AI Model Pricing & Specs Comparison
Updated 1/12/2026341+ ModelsVia OpenRouter
Compare the latest AI models including GPT-5, Claude Opus 4.5, Gemini 3 Pro, and open-source options. View detailed pricing, context windows, and technical specs to find the perfect model for your application.
Filters & Sorting
Showing 340 of 341 models
No limit
| Model Details | Input Price | Output Price | Context | Specs |
|---|---|---|---|---|
xAI: Grok 4.1 Fast▶ X-ai | Free per 1M tokens | Free per 1M tokens | 2.0M Max Out: 30K | text+image->text |
xAI: Grok 4.1 Fast (free)▶ X-ai | Free per 1M tokens | Free per 1M tokens | 2.0M Max Out: 30K | text+image->text |
Google: Gemini 2.0 Flash Experimental (free)▶ Google | Free per 1M tokens | Free per 1M tokens | 1.0M Max Out: 8K | text+image->text |
Qwen: Qwen3 Coder 480B A35B (free)▶ Qwen | Free per 1M tokens | Free per 1M tokens | 262K Max Out: 262K | text->text |
Kwaipilot: KAT-Coder-Pro V1 (free)▶ Kwaipilot | Free per 1M tokens | Free per 1M tokens | 256K Max Out: 32K | text->text |
TNG: DeepSeek R1T2 Chimera (free)▶ Tngtech | Free per 1M tokens | Free per 1M tokens | 164K Max Out: - | text->text |
DeepSeek: R1 0528 (free)▶ Deepseek | Free per 1M tokens | Free per 1M tokens | 164K Max Out: - | text->text |
TNG: DeepSeek R1T Chimera (free)▶ Tngtech | Free per 1M tokens | Free per 1M tokens | 164K Max Out: - | text->text |
Microsoft: MAI DS R1 (free)▶ Microsoft | Free per 1M tokens | Free per 1M tokens | 164K Max Out: - | text->text |
DeepSeek: DeepSeek V3 0324 (free)▶ Deepseek | Free per 1M tokens | Free per 1M tokens | 164K Max Out: - | text->text |
DeepSeek: R1 (free)▶ Deepseek | Free per 1M tokens | Free per 1M tokens | 164K Max Out: - | text->text |
Tongyi DeepResearch 30B A3B (free)▶ Alibaba | Free per 1M tokens | Free per 1M tokens | 131K Max Out: 131K | text->text |
Meituan: LongCat Flash Chat (free)▶ Meituan | Free per 1M tokens | Free per 1M tokens | 131K Max Out: 131K | text->text |
OpenAI: gpt-oss-20b (free)▶ Openai | Free per 1M tokens | Free per 1M tokens | 131K Max Out: 131K | text->text |
Z.AI: GLM 4.5 Air (free)▶ Z-ai | Free per 1M tokens | Free per 1M tokens | 131K Max Out: 131K | text->text |
Mistral: Mistral Small 3.2 24B (free)▶ Mistralai | Free per 1M tokens | Free per 1M tokens | 131K Max Out: - | text+image->text |
DeepSeek: DeepSeek R1 0528 Qwen3 8B (free)▶ Deepseek | Free per 1M tokens | Free per 1M tokens | 131K Max Out: - | text->text |
Google: Gemma 3 27B (free)▶ Google | Free per 1M tokens | Free per 1M tokens | 131K Max Out: - | text+image->text |
Meta: Llama 3.3 70B Instruct (free)▶ Meta-llama | Free per 1M tokens | Free per 1M tokens | 131K Max Out: - | text->text |
Meta: Llama 3.2 3B Instruct (free)▶ Meta-llama | Free per 1M tokens | Free per 1M tokens | 131K Max Out: - | text->text |
Nous: Hermes 3 405B Instruct (free)▶ Nousresearch | Free per 1M tokens | Free per 1M tokens | 131K Max Out: - | text->text |
Mistral: Mistral Nemo (free)▶ Mistralai | Free per 1M tokens | Free per 1M tokens | 131K Max Out: 128K | text->text |
NVIDIA: Nemotron Nano 12B 2 VL (free)▶ Nvidia | Free per 1M tokens | Free per 1M tokens | 128K Max Out: 128K | text+image->text |
NVIDIA: Nemotron Nano 9B V2 (free)▶ Nvidia | Free per 1M tokens | Free per 1M tokens | 128K Max Out: - | text->text |
Mistral: Mistral Small 3.1 24B (free)▶ Mistralai | Free per 1M tokens | Free per 1M tokens | 96K Max Out: 96K | text+image->text |
Qwen: Qwen3 4B (free)▶ Qwen | Free per 1M tokens | Free per 1M tokens | 41K Max Out: - | text->text |
Qwen: Qwen3 30B A3B (free)▶ Qwen | Free per 1M tokens | Free per 1M tokens | 41K Max Out: - | text->text |
Qwen: Qwen3 14B (free)▶ Qwen | Free per 1M tokens | Free per 1M tokens | 41K Max Out: - | text->text |
Qwen: Qwen3 235B A22B (free)▶ Qwen | Free per 1M tokens | Free per 1M tokens | 41K Max Out: - | text->text |
MoonshotAI: Kimi K2 0711 (free)▶ Moonshotai | Free per 1M tokens | Free per 1M tokens | 33K Max Out: - | text->text |
Venice: Uncensored (free)▶ Cognitivecomputations | Free per 1M tokens | Free per 1M tokens | 33K Max Out: - | text->text |
ArliAI: QwQ 32B RpR v1 (free)▶ Arliai | Free per 1M tokens | Free per 1M tokens | 33K Max Out: - | text->text |
Google: Gemma 3 4B (free)▶ Google | Free per 1M tokens | Free per 1M tokens | 33K Max Out: 8K | text+image->text |
Google: Gemma 3 12B (free)▶ Google | Free per 1M tokens | Free per 1M tokens | 33K Max Out: 8K | text+image->text |
Mistral: Mistral Small 3 (free)▶ Mistralai | Free per 1M tokens | Free per 1M tokens | 33K Max Out: - | text->text |
Qwen2.5 Coder 32B Instruct (free)▶ Qwen | Free per 1M tokens | Free per 1M tokens | 33K Max Out: - | text->text |
Qwen2.5 72B Instruct (free)▶ Qwen | Free per 1M tokens | Free per 1M tokens | 33K Max Out: - | text->text |
Mistral: Mistral 7B Instruct (free)▶ Mistralai | Free per 1M tokens | Free per 1M tokens | 33K Max Out: 16K | text->text |
Qwen: Qwen2.5 VL 32B Instruct (free)▶ Qwen | Free per 1M tokens | Free per 1M tokens | 16K Max Out: - | text+image->text |
