LLM API pricing

Compare per-token prices across LLM API providers.

3,516
Chat models
18
Providers
Free
Lowest input / 1M tokens
10.5M
Largest context

LLM market heatmap

3,582 models grouped by vendor — click a vendor, then a family to filter the catalog

DEAL% · listings-weighted · signed (− red / + green) · n=24/29

Models

375 models
ModelProvidersInput from / 1MOutput from / 1MContextCapabilities
Cohere: North Mini Code (free)1FreeFree256,000 FC Reasoning
Dots Studio: Dots3-Note Preview (free)1FreeFree512,000Vision FC Reasoning
Google: Gemma 4 26B A4B (free)1FreeFree262,144Vision FC Reasoning
Google: Gemma 4 31B (free)1FreeFree262,144Vision FC Reasoning
inclusionAI: Ling 3.0 Flash Fin (free)1FreeFree262,144 FC Reasoning
inclusionAI: Ling 3.0 Flash Sante (free)1FreeFree262,144 FC Reasoning
inclusionAI: Ling 3.0 Flash VL (free)1FreeFree262,144Vision FC Reasoning
LiquidAI: LFM2.5-2.6B (free)1FreeFree65,536 FC Reasoning
Nex AGI: Nex-N2.5-Mini (free)1FreeFree262,144Vision FC Reasoning
Nex AGI: Nex-N2.5-Pro (free)1FreeFree262,144Vision FC Reasoning
NVIDIA: Nemotron 3 Nano Omni (free)1FreeFree256,000Vision FC Reasoning
NVIDIA: Nemotron 3 Super (free)1FreeFree262,144 FC Reasoning
NVIDIA: Nemotron 3 Ultra (free)1FreeFree1,000,000 FC Reasoning
NVIDIA: Nemotron 3.5 Lightning (free)1FreeFree1,000,000 FC Reasoning
Free Models Router1FreeFree200,000Vision FC Reasoning
Poolside: Laguna S 2.1 (free)1FreeFree262,144 FC Reasoning
Poolside: Laguna XS 2.1 (free)1FreeFree262,144 FC Reasoning
Thinking Machines: Inkling Small (free)1FreeFree1,048,576Vision FC Reasoning
Thinking Machines: Inkling (free)1FreeFree1,048,576Vision FC Reasoning
Mistral: Mistral Nemo1$0.02/1M tokens$0.03/1M tokens131,072 FC
inclusionAI: Ling 3.0 Flash1$0.02/1M tokens$0.06/1M tokens262,144 FC Reasoning
DeepSeek: DeepSeek V4 Flash Latest1$0.03/1M tokens$0.07/1M tokens1,310,720 FC Reasoning
DeepSeek: DeepSeek V4 Flash 07311$0.04/1M tokens$0.08/1M tokens1,310,720 FC Reasoning
Meta: Llama 3.1 8B Instruct1$0.05/1M tokens$0.08/1M tokens131,072 FC
Mistral: Ministral 3 8B 2512 (batch)1$0.08/1M tokens$0.08/1M tokens262,144Vision FC
Mistral: Ministral 3 3B 25121$0.10/1M tokens$0.10/1M tokens131,072Vision FC
Reka Edge1$0.10/1M tokens$0.10/1M tokens16,384Vision FC
Poolside: Laguna XS 2.11$0.06/1M tokens$0.12/1M tokens262,144 FC Reasoning
DeepSeek: DeepSeek V4 Flash 04231$0.07/1M tokens$0.13/1M tokens1,048,576 FC Reasoning
OpenAI: gpt-oss-20b1$0.03/1M tokens$0.13/1M tokens131,072 FC Reasoning
Qwen: Qwen3.7 Flash1$0.03/1M tokens$0.13/1M tokens1,000,000Vision FC Reasoning
Amazon: Nova Micro 1.01$0.04/1M tokens$0.14/1M tokens128,000 FC
