Model Price Map
Which AI model is cheapest right now?
Prices per 1M tokens, context windows and input types for 7,517 model offers from 199 providers, read from a public open catalogue every 6 hours.
- Nothing to install
- No sign-up
- 20 languages
1,351–1,400 of 6,835
- GLM-5.3-FlashTensorXInput / 1M$0.20Output / 1M$0.50Context1M
- Grok 4 Fast (Non-Reasoning)AbacusInput / 1M$0.20Output / 1M$0.50Context2M
- Grok 4.1 FastOfoxInput / 1M$0.20Output / 1M$0.50Context2M
- Grok 4.1 Fast (Non-Reasoning)AbacusInput / 1M$0.20Output / 1M$0.50Context2M
- Grok 4.1 Fast (Non-Reasoning)AzureInput / 1M$0.20Output / 1M$0.50Context128K
- Grok 4.1 Fast (Non-Reasoning)FrogBotInput / 1M$0.20Output / 1M$0.50Context2M
- Grok 4.1 Fast (Non-Reasoning)Perplexity AgentInput / 1M$0.20Output / 1M$0.50Context2M
- Grok 4.1 Fast (Reasoning)AzureInput / 1M$0.20Output / 1M$0.50Context128K
- Grok 4.1 Fast (Reasoning)FrogBotInput / 1M$0.20Output / 1M$0.50Context2M
- Grok 4.1 Fast Non-ReasoningDevPass (LLM Gateway)Input / 1M$0.20Output / 1M$0.50Context2M
- Grok 4.1 Fast Non-ReasoningVercel AI GatewayInput / 1M$0.20Output / 1M$0.50Context1M
- Grok 4.1 Fast Non-Reasoning (Azure AI Foundry)LLM GatewayInput / 1M$0.20Output / 1M$0.50Context2M
- Grok 4.1 Fast ReasoningDevPass (LLM Gateway)Input / 1M$0.20Output / 1M$0.50Context2M
- Grok 4.1 Fast ReasoningVercel AI GatewayInput / 1M$0.20Output / 1M$0.50Context1M
- Grok 4.1 Fast Reasoning (Azure AI Foundry)LLM GatewayInput / 1M$0.20Output / 1M$0.50Context2M
- grok-4-1-fast-reasoning302.AIInput / 1M$0.20Output / 1M$0.50Context2M
- grok-4-fast-non-reasoning302.AIInput / 1M$0.20Output / 1M$0.50Context2M
- Grok-4-Fast-Non-ReasoningPoeInput / 1M$0.20Output / 1M$0.50Context2M
- grok-4-fast-reasoning302.AIInput / 1M$0.20Output / 1M$0.50Context2M
- Grok-4-Fast-ReasoningPoeInput / 1M$0.20Output / 1M$0.50Context2M
- NVIDIA Nemotron 3 Super 120B A12BAmazon BedrockInput / 1M$0.15Output / 1M$0.65Context262.1K
- NVIDIA Nemotron 3 Super 120B A12BVercel AI GatewayInput / 1M$0.15Output / 1M$0.65Context256K
- Qwen 3 Next 80B InstructIO.NETInput / 1M$0.10Output / 1M$0.80Context262.1K
- Qwen3 30B A3B Instruct 2507NanoGPTInput / 1M$0.20Output / 1M$0.50Context256K
- Qwen3 Next 80B A3B (Instruct)NanoGPTInput / 1M$0.15Output / 1M$0.65Context262.1K
- Qwen3 Next 80B A3B (Thinking)NanoGPTInput / 1M$0.15Output / 1M$0.65Context256K
- Qwen3.8 Flash NextRequestyInput / 1M$0.20Output / 1M$0.50Context262.1K
- Qwen3.8 Flash NextTensorXInput / 1M$0.20Output / 1M$0.50Context262.1K