Google: Gemma 3n 2B (free)▶ Google | Free per 1M tokens | Free per 1M tokens | 8K Max Out: 2K | text->text |
Google: Gemma 3n 4B (free)▶ Google | Free per 1M tokens | Free per 1M tokens | 8K Max Out: 2K | text->text |
DeepSeek: R1 Distill Llama 70B (free)▶ Deepseek | Free per 1M tokens | Free per 1M tokens | 8K Max Out: 4K | text->text |
IBM: Granite 4.0 Micro▶ Ibm-granite | $0.02 per 1M tokens | $0.11 per 1M tokens | 131K Max Out: - | text->text |
Google: Gemma 3 4B▶ Google | $0.02 per 1M tokens | $0.07 per 1M tokens | 96K Max Out: - | text+image->text |
Llama Guard 3 8B▶ Meta-llama | $0.02 per 1M tokens | $0.06 per 1M tokens | 131K Max Out: - | text->text |
Meta: Llama 3.2 3B Instruct▶ Meta-llama | $0.02 per 1M tokens | $0.02 per 1M tokens | 131K Max Out: 16K | text->text |
Meta: Llama 3.1 8B Instruct▶ Meta-llama | $0.02 per 1M tokens | $0.03 per 1M tokens | 131K Max Out: 16K | text->text |
Mistral: Mistral Nemo▶ Mistralai | $0.02 per 1M tokens | $0.04 per 1M tokens | 131K Max Out: 16K | text->text |
DeepSeek: DeepSeek R1 0528 Qwen3 8B▶ Deepseek | $0.02 per 1M tokens | $0.10 per 1M tokens | 33K Max Out: 33K | text->text |
Google: Gemma 3n 4B▶ Google | $0.02 per 1M tokens | $0.04 per 1M tokens | 33K Max Out: - | text->text |
NousResearch: Hermes 2 Pro - Llama-3 8B▶ Nousresearch | $0.02 per 1M tokens | $0.08 per 1M tokens | 8K Max Out: 2K | text->text |
Meta: Llama 3.2 1B Instruct▶ Meta-llama | $0.03 per 1M tokens | $0.20 per 1M tokens | 60K Max Out: - | text->text |
Mistral: Mistral 7B Instruct▶ Mistralai | $0.03 per 1M tokens | $0.05 per 1M tokens | 33K Max Out: 16K | text->text |
OpenAI: gpt-oss-20b▶ Openai | $0.03 per 1M tokens | $0.14 per 1M tokens | 131K Max Out: - | text->text |
Mistral: Mistral Small 3.1 24B▶ Mistralai | $0.03 per 1M tokens | $0.11 per 1M tokens | 131K Max Out: 131K | text+image->text |
Google: Gemma 3 12B▶ Google | $0.03 per 1M tokens | $0.10 per 1M tokens | 131K Max Out: 131K | text+image->text |
DeepSeek: R1 Distill Llama 70B▶ Deepseek | $0.03 per 1M tokens | $0.13 per 1M tokens | 131K Max Out: 131K | text->text |
Qwen: Qwen2.5 Coder 7B Instruct▶ Qwen | $0.03 per 1M tokens | $0.09 per 1M tokens | 33K Max Out: - | text->text |
ArliAI: QwQ 32B RpR v1▶ Arliai | $0.03 per 1M tokens | $0.11 per 1M tokens | 33K Max Out: 33K | text->text |
Google: Gemma 2 9B▶ Google | $0.03 per 1M tokens | $0.09 per 1M tokens | 8K Max Out: - | text->text |
Meta: Llama 3 8B Instruct▶ Meta-llama | $0.03 per 1M tokens | $0.06 per 1M tokens | 8K Max Out: 16K | text->text |
Qwen: Qwen3 8B▶ Qwen | $0.04 per 1M tokens | $0.14 per 1M tokens | 128K Max Out: 20K | text->text |
Amazon: Nova Micro 1.0▶ Amazon | $0.04 per 1M tokens | $0.14 per 1M tokens | 128K Max Out: 5K | text->text |
THUDM: GLM 4.1V 9B Thinking▶ Thudm | $0.04 per 1M tokens | $0.14 per 1M tokens | 66K Max Out: 8K | text+image->text |
Cohere: Command R7B (12-2024)▶ Cohere | $0.04 per 1M tokens | $0.15 per 1M tokens | 128K Max Out: 4K | text->text |
NVIDIA: Nemotron Nano 9B V2▶ Nvidia | $0.04 per 1M tokens | $0.16 per 1M tokens | 131K Max Out: - | text->text |
OpenAI: gpt-oss-120b▶ Openai | $0.04 per 1M tokens | $0.40 per 1M tokens | 131K Max Out: 131K | text->text |
Mistral: Ministral 3B▶ Mistralai | $0.04 per 1M tokens | $0.04 per 1M tokens | 131K Max Out: - | text->text |
Qwen2.5 Coder 32B Instruct▶ Qwen | $0.04 per 1M tokens | $0.16 per 1M tokens | 33K Max Out: 33K | text->text |
Qwen: Qwen2.5 7B Instruct▶ Qwen | $0.04 per 1M tokens | $0.10 per 1M tokens | 33K Max Out: - | text->text |
Sao10K: Llama 3 8B Lunaris▶ Sao10k | $0.04 per 1M tokens | $0.05 per 1M tokens | 8K Max Out: - | text->text |
Arcee AI: AFM 4.5B▶ Arcee-ai | $0.05 per 1M tokens | $0.15 per 1M tokens | 66K Max Out: - | text->text |
Meta: Llama 3.2 11B Vision Instruct▶ Meta-llama | $0.05 per 1M tokens | $0.05 per 1M tokens | 131K Max Out: 16K | text+image->text |
Qwen: Qwen-Turbo▶ Qwen | $0.05 per 1M tokens | $0.20 per 1M tokens | 1.0M Max Out: 8K | text->text |
OpenAI: GPT-5 Nano▶ Openai | $0.05 per 1M tokens | $0.40 per 1M tokens | 400K Max Out: 128K | text+image->text |
OpenAI: gpt-oss-120b (exacto)▶ Openai | $0.05 per 1M tokens | $0.24 per 1M tokens | 131K Max Out: - | text->text |
Microsoft: Phi 4 Multimodal Instruct▶ Microsoft | $0.05 per 1M tokens | $0.10 per 1M tokens | 131K Max Out: - | text+image->text |
Qwen: Qwen3 14B▶ Qwen | $0.05 per 1M tokens | $0.22 per 1M tokens | 41K Max Out: 41K | text->text |
Qwen: Qwen3 32B▶ Qwen | $0.05 per 1M tokens | $0.20 per 1M tokens | 41K Max Out: 41K | text->text |
LiquidAI/LFM2-8B-A1B▶ Liquid | $0.05 per 1M tokens | $0.10 per 1M tokens | 33K Max Out: - | text->text |
LiquidAI/LFM2-2.6B▶ Liquid | $0.05 per 1M tokens | $0.10 per 1M tokens | 33K Max Out: - | text->text |
Mistral: Mistral Small 3▶ Mistralai | $0.05 per 1M tokens | $0.08 per 1M tokens | 33K Max Out: 16K | text->text |
Qwen: Qwen2.5 VL 32B Instruct▶ Qwen | $0.05 per 1M tokens | $0.22 per 1M tokens | 16K Max Out: 16K | text+image->text |
