AI model pricing
API prices for 1697 models across every provider that serves them. Each row shows the lowest price and who sells at it; open a row to compare all providers.
| GPT-5 Chat LatestOpenAIPrompt cachingJSON+2 | $10/1Mvia Helicone | — | $1.25/1M | $10/1M | |
| GPT-5 CodexOpenAIPrompt cachingJSON+3 | $8/1Mvia APIMart | 400K | $1/1M | $8/1M | |
| GPT-5 ProOpenAIJSONReasoning+2 | $96/1Mvia APIMart | 400K | $15/1M | $120/1M | |
| GPT-5 Search APIOpenAIPrompt cachingJSON+2 | $8/1Mvia APIMart | — | $1/1M | $8/1M | |
| GPT-5 StructuredOpenAI | $0.40/1Mvia Replicate | — | $0.05/1M | $0.40/1M | |
| GPT-5.1OpenAIPrompt cachingJSON+3 | $8/1Mvia APIMart | 400K | $1.25/1M | $10/1M | |
| GPT-5.1 CodexOpenAIPrompt cachingJSON+3 | $8/1Mvia APIMart | 400K | $1/1M | $8/1M | |
| GPT-5.1 Codex MaxOpenAIPrompt cachingJSON+3 | $8/1Mvia APIMart | 400K | $1/1M | $8/1M | |
| GPT-5.1 Codex miniOpenAIPrompt cachingJSON+3 | $1.60/1Mvia APIMart | 400K | $0.20/1M | $1.60/1M | |
| GPT-5.1-InstantOpenAIPrompt cachingJSON+2 | $10/1Mvia Helicone | — | $1.25/1M | $10/1M | |
| GPT-5.2 ChatOpenAIPrompt cachingJSON+2 | $3.50/1Mvia Kie.ai | 128K | $0.44/1M | $3.50/1M | |
| GPT-5.2 CodexOpenAIPrompt cachingJSON+3 | $11.20/1Mvia APIMart | 400K | $1.40/1M | $11.20/1M | |
| GPT-5.3-Codex-SparkOpenAI | $14/1Mvia OpenCode | — | $1.75/1M | $14/1M | |
| GPT-5.5 CyberOpenAI | $75/1Mvia OpenAI | — | $12.50/1M | $75/1M | |
| GPT-5.5 ProOpenAIJSONReasoning+2 | $144/1Mvia CometAPI | 1.05M | $30/1M | $180/1M | |
| GPT-5.6 TerraOpenAIPrompt cachingJSON+3 | $9.60/1Mvia APIMart | 1.05M | $2/1M | $12/1M | |
| GPT-6 Astra (Fast)OpenAIPrompt cachingJSON+3 | $100/1Mvia Vercel AI Gateway | 1.05M | $20/1M | $100/1M | |
| GPT-6 Astra Pro ($$$$)OpenAIPrompt cachingJSON+3 | $50/1Mvia OpenRouter | 1.05M | $10/1M | $50/1M | |
| GPT-6 Luna DecisionsOpenAI | Free/1Mvia CrossModel | 1.05M | $0.10/1M | Free/1M | |
| GPT-6 Luna ProOpenAIPrompt cachingJSON+3 | $0.50/1Mvia OpenRouter | 1.05M | $0.10/1M | $0.50/1M | |
| GPT-6 Sol ProOpenAIPrompt cachingJSON+3 | $10/1Mvia OpenRouter | 1.05M | $2/1M | $10/1M | |
| GPT-6.1 Sol ProOpenAIPrompt cachingJSON+3 | $10/1Mvia OpenRouter | 1.05M | $2/1M | $10/1M | |
| GPT-AudioOpenAIJSONTool calling | $10/1Mvia OpenRouter | 128K | $2.50/1M | $10/1M | |
| GPT-Audio MiniOpenAIJSONTool calling | $2.40/1Mvia OpenRouter | 128K | $0.60/1M | $2.40/1M | |