Google: Gemma 3 12B1$0.05/1M tokens$0.15/1M tokens131,072Vision FC
Inception: Mercury 2.51$0.04/1M tokens$0.15/1M tokens260,000 FC Reasoning
Mistral: Ministral 3 8B 25121$0.15/1M tokens$0.15/1M tokens262,144Vision FC
Qwen: Qwen3.5-9B1$0.10/1M tokens$0.15/1M tokens262,144Vision FC Reasoning
OpenAI: gpt-oss-120b1$0.04/1M tokens$0.17/1M tokens131,072 FC Reasoning
inclusionAI: Ling 3.0 Flash Fin1$0.06/1M tokens$0.18/1M tokens262,144 FC Reasoning
inclusionAI: Ling 3.0 Flash VL1$0.06/1M tokens$0.18/1M tokens131,072Vision FC Reasoning
Poolside: Laguna S 2.11$0.09/1M tokens$0.18/1M tokens1,048,576 FC Reasoning
Google: Gemini 2.5 Flash Lite (batch)1$0.05/1M tokens$0.20/1M tokens1,048,576Vision FC Reasoning
Meta: Muse Spark 1.2 Contributor1$0.10/1M tokens$0.20/1M tokens1,048,576Vision FC Reasoning
Meta: Muse Spark 1.3 Contributor1$0.10/1M tokens$0.20/1M tokens1,048,576Vision FC Reasoning
Mistral: Ministral 3 14B 25121$0.20/1M tokens$0.20/1M tokens262,144Vision FC
Mistral: Mistral Small 3.2 24B1$0.08/1M tokens$0.20/1M tokens256,000Vision FC
NVIDIA: Nemotron 3 Nano 30B A3B1$0.05/1M tokens$0.20/1M tokens262,144 FC Reasoning
NVIDIA: Nemotron 3.5 Lightning1$0.08/1M tokens$0.20/1M tokens262,144 FC Reasoning
OpenAI: GPT-4.1 Nano (batch)1$0.05/1M tokens$0.20/1M tokens1,047,576Vision FC
OpenAI: GPT-5 Nano (batch)1$0.03/1M tokens$0.20/1M tokens400,000Vision FC Reasoning
Qwen: Qwen2.5 7B Instruct1$0.10/1M tokens$0.20/1M tokens32,768 FC
Google: Gemma 4 26B A4B 1$0.04/1M tokens$0.22/1M tokens262,144Vision FC Reasoning
Amazon: Nova Lite 1.01$0.06/1M tokens$0.24/1M tokens300,000Vision FC
IBM: Granite 4.2 8B1$0.06/1M tokens$0.25/1M tokens131,072 FC Reasoning
Qwen: Qwen3.5-9B (batch)1$0.17/1M tokens$0.25/1M tokens262,144Vision FC Reasoning
Z.ai: GLM 5.3 Flash (batch)1$0.08/1M tokens$0.25/1M tokens1,048,576Vision FC Reasoning
Z.ai: GLM Flash Latest1$0.08/1M tokens$0.25/1M tokens1,310,720Vision FC Reasoning
Qwen: Qwen3.5-Flash1$0.07/1M tokens$0.26/1M tokens1,000,000Vision FC Reasoning
Qwen: Qwen3 32B1$0.08/1M tokens$0.28/1M tokens131,072 FC Reasoning
Qwen: Qwen3 Coder 30B A3B Instruct1$0.07/1M tokens$0.28/1M tokens262,144 FC
Xiaomi: MiMo-V2.51$0.14/1M tokens$0.28/1M tokens1,050,000Vision FC Reasoning
ByteDance Seed: Seed 1.6 Flash1$0.08/1M tokens$0.30/1M tokens262,144Vision FC Reasoning
Meta: Llama 4 Scout1$0.10/1M tokens$0.30/1M tokens1,310,720Vision FC
Mistral: Mistral Small 4 (batch)1$0.08/1M tokens$0.30/1M tokens262,144Vision FC Reasoning
Mistral: Voxtral Small 24B 25071$0.10/1M tokens$0.30/1M tokens32,768 FC
OpenAI: GPT-4o-mini (batch)1$0.08/1M tokens$0.30/1M tokens128,000Vision FC