Qwen: Qwen3 30B A3B Thinking 2507▶ Qwen | $0.05 per 1M tokens | $0.34 per 1M tokens | 33K Max Out: - | text->text |
Amazon: Nova Lite 1.0▶ Amazon | $0.06 per 1M tokens | $0.24 per 1M tokens | 300K Max Out: 5K | text+image->text |
Qwen: Qwen3 Coder 30B A3B Instruct▶ Qwen | $0.06 per 1M tokens | $0.25 per 1M tokens | 262K Max Out: 262K | text->text |
Mistral: Mistral Small 3.2 24B▶ Mistralai | $0.06 per 1M tokens | $0.18 per 1M tokens | 131K Max Out: 131K | text+image->text |
Mistral: Devstral Small 2505▶ Mistralai | $0.06 per 1M tokens | $0.12 per 1M tokens | 128K Max Out: - | text->text |
Qwen: Qwen3 30B A3B▶ Qwen | $0.06 per 1M tokens | $0.22 per 1M tokens | 41K Max Out: 41K | text->text |
Microsoft: Phi 4▶ Microsoft | $0.06 per 1M tokens | $0.14 per 1M tokens | 16K Max Out: - | text->text |
MythoMax 13B▶ Gryphe | $0.06 per 1M tokens | $0.06 per 1M tokens | 4K Max Out: - | text->text |
Baidu: ERNIE 4.5 21B A3B Thinking▶ Baidu | $0.07 per 1M tokens | $0.28 per 1M tokens | 131K Max Out: 66K | text->text |
Google: Gemma 3 27B▶ Google | $0.07 per 1M tokens | $0.50 per 1M tokens | 131K Max Out: 131K | text+image->text |
Mistral: Devstral Small 1.1▶ Mistralai | $0.07 per 1M tokens | $0.28 per 1M tokens | 128K Max Out: - | text->text |
Baidu: ERNIE 4.5 21B A3B▶ Baidu | $0.07 per 1M tokens | $0.28 per 1M tokens | 120K Max Out: 8K | text->text |
OpenGVLab: InternVL3 78B▶ Opengvlab | $0.07 per 1M tokens | $0.26 per 1M tokens | 33K Max Out: 33K | text+image->text |
Microsoft: Phi 4 Reasoning Plus▶ Microsoft | $0.07 per 1M tokens | $0.35 per 1M tokens | 33K Max Out: - | text->text |
Qwen2.5 72B Instruct▶ Qwen | $0.07 per 1M tokens | $0.26 per 1M tokens | 33K Max Out: 33K | text->text |
Google: Gemini 2.0 Flash Lite▶ Google | $0.07 per 1M tokens | $0.30 per 1M tokens | 1.0M Max Out: 8K | text+image->text |
OpenAI: gpt-oss-safeguard-20b▶ Openai | $0.07 per 1M tokens | $0.30 per 1M tokens | 131K Max Out: 66K | text->text |
Meta: Llama 4 Scout▶ Meta-llama | $0.08 per 1M tokens | $0.30 per 1M tokens | 328K Max Out: 16K | text+image->text |
Qwen: Qwen3 30B A3B Instruct 2507▶ Qwen | $0.08 per 1M tokens | $0.33 per 1M tokens | 262K Max Out: 262K | text->text |
Qwen: Qwen3 235B A22B Instruct 2507▶ Qwen | $0.08 per 1M tokens | $0.55 per 1M tokens | 262K Max Out: 262K | text->text |
Qwen: Qwen3 VL 8B Instruct▶ Qwen | $0.08 per 1M tokens | $0.50 per 1M tokens | 131K Max Out: 33K | text+image->text |
Qwen: Qwen2.5 VL 72B Instruct▶ Qwen | $0.08 per 1M tokens | $0.33 per 1M tokens | 33K Max Out: 33K | text+image->text |
Tongyi DeepResearch 30B A3B▶ Alibaba | $0.09 per 1M tokens | $0.40 per 1M tokens | 131K Max Out: 131K | text->text |
NeverSleep: Lumimaid v0.2 8B▶ Neversleep | $0.09 per 1M tokens | $0.60 per 1M tokens | 33K Max Out: - | text->text |
Google: Gemini 2.5 Flash Lite Preview 09-2025▶ Google | $0.10 per 1M tokens | $0.40 per 1M tokens | 1.0M Max Out: 66K | text+image->text |
Google: Gemini 2.5 Flash Lite▶ Google | $0.10 per 1M tokens | $0.40 per 1M tokens | 1.0M Max Out: 66K | text+image->text |
Google: Gemini 2.0 Flash▶ Google | $0.10 per 1M tokens | $0.40 per 1M tokens | 1.0M Max Out: 8K | text+image->text |
OpenAI: GPT-4.1 Nano▶ Openai | $0.10 per 1M tokens | $0.40 per 1M tokens | 1.0M Max Out: 33K | text+image->text |
Qwen: Qwen3 Next 80B A3B Instruct▶ Qwen | $0.10 per 1M tokens | $0.80 per 1M tokens | 262K Max Out: 262K | text->text |
NVIDIA: Llama 3.3 Nemotron Super 49B V1.5▶ Nvidia | $0.10 per 1M tokens | $0.40 per 1M tokens | 131K Max Out: - | text->text |
Mistral: Ministral 8B▶ Mistralai | $0.10 per 1M tokens | $0.10 per 1M tokens | 131K Max Out: - | text->text |
Z.AI: GLM 4 32B ▶ Z-ai | $0.10 per 1M tokens | $0.10 per 1M tokens | 128K Max Out: - | text->text |
ByteDance: UI-TARS 7B ▶ Bytedance | $0.10 per 1M tokens | $0.20 per 1M tokens | 128K Max Out: 2K | text+image->text |
Microsoft: Phi-3.5 Mini 128K Instruct▶ Microsoft | $0.10 per 1M tokens | $0.10 per 1M tokens | 128K Max Out: - | text->text |
Microsoft: Phi-3 Mini 128K Instruct▶ Microsoft | $0.10 per 1M tokens | $0.10 per 1M tokens | 128K Max Out: - | text->text |
AllenAI: Olmo 3 7B Instruct▶ Allenai | $0.10 per 1M tokens | $0.20 per 1M tokens | 66K Max Out: 66K | text->text |
Mistral: Pixtral 12B▶ Mistralai | $0.10 per 1M tokens | $0.10 per 1M tokens | 33K Max Out: - | text+image->text |
Mistral: Voxtral Small 24B 2507▶ Mistralai | $0.10 per 1M tokens | $0.30 per 1M tokens | 32K Max Out: - | text->text |
Qwen: Qwen3 235B A22B Thinking 2507▶ Qwen | $0.11 per 1M tokens | $0.60 per 1M tokens | 262K Max Out: 262K | text->text |
Nous: Hermes 4 70B▶ Nousresearch | $0.11 per 1M tokens | $0.38 per 1M tokens | 131K Max Out: 131K | text->text |
Mistral: Mistral 7B Instruct v0.1▶ Mistralai | $0.11 per 1M tokens | $0.19 per 1M tokens | 3K Max Out: - | text->text |
AllenAI: Olmo 3 7B Think▶ Allenai | $0.12 per 1M tokens | $0.20 per 1M tokens | 66K Max Out: 66K | text->text |
Z.AI: GLM 4.5 Air▶ Z-ai | $0.13 per 1M tokens | $0.85 per 1M tokens | 131K Max Out: 98K | text->text |