- Qwen3.8 Flash Next (EU)RequestyInput / 1M$0.20Output / 1M$0.50Context262.1K
- xAI Grok 4 Fast Non-ReasoningHeliconeInput / 1M$0.20Output / 1M$0.50Context2M
- xAI Grok 4.1 Fast Non-ReasoningHeliconeInput / 1M$0.20Output / 1M$0.50Context2M
- xAI Grok 4.1 Fast ReasoningHeliconeInput / 1M$0.20Output / 1M$0.50Context2M
- xAI: Grok 4 Fast ReasoningHeliconeInput / 1M$0.20Output / 1M$0.50Context2M
- Qwen3.8 Flash NextCortecsInput / 1M$0.201Output / 1M$0.50Context262.1K
- Qwen3.8 Flash302.AIInput / 1M$0.18Output / 1M$0.564Context1M
- GPT OSS 120Bwatsonx.aiInput / 1M$0.159Output / 1M$0.636Context131.1K
- MiniCPM5-2BAMDInput / 1M$0.124Output / 1M$0.743Context131.1K
- GPT-4o miniCortecsInput / 1M$0.159Output / 1M$0.638Context128K
- Hy3CrossModelInput / 1M$0.16Output / 1M$0.64Context262.1K
- Qwen 3.32BVercel AI GatewayInput / 1M$0.16Output / 1M$0.64Context128K
- Doubao Seed 1.6NanoGPTInput / 1M$0.204Output / 1M$0.51Context256K
- Gemini 3.1 Flash LiteKilo GatewayInput / 1M$0.125Output / 1M$0.75Context1M
- Gemini 3.1 Flash Lite PreviewKilo GatewayInput / 1M$0.125Output / 1M$0.75Context1M
- Claude Haiku 4.5QiHangInput / 1M$0.14Output / 1M$0.71Context200K
- Hy3OrcaRouterInput / 1M$0.18Output / 1M$0.59Context256K
- Llama 4 Scout 17B InstructDevPass (LLM Gateway)Input / 1M$0.18Output / 1M$0.59Context131.1K
- Llama 4 Scout 17B Instruct (NovitaAI)LLM GatewayInput / 1M$0.18Output / 1M$0.59Context131.1K
- Llama 4 Scout InstructNovitaAIInput / 1M$0.18Output / 1M$0.59Context131.1K
- Qwen3.6 35B A3BNanoGPTInput / 1M$0.112Output / 1M$0.80Context262.1K
- Qwen3.6 35B A3B ThinkingNanoGPTInput / 1M$0.112Output / 1M$0.80Context262.1K
Price changes
Models whose price changed in the catalogue, newest first. We compare prices every day.
- DeepSeek R1 0528NanoGPTInput / 1M$0.40$0.50▲ 25%Output / 1M$1.70$2.15▲ 26%Changed: Oct 4, 2026, 12:08 PM UTC
- Gemma 4 31B IT (DeepInfra)LLM GatewayInput / 1M$0.15$0.20▲ 33%Output / 1M$0.40Changed: Oct 4, 2026, 12:08 PM UTC
- Z.ai: GLM LatestKilo GatewayInput / 1M$0.05Output / 1M$4.40$5.00▲ 14%Changed: Oct 4, 2026, 12:08 PM UTC
- MiMo-V2.6-FlashKilo GatewayInput / 1M$0.10$0.115▲ 15%Output / 1M$0.28Changed: Oct 4, 2026, 12:08 PM UTC
- MoonshotAI: Kimi LatestKilo GatewayInput / 1M$0.576$0.644▲ 12%Output / 1M$13.00Changed: Oct 4, 2026, 12:08 PM UTC
- DeepSeek: DeepSeek Pro LatestKilo GatewayInput / 1M$0.136$0.19▲ 40%Output / 1M$4.20Changed: Oct 4, 2026, 12:08 PM UTC