OpenAI: gpt-oss-safeguard-20b1$0.08/1M tokens$0.30/1M tokens131,072 FC Reasoning
Qwen: Qwen3 30B A3B Instruct 25071$0.09/1M tokens$0.30/1M tokens262,144 FC
StepFun: Step 3.5 Flash1$0.10/1M tokens$0.30/1M tokens262,144 FC Reasoning
Meta: Llama 3.3 70B Instruct1$0.10/1M tokens$0.32/1M tokens131,072 FC
DeepSeek: DeepSeek V4 Flash 0731 (batch)1$0.11/1M tokens$0.33/1M tokens1,048,576 FC Reasoning
DeepSeek: DeepSeek V4 Flash Vision Exp (batch)1$0.11/1M tokens$0.33/1M tokens1,048,576Vision FC Reasoning
Google: Gemma 4 31B1$0.09/1M tokens$0.34/1M tokens262,144Vision FC Reasoning
Qwen: Qwen3 235B A22B Instruct 25071$0.09/1M tokens$0.35/1M tokens262,144 FC
Upstage: Solar Pro 41$0.09/1M tokens$0.36/1M tokens524,288 FC Reasoning
ByteDance Seed: Seed-2.0-Mini1$0.10/1M tokens$0.40/1M tokens262,144Vision FC Reasoning
DeepSeek: DeepSeek V3.21$0.27/1M tokens$0.40/1M tokens163,840 FC Reasoning
Google: Gemini 2.5 Flash Lite1$0.10/1M tokens$0.40/1M tokens1,048,576Vision FC Reasoning
Meta: Llama 3.1 70B Instruct1$0.40/1M tokens$0.40/1M tokens131,072 FC
NVIDIA: Nemotron 3 Super1$0.09/1M tokens$0.40/1M tokens262,144 FC Reasoning
OpenAI: GPT-4.1 Nano1$0.10/1M tokens$0.40/1M tokens1,047,576Vision FC
OpenAI: GPT-5 Nano1$0.05/1M tokens$0.40/1M tokens400,000Vision FC Reasoning
Qwen2.5 72B Instruct1$0.36/1M tokens$0.40/1M tokens32,768 FC
TheDrummer: UnslopNemo 12B1$0.40/1M tokens$0.40/1M tokens1,024,000 FC
Z.ai: GLM 4.7 Flash1$0.06/1M tokens$0.40/1M tokens200,000 FC Reasoning
DeepSeek: DeepSeek V3.2 Exp1$0.27/1M tokens$0.41/1M tokens163,840 FC Reasoning
Qwen: Qwen3 VL 32B Instruct1$0.10/1M tokens$0.42/1M tokens131,072Vision FC
Google: Gemma 3 27B1$0.08/1M tokens$0.45/1M tokens131,072Vision FC
Mistral: Codestral 2508 (batch)1$0.15/1M tokens$0.45/1M tokens256,000 FC
Qwen: Qwen3 8B1$0.12/1M tokens$0.46/1M tokens131,072 FC Reasoning
Qwen: Qwen3 VL 8B Instruct1$0.12/1M tokens$0.46/1M tokens262,144Vision FC
Qwen: Qwen3.8 Flash1$0.15/1M tokens$0.47/1M tokens1,000,000Vision FC Reasoning
Qwen: Qwen3 30B A3B1$0.12/1M tokens$0.50/1M tokens131,072 FC Reasoning
Z.ai: GLM 5.3 Flash1$0.15/1M tokens$0.50/1M tokens1,310,720Vision FC Reasoning
Tencent: Hy31$0.13/1M tokens$0.53/1M tokens262,144 FC Reasoning
Cohere: Command R (08-2024)1$0.15/1M tokens$0.60/1M tokens128,000 FC
DeepSeek: DeepSeek V4.1 Flash1$0.15/1M tokens$0.60/1M tokens1,048,576Vision FC Reasoning
Mistral: Saba1$0.20/1M tokens$0.60/1M tokens32,768 FC
Mistral: Mistral Small 41$0.15/1M tokens$0.60/1M tokens262,144Vision FC Reasoning
OpenAI: GPT-4o-mini1$0.15/1M tokens$0.60/1M tokens128,000Vision FC
OpenAI: GPT-4o-mini (2024-07-18)1$0.15/1M tokens$0.60/1M tokens128,000Vision FC