Meta: Llama 3.3 70B Instruct▶ Meta-llama | $0.13 per 1M tokens | $0.38 per 1M tokens | 131K Max Out: 16K | text->text |
Tencent: Hunyuan A13B Instruct▶ Tencent | $0.14 per 1M tokens | $0.57 per 1M tokens | 131K Max Out: 131K | text->text |
Baidu: ERNIE 4.5 VL 28B A3B▶ Baidu | $0.14 per 1M tokens | $0.56 per 1M tokens | 30K Max Out: 8K | text+image->text |
Meta: Llama 4 Maverick▶ Meta-llama | $0.15 per 1M tokens | $0.60 per 1M tokens | 1.0M Max Out: 16K | text+image->text |
Qwen: Qwen3 VL 30B A3B Instruct▶ Qwen | $0.15 per 1M tokens | $0.60 per 1M tokens | 262K Max Out: - | text+image->text |
Qwen: Qwen3 Next 80B A3B Thinking▶ Qwen | $0.15 per 1M tokens | $1.20 per 1M tokens | 262K Max Out: 262K | text->text |
Meituan: LongCat Flash Chat▶ Meituan | $0.15 per 1M tokens | $0.75 per 1M tokens | 131K Max Out: 131K | text->text |
OpenAI: GPT-4o-mini Search Preview▶ Openai | $0.15 per 1M tokens | $0.60 per 1M tokens | 128K Max Out: 16K | text->text |
Cohere: Command R (08-2024)▶ Cohere | $0.15 per 1M tokens | $0.60 per 1M tokens | 128K Max Out: 4K | text->text |
OpenAI: GPT-4o-mini (2024-07-18)▶ Openai | $0.15 per 1M tokens | $0.60 per 1M tokens | 128K Max Out: 16K | text+image->text |
OpenAI: GPT-4o-mini▶ Openai | $0.15 per 1M tokens | $0.60 per 1M tokens | 128K Max Out: 16K | text+image->text |
Nous: DeepHermes 3 Mistral 24B Preview▶ Nousresearch | $0.15 per 1M tokens | $0.59 per 1M tokens | 33K Max Out: 33K | text->text |
Qwen: QwQ 32B▶ Qwen | $0.15 per 1M tokens | $0.40 per 1M tokens | 33K Max Out: - | text->text |
DeepSeek: R1 Distill Qwen 14B▶ Deepseek | $0.15 per 1M tokens | $0.15 per 1M tokens | 33K Max Out: 16K | text->text |
TheDrummer: Rocinante 12B▶ Thedrummer | $0.17 per 1M tokens | $0.43 per 1M tokens | 33K Max Out: - | text->text |
Qwen: Qwen3 VL 8B Thinking▶ Qwen | $0.18 per 1M tokens | $2.10 per 1M tokens | 256K Max Out: 33K | text+image->text |
Meta: Llama Guard 4 12B▶ Meta-llama | $0.18 per 1M tokens | $0.18 per 1M tokens | 164K Max Out: - | text+image->text |
Arcee AI: Spotlight▶ Arcee-ai | $0.18 per 1M tokens | $0.18 per 1M tokens | 131K Max Out: 66K | text+image->text |
Qwen: Qwen3 235B A22B▶ Qwen | $0.18 per 1M tokens | $0.54 per 1M tokens | 41K Max Out: 41K | text->text |
Cogito V2 Preview Llama 109B▶ Deepcogito | $0.18 per 1M tokens | $0.59 per 1M tokens | 33K Max Out: - | text+image->text |
xAI: Grok 4 Fast▶ X-ai | $0.20 per 1M tokens | $0.50 per 1M tokens | 2.0M Max Out: 30K | text+image->text |
MiniMax: MiniMax-01▶ Minimax | $0.20 per 1M tokens | $1.10 per 1M tokens | 1.0M Max Out: 1.0M | text+image->text |
xAI: Grok Code Fast 1▶ X-ai | $0.20 per 1M tokens | $1.50 per 1M tokens | 256K Max Out: 10K | text->text |
AI21: Jamba Mini 1.7▶ Ai21 | $0.20 per 1M tokens | $0.40 per 1M tokens | 256K Max Out: 4K | text->text |
DeepSeek: DeepSeek V3.1▶ Deepseek | $0.20 per 1M tokens | $0.80 per 1M tokens | 164K Max Out: 164K | text->text |
DeepSeek: R1 0528▶ Deepseek | $0.20 per 1M tokens | $4.50 per 1M tokens | 164K Max Out: 164K | text->text |
NVIDIA: Nemotron Nano 12B 2 VL▶ Nvidia | $0.20 per 1M tokens | $0.60 per 1M tokens | 131K Max Out: - | text+image->text |
Qwen: Qwen3 VL 30B A3B Thinking▶ Qwen | $0.20 per 1M tokens | $1.00 per 1M tokens | 131K Max Out: 33K | text+image->text |
AllenAI: Olmo 3 32B Think▶ Allenai | $0.20 per 1M tokens | $0.35 per 1M tokens | 66K Max Out: 66K | text->text |
Mistral: Saba▶ Mistralai | $0.20 per 1M tokens | $0.60 per 1M tokens | 33K Max Out: - | text->text |
AionLabs: Aion-RP 1.0 (8B)▶ Aion-labs | $0.20 per 1M tokens | $0.20 per 1M tokens | 33K Max Out: 33K | text->text |
Qwen: Qwen2.5-VL 7B Instruct▶ Qwen | $0.20 per 1M tokens | $0.20 per 1M tokens | 33K Max Out: - | text+image->text |
Mistral: Mistral 7B Instruct v0.3▶ Mistralai | $0.20 per 1M tokens | $0.20 per 1M tokens | 33K Max Out: 4K | text->text |
Mistral Small▶ Mistralai | $0.20 per 1M tokens | $0.60 per 1M tokens | 33K Max Out: - | text->text |
Mistral: Mistral 7B Instruct v0.2▶ Mistralai | $0.20 per 1M tokens | $0.20 per 1M tokens | 33K Max Out: - | text->text |
Meta: LlamaGuard 2 8B▶ Meta-llama | $0.20 per 1M tokens | $0.20 per 1M tokens | 8K Max Out: - | text->text |
AllenAI: Olmo 2 32B Instruct▶ Allenai | $0.20 per 1M tokens | $0.35 per 1M tokens | 4K Max Out: 4K | text->text |
Qwen: Qwen3 VL 235B A22B Instruct▶ Qwen | $0.21 per 1M tokens | $1.90 per 1M tokens | 131K Max Out: 33K | text+image->text |
Qwen: Qwen VL Plus▶ Qwen | $0.21 per 1M tokens | $0.63 per 1M tokens | 8K Max Out: 2K | text+image->text |
Qwen: Qwen3 Coder 480B A35B▶ Qwen | $0.22 per 1M tokens | $0.95 per 1M tokens | 262K Max Out: 262K | text->text |
DeepSeek: DeepSeek V3.1 Terminus▶ Deepseek | $0.23 per 1M tokens | $0.90 per 1M tokens | 164K Max Out: 164K | text->text |
DeepSeek: DeepSeek V3 0324▶ Deepseek | $0.24 per 1M tokens | $0.84 per 1M tokens | 164K Max Out: 164K | text->text |
OpenAI: GPT-5.1-Codex-Mini▶ Openai | $0.25 per 1M tokens | $2.00 per 1M tokens | 400K Max Out: 100K | text+image->text |