| Granite 3.0 3B A800m InstructIBMApache 2.0 | Free/1Mvia Nvidia | — | Free/1M | Free/1M | |
| Granite 3.0 8B InstructIBMApache 2.0 | $0.25/1Mvia Replicate | — | $0.05/1M | $0.25/1M | |
| Granite 34B Code InstructIBM | Free/1Mvia Nvidia | — | Free/1M | Free/1M | |
| Granite 4.0 H MicroIBMApache 2.0JSON | $0.112/1Mvia Cloudflare Workers AI | 131K | $0.017/1M | $0.112/1M | |
| Granite 4.2 3BIBMApache 2.0 | $0.12/1Mvia Hugging Face | — | $0.03/1M | $0.12/1M | |
| Granite 4.2 8BIBMApache 2.0Prompt caching+3 | $0.25/1Mvia Deep Infra | 131K | $0.06/1M | $0.25/1M | |
| Granite 8B Code InstructIBM | Free/1Mvia Nvidia | — | Free/1M | Free/1M | |
| Granite-4.0-H-SmallIBMApache 2.0 | $0.25/1Mvia Replicate | — | $0.06/1M | $0.25/1M | |
| Grok 2xAIOpen weights | $9/1Mvia AIHubMix | — | $1.80/1M | $9/1M | |
| Grok 2 VisionxAIVision | $9/1Mvia AIHubMix | — | $1.80/1M | $9/1M | |
| Grok 3 FastxAI | $27.50/1Mvia AIHubMix | — | $5.50/1M | $27.50/1M | |
| Grok 3 MinixAIPrompt cachingJSON+2 | $0.50/1Mvia Helicone | 131K | $0.30/1M | $0.50/1M | |
| Grok 3 Mini FastxAI | $2.20/1Mvia AIHubMix | — | $0.33/1M | $2.20/1M | |
| Grok 4 Fast Non ReasoningxAIPrompt cachingJSON+2 | $0.50/1Mvia Helicone | 2M | $0.20/1M | $0.50/1M | |
| Grok 4 Fast ReasoningxAI | $0.50/1Mvia Helicone | — | $0.20/1M | $0.50/1M | |
| Grok 4.1 FastxAIPrompt cachingJSON+2 | $0.475/1Mvia Jiekou.AI | 2M | $0.19/1M | $0.475/1M | |
| Grok 4.1 Fast (Reasoning)xAIPrompt cachingJSON+3 | $0.475/1Mvia Jiekou.AI | 2M | $0.19/1M | $0.475/1M | |
| GPT-5 ImageOpenAIPrompt cachingJSON+2 | $10/1Mvia OpenRouter | 400K | $10/1M | $10/1M | |
| GPT-5 Image MiniOpenAIPrompt cachingJSON+2 | $2/1Mvia OpenRouter | 400K | $2.50/1M | $2/1M | |
| GPT-5.4 Image 2OpenAIPrompt cachingJSON+2 | $15/1Mvia OpenRouter | 272K | $8/1M | $15/1M | |
| GPT-Image-1-MiniOpenAIPrompt caching | $8/1Mvia APIYI | 128K | $2/1M | $8/1M | |
| Grok 2 ImagexAI | $0.07/runvia WaveSpeedAI | — | — | $0.07/run | |
| GPT-Live-TranscribeOpenAI | $0.017/minvia AIHubMix | — | — | $0.017/min | |
| GPT-Realtime miniOpenAIPrompt cachingTool calling | $2.40/1Mvia FastRouter | 32K | $0.60/1M | $2.40/1M | |
| GPT-Realtime-1.5OpenAIPrompt cachingTool calling | $12.80/1Mvia CometAPI | 32K | $3.20/1M | $12.80/1M | |
| GPT-Realtime-2.1OpenAIPrompt cachingReasoning+2 | $19.20/1Mvia CometAPI | 128K | $3.20/1M | $19.20/1M |
LLM API pricing at a glance
Where the lowest output prices of 738 LLMs sit, and the cheapest model of each type.
