neuralwatt | $0.05 | $0.1 | ? | 🔧 Tool 🧠 Reason |
| openai--gpt-oss-120b | novitaai | $0.05 | $0.25 | 131K | 🔧 Tool 🧠 Reason |
| qwen3-30b-a3b-fp8 | cloudflare | $0.051 | $0.335 | 40K | 🔧 Tool 🧠 Reason |
| glm-4.7-flash | cloudflare | $0.06 | $0.4 | 131K | 🔧 Tool 🧠 Reason |
| Nemotron-3-Nano-Omni | nebius | $0.06 | $0.24 | 128K | 🔧 Tool 🧠 Reason |
| hermes-4-llama-3.1-8b | nousresearch | $0.06 | $0.12 | 131K | 🔧 Tool 🧠 Reason |
| seed-1.6-flash | bytedance | $0.07 | $0.3 | 262K | 🔧 Tool 🧠 Reason |
1306 models with advanced reasoning capabilities.
| Model | Provider | Input $/M | Output $/M | Context |
|---|---|---|---|---|
| qwen3.5-0.8b | deepinfra | $0.01 | $0.05 | 262K |
| qwen3.5-2b | deepinfra | $0.02 | $0.1 | 262K |
| gpt-oss-20b | deepinfra | $0.03 | $0.14 | 131K |
| qwen3.5-4b | deepinfra | $0.03 | $0.15 | 262K |
| openai--gpt-oss-20b | neuralwatt | $0.03 | $0.16 | ? |
| qwen--qwen3-4b-fp8 | novitaai | $0.03 | $0.03 | 128K |
| gpt-oss-120b | deepinfra | $0.039 | $0.19 | 131K |
| nvidia-nemotron-nano-9b-v2 | deepinfra | $0.04 | $0.16 | 131K |
| openai--gpt-oss-20b | novitaai | $0.04 | $0.15 | 131K |
| nemotron-3-nano-30b-a3b | deepinfra | $0.05 | $0.2 | 262K |
1487 models that can understand images and visual content.
| Model | Provider | Input $/M | Output $/M | Context |
|---|---|---|---|---|
| qwen3.5-0.8b | deepinfra | $0.01 | $0.05 | 262K |
| qwen3.5-2b | deepinfra | $0.02 | $0.1 | 262K |
| paddlepaddle--paddleocr-vl | novitaai | $0.02 | $0.02 | 16K |
| qwen3.5-4b | deepinfra | $0.03 | $0.15 | 262K |
| deepseek--deepseek-ocr-2 | novitaai | $0.03 | $0.03 | 8K |
| deepseek--deepseek-ocr | novitaai | $0.03 | $0.03 | 8K |
| reka-edge-2 | reka | $0.03 | $0.1 | 131K |
| zai-org--autoglm-phone-9b-multilingual | novitaai | $0.035 | $0.138 | 65K |
| gemini-1.5-flash-8b | deepinfra | $0.0375 | $0.15 | 1M |
| google-gemma-3-4b | amazon-bedrock | $0.04 | $0.08 | 131K |
Models with the largest context windows for processing long documents.
| Model | Provider | Context | Input $/M | Output $/M |
|---|---|---|---|---|
| meta-llama-4-scout | meta | 10M | $0.17 | $0.66 |
| gemini-1.5-pro | 2M | $1.25 | $5 | |
| xai--grok-4-fast-non-reasoning | aimlapi | 2M | $0.52 | $1.3 |
| xai--grok-4-fast-reasoning | aimlapi | 2M | $0.52 | $1.3 |
| meta-llama-4-maverick-17b | amazon-bedrock | 1M | $0.24 | $0.97 |
| meta-llama-4-scout-17b | amazon-bedrock | 1M | $0.17 | $0.66 |
| minimax-m2-1 | amazon-bedrock | 1M | $0.3 | $1.2 |
| minimax-m2-5 | amazon-bedrock | 1M | $0.3 | $1.2 |
| minimax-m2 | amazon-bedrock | 1M | $0.3 | $1.2 |
| deepseek-v4-flash | baidu | 1M | $0.126 | $0.252 |
527 models with downloadable weights you can run locally.
| Model | Provider | Context | Capabilities |
|---|---|---|---|
| google--gemma-4-31b-it | orcarouter | 1M | 🔧 Tool |
| qwen--qwen3.5-flash-2026-02-23 | orcarouter | 1M | 🔧 Tool |
| qwen--qwen3.5-flash | orcarouter | 1M | 🔧 Tool |
| qwen--qwen3.6-flash-2026-04-16 | orcarouter | 1M | 🔧 Tool |
| qwen--qwen3.6-flash | orcarouter | 1M | 🔧 Tool |
| MiniMax-Text-01 | 302ai | 1M | |
| llama-4-maverick | 302ai | 1M | |
| llama-4-scout | 302ai | 1M | |
| meta-llama-4-maverick-17b | amazon-bedrock | 1M | 🔧 Tool |
| meta-llama-4-scout-17b | amazon-bedrock | 1M | 🔧 Tool |
All data is sourced from first-party APIs — not third-party aggregators. Pricing, context windows, and capabilities are verified against official provider documentation. Aggregator providers (OpenRouter, Requesty, etc.) are excluded from ranking tables to avoid duplicate models.
Data is auto-scraped and validated with Zod schemas. Last updated: 2025-05-21.