OpenAI: GPT-5 Mini▶ Openai | $0.25 per 1M tokens | $2.00 per 1M tokens | 400K Max Out: 128K | text+image->text |
Anthropic: Claude 3 Haiku▶ Anthropic | $0.25 per 1M tokens | $1.25 per 1M tokens | 200K Max Out: 4K | text+image->text |
Inception: Mercury▶ Inception | $0.25 per 1M tokens | $1.00 per 1M tokens | 128K Max Out: 16K | text->text |
Inception: Mercury Coder▶ Inception | $0.25 per 1M tokens | $1.00 per 1M tokens | 128K Max Out: 16K | text->text |
Mistral Tiny▶ Mistralai | $0.25 per 1M tokens | $0.25 per 1M tokens | 33K Max Out: - | text->text |
MiniMax: MiniMax M2▶ Minimax | $0.26 per 1M tokens | $1.02 per 1M tokens | 205K Max Out: 131K | text->text |
DeepSeek: DeepSeek V3.2 Exp▶ Deepseek | $0.27 per 1M tokens | $0.40 per 1M tokens | 164K Max Out: - | text->text |
DeepSeek: DeepSeek V3.1 Terminus (exacto)▶ Deepseek | $0.27 per 1M tokens | $1.00 per 1M tokens | 131K Max Out: 66K | text->text |
DeepSeek: R1 Distill Qwen 32B▶ Deepseek | $0.27 per 1M tokens | $0.27 per 1M tokens | 131K Max Out: - | text->text |
Baidu: ERNIE 4.5 300B A47B ▶ Baidu | $0.28 per 1M tokens | $1.10 per 1M tokens | 123K Max Out: 12K | text->text |
MoonshotAI: Kimi Dev 72B▶ Moonshotai | $0.29 per 1M tokens | $1.15 per 1M tokens | 131K Max Out: 131K | text->text |
Google: Gemini 2.5 Flash Preview 09-2025▶ Google | $0.30 per 1M tokens | $2.50 per 1M tokens | 1.0M Max Out: 66K | text+image->text |
Google: Gemini 2.5 Flash▶ Google | $0.30 per 1M tokens | $2.50 per 1M tokens | 1.0M Max Out: 66K | text+image->text |
Qwen: Qwen3 VL 235B A22B Thinking▶ Qwen | $0.30 per 1M tokens | $1.20 per 1M tokens | 262K Max Out: 262K | text+image->text |
Mistral: Codestral 2508▶ Mistralai | $0.30 per 1M tokens | $0.90 per 1M tokens | 256K Max Out: - | text->text |
Mistral: Codestral 2501▶ Mistralai | $0.30 per 1M tokens | $0.90 per 1M tokens | 256K Max Out: - | text->text |
TNG: DeepSeek R1T2 Chimera▶ Tngtech | $0.30 per 1M tokens | $1.20 per 1M tokens | 164K Max Out: 164K | text->text |
TNG: DeepSeek R1T Chimera▶ Tngtech | $0.30 per 1M tokens | $1.20 per 1M tokens | 164K Max Out: 164K | text->text |
Microsoft: MAI DS R1▶ Microsoft | $0.30 per 1M tokens | $1.20 per 1M tokens | 164K Max Out: 164K | text->text |
DeepSeek: R1▶ Deepseek | $0.30 per 1M tokens | $1.20 per 1M tokens | 164K Max Out: - | text->text |
DeepSeek: DeepSeek V3▶ Deepseek | $0.30 per 1M tokens | $1.20 per 1M tokens | 164K Max Out: 164K | text->text |
TheDrummer: Cydonia 24B V4.1▶ Thedrummer | $0.30 per 1M tokens | $0.50 per 1M tokens | 131K Max Out: 131K | text->text |
Nous: Hermes 4 405B▶ Nousresearch | $0.30 per 1M tokens | $1.20 per 1M tokens | 131K Max Out: 131K | text->text |
xAI: Grok 3 Mini▶ X-ai | $0.30 per 1M tokens | $0.50 per 1M tokens | 131K Max Out: - | text->text |
xAI: Grok 3 Mini Beta▶ X-ai | $0.30 per 1M tokens | $0.50 per 1M tokens | 131K Max Out: - | text->text |
Qwen: Qwen3 Coder Flash▶ Qwen | $0.30 per 1M tokens | $1.50 per 1M tokens | 128K Max Out: 66K | text->text |
Nous: Hermes 3 70B Instruct▶ Nousresearch | $0.30 per 1M tokens | $0.30 per 1M tokens | 66K Max Out: - | text->text |
Google: Gemini 2.5 Flash Image (Nano Banana)▶ Google | $0.30 per 1M tokens | $2.50 per 1M tokens | 33K Max Out: 33K | text+image->text+image |
Google: Gemini 2.5 Flash Image Preview (Nano Banana)▶ Google | $0.30 per 1M tokens | $2.50 per 1M tokens | 33K Max Out: 33K | text+image->text+image |
Meta: Llama 3 70B Instruct▶ Meta-llama | $0.30 per 1M tokens | $0.40 per 1M tokens | 8K Max Out: 16K | text->text |
Z.AI: GLM 4.5▶ Z-ai | $0.35 per 1M tokens | $1.50 per 1M tokens | 131K Max Out: 131K | text->text |
Meta: Llama 3.2 90B Vision Instruct▶ Meta-llama | $0.35 per 1M tokens | $0.40 per 1M tokens | 33K Max Out: 16K | text+image->text |
Qwen: Qwen3 Coder 480B A35B (exacto)▶ Qwen | $0.38 per 1M tokens | $1.53 per 1M tokens | 262K Max Out: 262K | text->text |
MoonshotAI: Kimi K2 0905▶ Moonshotai | $0.39 per 1M tokens | $1.90 per 1M tokens | 262K Max Out: 262K | text->text |
OpenAI: GPT-4.1 Mini▶ Openai | $0.40 per 1M tokens | $1.60 per 1M tokens | 1.0M Max Out: 33K | text+image->text |
Qwen: Qwen Plus 0728▶ Qwen | $0.40 per 1M tokens | $1.20 per 1M tokens | 1.0M Max Out: 33K | text->text |
Qwen: Qwen Plus 0728 (thinking)▶ Qwen | $0.40 per 1M tokens | $4.00 per 1M tokens | 1.0M Max Out: 33K | text->text |
MiniMax: MiniMax M1▶ Minimax | $0.40 per 1M tokens | $2.20 per 1M tokens | 1.0M Max Out: 40K | text->text |
Z.AI: GLM 4.6▶ Z-ai | $0.40 per 1M tokens | $1.75 per 1M tokens | 203K Max Out: 203K | text->text |
Mistral: Mistral Medium 3.1▶ Mistralai | $0.40 per 1M tokens | $2.00 per 1M tokens | 131K Max Out: - | text+image->text |
Mistral: Devstral Medium▶ Mistralai | $0.40 per 1M tokens | $2.00 per 1M tokens | 131K Max Out: - | text->text |
Mistral: Mistral Medium 3▶ Mistralai | $0.40 per 1M tokens | $2.00 per 1M tokens | 131K Max Out: - | text+image->text |
Qwen: Qwen-Plus▶ Qwen | $0.40 per 1M tokens | $1.20 per 1M tokens | 131K Max Out: 8K | text->text |
Meta: Llama 3.1 70B Instruct▶ Meta-llama | $0.40 per 1M tokens | $0.40 per 1M tokens | 131K Max Out: - | text->text |