- Under $0.1067
- $0.10–$0.50200
- $0.50–$1100
- $1–$3156
- $3–$10131
- $10–$3058
- Over $3026
DeepSeek R1 Distill Qwen 7B$0.01/1M
Qwen Image 3$0.003/img
PixVerse C1$0.005/secQwen3 Embedding 0.6B$0.01/1MLLM pricing comparison
The most searched LLMs at the lowest input and output price any provider charges.
Gemini 4 Argon$1.60/$8- Kimi K3$0.828/$8.28
- GPT-6 Astra$5/$25
Muse Wonder$3.20/$16- Claude Opus 5.5$3.20/$16
- GPT-6.1 Sol$1.60/$8
GLM-5.3$0.15/$1.10- GPT-6 Sol$1.60/$8
- Qwen3.8 2.4T A95B$1.37/$4.11
- Grok 4.7$1.60/$4.80
- Gemini 3 Flash$0.30/$2.40
- DeepSeek V4.1 Flash$0.007/$0.03
Mistral Large 4$0.68/$2.09- GLM-5.3-Flash$0.06/$0.20
- Muse Spark 1.3$1.25/$4.25
How much prices differ between providers
The same model can cost several times more from one provider than another. Here is the spread for the most searched models.
- Gemini 4 Argon$8$202.5×
- Kimi K3$8.28$17.252.1×
- GPT-6 Astra$25$61.652.5×
- Muse Wonder$16$402.5×
- Claude Opus 5.5$16$22.101.4×
- GPT-6.1 Sol$8$12.061.5×
- GLM-5.3$1.10$5.755.2×
- GPT-6 Sol$8$12.061.5×
- Qwen3.8 2.4T A95B$4.11$7.501.8×
- Grok 4.7$4.80$6.801.4×
- Gemini 3 Flash$2.40$31.3×
- DeepSeek V4.1 Flash$0.03$2.4080×
Standard paid rates only; context-tiered and batch prices are left out.
LLM API pricing calculator
Enter your monthly tokens to see what each popular model costs at the provider cheapest for that mix.
Standard prices only. Caching, batch and volume discounts can lower the bill.
- 1DeepSeek V4.1 Flashvia UnoRouter$0.132/mo
- 2GLM-5.3-Flashvia APIMart$1.00/mo
- 3Gemini 3 Flashvia CrazyRouter$7.80/mo
- 4GLM-5.3via NanoGPT$8.20/mo
- 5Mistral Large 4via Opper$10.98/mo
- 6Muse Spark 1.3via OpenCode$21.00/mo
- 7Qwen3.8 2.4T A95Bvia APIMart$21.94/mo
- 8Kimi K3via Kenari$24.85/mo
- 9Grok 4.7via Prime Inference$25.60/mo
- 10Gemini 4 Argonvia APIMart$32.00/mo
- 11GPT-6.1 Solvia APIMart$32.00/mo
- 12GPT-6 Solvia APIMart$32.00/mo
- 13Muse Wondervia CometAPI$64.00/mo
- 14Claude Opus 5.5via APIMart$64.00/mo
- 15GPT-6 Astravia CrazyRouter$100/mo
Frequently asked questions
The model's maker and third-party hosts set their own prices. A host can undercut the maker, add a margin, or charge differently for cached input. We list every provider's price so you can pick the cheapest one that meets your needs.
Text models are priced per 1 million input and output tokens. Image models are priced per image or per megapixel, video models per second of output, and audio models per minute or per character.
We refresh prices from providers' public price lists regularly. Check the provider's own page before a large commitment, as prices can change without notice.
Pick the model type tab, then sort by input or output price. Use the filters to keep only models with the context window, capabilities or quality you need.
Can't find what you're looking for? Contact us