TheDrummer: UnslopNemo 12B▶ Thedrummer | $0.40 per 1M tokens | $0.40 per 1M tokens | 33K Max Out: - | text->text |
Baidu: ERNIE 4.5 VL 424B A47B ▶ Baidu | $0.42 per 1M tokens | $1.25 per 1M tokens | 123K Max Out: 16K | text+image->text |
MoonshotAI: Kimi K2 Thinking▶ Moonshotai | $0.45 per 1M tokens | $2.35 per 1M tokens | 262K Max Out: 16K | text->text |
Z.AI: GLM 4.6 (exacto)▶ Z-ai | $0.45 per 1M tokens | $1.90 per 1M tokens | 203K Max Out: - | text->text |
ReMM SLERP 13B▶ Undi95 | $0.45 per 1M tokens | $0.65 per 1M tokens | 6K Max Out: - | text->text |
WizardLM-2 8x22B▶ Microsoft | $0.48 per 1M tokens | $0.48 per 1M tokens | 66K Max Out: 16K | text->text |
MoonshotAI: Kimi Linear 48B A3B Instruct▶ Moonshotai | $0.50 per 1M tokens | $0.60 per 1M tokens | 1.0M Max Out: 1.0M | text->text |
DeepSeek: DeepSeek Prover V2▶ Deepseek | $0.50 per 1M tokens | $2.18 per 1M tokens | 164K Max Out: - | text->text |
MoonshotAI: Kimi K2 0711▶ Moonshotai | $0.50 per 1M tokens | $2.40 per 1M tokens | 131K Max Out: - | text->text |
Mistral: Magistral Small 2506▶ Mistralai | $0.50 per 1M tokens | $1.50 per 1M tokens | 40K Max Out: 40K | text->text |
Arcee AI: Coder Large▶ Arcee-ai | $0.50 per 1M tokens | $0.80 per 1M tokens | 33K Max Out: - | text->text |
TheDrummer: Skyfall 36B V2▶ Thedrummer | $0.50 per 1M tokens | $0.80 per 1M tokens | 33K Max Out: 33K | text->text |
OpenAI: GPT-3.5 Turbo▶ Openai | $0.50 per 1M tokens | $1.50 per 1M tokens | 16K Max Out: 4K | text->text |
Mistral: Mixtral 8x7B Instruct▶ Mistralai | $0.54 per 1M tokens | $0.54 per 1M tokens | 33K Max Out: 16K | text->text |
StepFun: Step3▶ Stepfun-ai | $0.57 per 1M tokens | $1.42 per 1M tokens | 66K Max Out: 66K | text+image->text |
MoonshotAI: Kimi K2 0905 (exacto)▶ Moonshotai | $0.60 per 1M tokens | $2.50 per 1M tokens | 262K Max Out: - | text->text |
NVIDIA: Llama 3.1 Nemotron Ultra 253B v1▶ Nvidia | $0.60 per 1M tokens | $1.80 per 1M tokens | 131K Max Out: - | text->text |
Z.AI: GLM 4.5V▶ Z-ai | $0.60 per 1M tokens | $1.80 per 1M tokens | 66K Max Out: 16K | text+image->text |
TheDrummer: Anubis 70B V1.1▶ Thedrummer | $0.65 per 1M tokens | $1.00 per 1M tokens | 131K Max Out: 131K | text->text |
Sao10K: Llama 3.3 Euryale 70B▶ Sao10k | $0.65 per 1M tokens | $0.75 per 1M tokens | 131K Max Out: 16K | text->text |
Sao10K: Llama 3.1 Euryale 70B v2.2▶ Sao10k | $0.65 per 1M tokens | $0.75 per 1M tokens | 33K Max Out: - | text->text |
Google: Gemma 2 27B▶ Google | $0.65 per 1M tokens | $0.65 per 1M tokens | 8K Max Out: - | text->text |
AionLabs: Aion-1.0-Mini▶ Aion-labs | $0.70 per 1M tokens | $1.40 per 1M tokens | 131K Max Out: 33K | text->text |
Arcee AI: Virtuoso Large▶ Arcee-ai | $0.75 per 1M tokens | $1.20 per 1M tokens | 131K Max Out: 64K | text->text |
Amazon: Nova Pro 1.0▶ Amazon | $0.80 per 1M tokens | $3.20 per 1M tokens | 300K Max Out: 5K | text+image->text |
Anthropic: Claude 3.5 Haiku (2024-10-22)▶ Anthropic | $0.80 per 1M tokens | $4.00 per 1M tokens | 200K Max Out: 8K | text+image->text |
Anthropic: Claude 3.5 Haiku▶ Anthropic | $0.80 per 1M tokens | $4.00 per 1M tokens | 200K Max Out: 8K | text+image->text |
Qwen: Qwen VL Max▶ Qwen | $0.80 per 1M tokens | $3.20 per 1M tokens | 131K Max Out: 8K | text+image->text |
Morph: Morph V3 Fast▶ Morph | $0.80 per 1M tokens | $1.20 per 1M tokens | 82K Max Out: 38K | text->text |
EleutherAI: Llemma 7b▶ Eleutherai | $0.80 per 1M tokens | $1.20 per 1M tokens | 4K Max Out: 4K | text->text |
AlfredPros: CodeLLaMa 7B Instruct Solidity▶ Alfredpros | $0.80 per 1M tokens | $1.20 per 1M tokens | 4K Max Out: 4K | text->text |
Relace: Relace Apply 3▶ Relace | $0.85 per 1M tokens | $1.25 per 1M tokens | 256K Max Out: 128K | text->text |
Switchpoint Router▶ Switchpoint | $0.85 per 1M tokens | $3.40 per 1M tokens | 131K Max Out: - | text->text |
Deep Cogito: Cogito V2 Preview Llama 70B▶ Deepcogito | $0.88 per 1M tokens | $0.88 per 1M tokens | 33K Max Out: - | text->text |
Morph: Morph V3 Large▶ Morph | $0.90 per 1M tokens | $1.90 per 1M tokens | 262K Max Out: 131K | text->text |
Arcee AI: Maestro Reasoning▶ Arcee-ai | $0.90 per 1M tokens | $3.30 per 1M tokens | 131K Max Out: 32K | text->text |
Anthropic: Claude Haiku 4.5▶ Anthropic | $1.00 per 1M tokens | $5.00 per 1M tokens | 200K Max Out: 64K | text+image->text |
Nous: Hermes 3 405B Instruct▶ Nousresearch | $1.00 per 1M tokens | $1.00 per 1M tokens | 131K Max Out: 16K | text->text |
Qwen: Qwen3 Coder Plus▶ Qwen | $1.00 per 1M tokens | $5.00 per 1M tokens | 128K Max Out: 66K | text->text |
Microsoft: Phi-3 Medium 128K Instruct▶ Microsoft | $1.00 per 1M tokens | $1.00 per 1M tokens | 128K Max Out: - | text->text |
Perplexity: Sonar▶ Perplexity | $1.00 per 1M tokens | $1.00 per 1M tokens | 127K Max Out: - | text+image->text |
Perplexity: Sonar Reasoning▶ Perplexity | $1.00 per 1M tokens | $5.00 per 1M tokens | 127K Max Out: - | text->text |
Noromaid 20B▶ Neversleep | $1.00 per 1M tokens | $1.75 per 1M tokens | 4K Max Out: - | text->text |
OpenAI: GPT-3.5 Turbo (older v0613)▶ Openai | $1.00 per 1M tokens | $2.00 per 1M tokens | 4K Max Out: 4K | text->text |
OpenAI: o4 Mini High▶ Openai | $1.10 per 1M tokens | $4.40 per 1M tokens | 200K Max Out: 100K | text+image->text |
OpenAI: o4 Mini▶ Openai | $1.10 per 1M tokens | $4.40 per 1M tokens | 200K Max Out: 100K | text+image->text |
OpenAI: o3 Mini High▶ Openai | $1.10 per 1M tokens | $4.40 per 1M tokens | 200K Max Out: 100K | text->text |
OpenAI: o3 Mini▶ Openai | $1.10 per 1M tokens | $4.40 per 1M tokens | 200K Max Out: 100K | text->text |
Mancer: Weaver (alpha)▶ Mancer | $1.13 per 1M tokens | $1.13 per 1M tokens | 8K Max Out: 2K | text->text |
Qwen: Qwen3 Max▶ Qwen | $1.20 per 1M tokens | $6.00 per 1M tokens | 256K Max Out: 33K | text->text |
NVIDIA: Llama 3.1 Nemotron 70B Instruct▶ Nvidia | $1.20 per 1M tokens | $1.20 per 1M tokens | 131K Max Out: 16K | text->text |
Google: Gemini 2.5 Pro▶ Google | $1.25 per 1M tokens | $10.00 per 1M tokens | 1.0M Max Out: 66K | text+image->text |
Google: Gemini 2.5 Pro Preview 06-05▶ Google | $1.25 per 1M tokens | $10.00 per 1M tokens | 1.0M Max Out: 66K | text+image->text |
Google: Gemini 2.5 Pro Preview 05-06▶ Google | $1.25 per 1M tokens | $10.00 per 1M tokens | 1.0M Max Out: 66K | text+image->text |
OpenAI: GPT-5.1▶ Openai | $1.25 per 1M tokens | $10.00 per 1M tokens | 400K Max Out: 128K | text+image->text |
OpenAI: GPT-5.1-Codex▶ Openai | $1.25 per 1M tokens | $10.00 per 1M tokens | 400K Max Out: 128K | text+image->text |
OpenAI: GPT-5 Codex▶ Openai | $1.25 per 1M tokens | $10.00 per 1M tokens | 400K Max Out: 128K | text+image->text |
OpenAI: GPT-5▶ Openai | $1.25 per 1M tokens | $10.00 per 1M tokens | 400K Max Out: 128K | text+image->text |
Deep Cogito: Cogito V2 Preview Deepseek 671B▶ Deepcogito | $1.25 per 1M tokens | $1.25 per 1M tokens | 164K Max Out: - | text->text |
Deep Cogito: Cogito v2.1 671B▶ Deepcogito | $1.25 per 1M tokens | $1.25 per 1M tokens | 128K Max Out: - | text->text |
OpenAI: GPT-5.1 Chat▶ Openai | $1.25 per 1M tokens | $10.00 per 1M tokens | 128K Max Out: 16K | text+image->text |
OpenAI: GPT-5 Chat▶ Openai | $1.25 per 1M tokens | $10.00 per 1M tokens | 128K Max Out: 16K | text+image->text |
Sao10k: Llama 3 Euryale 70B v2.1▶ Sao10k | $1.48 per 1M tokens | $1.48 per 1M tokens | 8K Max Out: 8K | text->text |
OpenAI: Codex Mini▶ Openai | $1.50 per 1M tokens | $6.00 per 1M tokens | 200K Max Out: 100K | text+image->text |
OpenAI: GPT-3.5 Turbo Instruct▶ Openai | $1.50 per 1M tokens | $2.00 per 1M tokens | 4K Max Out: 4K | text->text |
Qwen: Qwen-Max ▶ Qwen | $1.60 per 1M tokens | $6.40 per 1M tokens | 33K Max Out: 8K | text->text |
Google: Gemini 3 Pro Preview▶ Google | $2.00 per 1M tokens | $12.00 per 1M tokens | 1.0M Max Out: 66K | text+image->text |
OpenAI: GPT-4.1▶ Openai | $2.00 per 1M tokens | $8.00 per 1M tokens | 1.0M Max Out: 33K | text+image->text |
AI21: Jamba Large 1.7▶ Ai21 | $2.00 per 1M tokens | $8.00 per 1M tokens | 256K Max Out: 4K | text->text |
OpenAI: o4 Mini Deep Research▶ Openai | $2.00 per 1M tokens | $8.00 per 1M tokens | 200K Max Out: 100K | text+image->text |
OpenAI: o3▶ Openai | $2.00 per 1M tokens | $8.00 per 1M tokens | 200K Max Out: 100K | text+image->text |
Mistral Large 2411▶ Mistralai | $2.00 per 1M tokens | $6.00 per 1M tokens | 131K Max Out: - | text->text |
Mistral Large 2407▶ Mistralai | $2.00 per 1M tokens | $6.00 per 1M tokens | 131K Max Out: - | text->text |
Mistral: Pixtral Large 2411▶ Mistralai | $2.00 per 1M tokens | $6.00 per 1M tokens | 131K Max Out: - | text+image->text |
Perplexity: Sonar Reasoning Pro▶ Perplexity | $2.00 per 1M tokens | $8.00 per 1M tokens | 128K Max Out: - | text+image->text |
Perplexity: Sonar Deep Research▶ Perplexity | $2.00 per 1M tokens | $8.00 per 1M tokens | 128K Max Out: - | text->text |
Mistral Large▶ Mistralai | $2.00 per 1M tokens | $6.00 per 1M tokens | 128K Max Out: - | text->text |
Google: Nano Banana Pro (Gemini 3 Pro Image Preview)▶ Google | $2.00 per 1M tokens | $12.00 per 1M tokens | 66K Max Out: 33K | text+image->text+image |
Mistral: Mixtral 8x22B Instruct▶ Mistralai | $2.00 per 1M tokens | $6.00 per 1M tokens | 66K Max Out: - | text->text |
Mistral: Magistral Medium 2506 (thinking)▶ Mistralai | $2.00 per 1M tokens | $5.00 per 1M tokens | 41K Max Out: 40K | text->text |
Mistral: Magistral Medium 2506▶ Mistralai | $2.00 per 1M tokens | $5.00 per 1M tokens | 41K Max Out: 40K | text->text |
Amazon: Nova Premier 1.0▶ Amazon | $2.50 per 1M tokens | $12.50 per 1M tokens | 1.0M Max Out: 32K | text+image->text |
OpenAI: GPT-5 Image Mini▶ Openai | $2.50 per 1M tokens | $2.00 per 1M tokens | 400K Max Out: 128K | text+image->text+image |
Cohere: Command A▶ Cohere | $2.50 per 1M tokens | $10.00 per 1M tokens | 256K Max Out: 8K | text->text |
OpenAI: GPT-4o Audio▶ Openai | $2.50 per 1M tokens | $10.00 per 1M tokens | 128K Max Out: 16K | text->text |
OpenAI: GPT-4o Search Preview▶ Openai | $2.50 per 1M tokens | $10.00 per 1M tokens | 128K Max Out: 16K | text->text |
OpenAI: GPT-4o (2024-11-20)▶ Openai | $2.50 per 1M tokens | $10.00 per 1M tokens | 128K Max Out: 16K | text+image->text |
Cohere: Command R+ (08-2024)▶ Cohere | $2.50 per 1M tokens | $10.00 per 1M tokens | 128K Max Out: 4K | text->text |
OpenAI: GPT-4o (2024-08-06)▶ Openai | $2.50 per 1M tokens | $10.00 per 1M tokens | 128K Max Out: 16K | text+image->text |
OpenAI: GPT-4o▶ Openai | $2.50 per 1M tokens | $10.00 per 1M tokens | 128K Max Out: 16K | text+image->text |
Inflection: Inflection 3 Pi▶ Inflection | $2.50 per 1M tokens | $10.00 per 1M tokens | 8K Max Out: 1K | text->text |
Inflection: Inflection 3 Productivity▶ Inflection | $2.50 per 1M tokens | $10.00 per 1M tokens | 8K Max Out: 1K | text->text |
Anthropic: Claude Sonnet 4.5▶ Anthropic | $3.00 per 1M tokens | $15.00 per 1M tokens | 1.0M Max Out: 64K | text+image->text |
Anthropic: Claude Sonnet 4▶ Anthropic | $3.00 per 1M tokens | $15.00 per 1M tokens | 1.0M Max Out: 64K | text+image->text |
xAI: Grok 4▶ X-ai | $3.00 per 1M tokens | $15.00 per 1M tokens | 256K Max Out: - | text+image->text |
Perplexity: Sonar Pro Search▶ Perplexity | $3.00 per 1M tokens | $15.00 per 1M tokens | 200K Max Out: 8K | text+image->text |
Perplexity: Sonar Pro▶ Perplexity | $3.00 per 1M tokens | $15.00 per 1M tokens | 200K Max Out: 8K | text+image->text |
Anthropic: Claude 3.7 Sonnet (thinking)▶ Anthropic | $3.00 per 1M tokens | $15.00 per 1M tokens | 200K Max Out: 64K | text+image->text |
Anthropic: Claude 3.7 Sonnet▶ Anthropic | $3.00 per 1M tokens | $15.00 per 1M tokens | 200K Max Out: 64K | text+image->text |
Anthropic: Claude 3.5 Sonnet▶ Anthropic | $3.00 per 1M tokens | $15.00 per 1M tokens | 200K Max Out: 8K | text+image->text |
xAI: Grok 3▶ X-ai | $3.00 per 1M tokens | $15.00 per 1M tokens | 131K Max Out: - | text->text |
xAI: Grok 3 Beta▶ X-ai | $3.00 per 1M tokens | $15.00 per 1M tokens | 131K Max Out: - | text->text |
OpenAI: GPT-3.5 Turbo 16k▶ Openai | $3.00 per 1M tokens | $4.00 per 1M tokens | 16K Max Out: 4K | text->text |
Magnum v4 72B▶ Anthracite-org | $3.00 per 1M tokens | $5.00 per 1M tokens | 16K Max Out: 2K | text->text |
Sao10K: Llama 3.1 70B Hanami x1▶ Sao10k | $3.00 per 1M tokens | $3.00 per 1M tokens | 16K Max Out: - | text->text |
Meta: Llama 3.1 405B Instruct▶ Meta-llama | $3.50 per 1M tokens | $3.50 per 1M tokens | 131K Max Out: - | text->text |
Deep Cogito: Cogito V2 Preview Llama 405B▶ Deepcogito | $3.50 per 1M tokens | $3.50 per 1M tokens | 33K Max Out: - | text->text |
AionLabs: Aion-1.0▶ Aion-labs | $4.00 per 1M tokens | $8.00 per 1M tokens | 131K Max Out: 33K | text->text |
Meta: Llama 3.1 405B (base)▶ Meta-llama | $4.00 per 1M tokens | $4.00 per 1M tokens | 33K Max Out: 33K | text->text |
SorcererLM 8x22B▶ Raifle | $4.50 per 1M tokens | $4.50 per 1M tokens | 16K Max Out: - | text->text |
OpenAI: ChatGPT-4o▶ Openai | $5.00 per 1M tokens | $15.00 per 1M tokens | 128K Max Out: 16K | text+image->text |
OpenAI: GPT-4o (2024-05-13)▶ Openai | $5.00 per 1M tokens | $15.00 per 1M tokens | 128K Max Out: 4K | text+image->text |
OpenAI: GPT-4o (extended)▶ Openai | $6.00 per 1M tokens | $18.00 per 1M tokens | 128K Max Out: 64K | text+image->text |
Goliath 120B▶ Alpindale | $6.00 per 1M tokens | $8.00 per 1M tokens | 6K Max Out: 1K | text->text |
OpenAI: GPT-5 Image▶ Openai | $10.00 per 1M tokens | $10.00 per 1M tokens | 400K Max Out: 128K | text+image->text+image |
OpenAI: o3 Deep Research▶ Openai | $10.00 per 1M tokens | $40.00 per 1M tokens | 200K Max Out: 100K | text+image->text |
OpenAI: GPT-4 Turbo▶ Openai | $10.00 per 1M tokens | $30.00 per 1M tokens | 128K Max Out: 4K | text+image->text |
OpenAI: GPT-4 Turbo Preview▶ Openai | $10.00 per 1M tokens | $30.00 per 1M tokens | 128K Max Out: 4K | text->text |
OpenAI: GPT-4 Turbo (older v1106)▶ Openai | $10.00 per 1M tokens | $30.00 per 1M tokens | 128K Max Out: 4K | text->text |
OpenAI: GPT-5 Pro▶ Openai | $15.00 per 1M tokens | $120.00 per 1M tokens | 400K Max Out: 128K | text+image->text |
Anthropic: Claude Opus 4.1▶ Anthropic | $15.00 per 1M tokens | $75.00 per 1M tokens | 200K Max Out: 32K | text+image->text |
Anthropic: Claude Opus 4▶ Anthropic | $15.00 per 1M tokens | $75.00 per 1M tokens | 200K Max Out: 32K | text+image->text |
OpenAI: o1▶ Openai | $15.00 per 1M tokens | $60.00 per 1M tokens | 200K Max Out: 100K | text+image->text |
Anthropic: Claude 3 Opus▶ Anthropic | $15.00 per 1M tokens | $75.00 per 1M tokens | 200K Max Out: 4K | text+image->text |
OpenAI: o3 Pro▶ Openai | $20.00 per 1M tokens | $80.00 per 1M tokens | 200K Max Out: 100K | text+image->text |
OpenAI: GPT-4▶ Openai | $30.00 per 1M tokens | $60.00 per 1M tokens | 8K Max Out: 4K | text->text |
OpenAI: GPT-4 (older v0314)▶ Openai | $30.00 per 1M tokens | $60.00 per 1M tokens | 8K Max Out: 4K | text->text |
Benchmark these models on your own prompts
Free tier: 6 curated models. Pro: any model from this list.
Model data sourced from OpenRouter. Prices and availability may change. Last synced: 1/12/2026.