- Z.ai: GLM Flash LatestKilo GatewayInput / 1M$0.03$0.035▲ 16%Output / 1M$0.50Changed: Oct 4, 2026, 4:51 AM UTC
- DeepSeek: DeepSeek Pro LatestKilo GatewayInput / 1M$0.176$0.136▼ 23%Output / 1M$4.20Changed: Oct 4, 2026, 4:51 AM UTC
- Z.ai: GLM LatestKilo GatewayInput / 1M$0.06$0.05▼ 17%Output / 1M$8.00$4.40▼ 45%Changed: Oct 4, 2026, 3:54 AM UTC
- Z.ai: GLM Flash LatestKilo GatewayInput / 1M$0.024$0.03▲ 26%Output / 1M$0.50Changed: Oct 4, 2026, 3:54 AM UTC
- MiMo-V2.6-FlashKilo GatewayInput / 1M$0.11$0.10▼ 9%Output / 1M$0.28Changed: Oct 4, 2026, 3:54 AM UTC
- Hy4 previewKilo GatewayInput / 1M$0.751$0.834▲ 11%Output / 1M$2.25$2.50▲ 11%Changed: Oct 4, 2026, 3:54 AM UTC
- Hy3Kilo GatewayInput / 1M$0.083$0.13▲ 58%Output / 1M$0.33$0.53▲ 61%Changed: Oct 4, 2026, 3:54 AM UTC
- MoonshotAI: Kimi LatestKilo GatewayInput / 1M$0.399$0.576▲ 44%Output / 1M$13.00Changed: Oct 4, 2026, 3:54 AM UTC
- Z.ai: GLM LatestKilo GatewayInput / 1M$0.10$0.06▼ 40%Output / 1M$4.40$8.00▲ 82%Changed: Oct 4, 2026, 1:05 AM UTC
- Z.ai: GLM Flash LatestKilo GatewayInput / 1M$0.034$0.024▼ 29%Output / 1M$0.50Changed: Oct 4, 2026, 1:05 AM UTC
- MoonshotAI: Kimi LatestKilo GatewayInput / 1M$0.65$0.399▼ 39%Output / 1M$10.33$13.00▲ 26%Changed: Oct 4, 2026, 1:05 AM UTC
- DeepSeek: DeepSeek V4 Flash LatestKilo GatewayInput / 1M$0.019$0.015▼ 19%Output / 1M$1.28Changed: Oct 4, 2026, 1:05 AM UTC
- DeepSeek: DeepSeek Pro LatestKilo GatewayInput / 1M$0.218$0.176▼ 19%Output / 1M$4.20Changed: Oct 4, 2026, 1:05 AM UTC
- DeepSeek: DeepSeek Flash LatestKilo GatewayInput / 1M$0.02$0.003▼ 85%Output / 1M$0.40$2.40▲ 500%Changed: Oct 4, 2026, 1:05 AM UTC
- DeepSeek: DeepSeek V3 0324Kilo GatewayInput / 1M$0.29$0.25▼ 14%Output / 1M$1.14$1.00▼ 12%Changed: Oct 4, 2026, 1:05 AM UTC
- Z.ai: GLM LatestKilo GatewayInput / 1M$0.12$0.10▼ 17%Output / 1M$4.00$4.40▲ 10%Changed: Oct 3, 2026, 10:13 PM UTC
- Z.ai: GLM Flash LatestKilo GatewayInput / 1M$0.035$0.034▼ 4%Output / 1M$0.50Changed: Oct 3, 2026, 10:13 PM UTC
- MoonshotAI: Kimi LatestKilo GatewayInput / 1M$0.73$0.65▼ 11%Output / 1M$13.00$10.33▼ 21%Changed: Oct 3, 2026, 10:13 PM UTC
- DeepSeek: DeepSeek Pro LatestKilo GatewayInput / 1M$0.22$0.218▼ 1%Output / 1M$4.20Changed: Oct 3, 2026, 10:13 PM UTC
- DeepSeek: DeepSeek Flash LatestKilo GatewayInput / 1M$0.02Output / 1M$0.60$0.40▼ 33%Changed: Oct 3, 2026, 10:13 PM UTC
- Hy4 previewKilo GatewayInput / 1M$0.834$0.751▼ 10%Output / 1M$2.50$2.25▼ 10%Changed: Oct 3, 2026, 8:38 PM UTC
- Hy3Kilo GatewayInput / 1M$0.13$0.083▼ 37%Output / 1M$0.53$0.33▼ 38%Changed: Oct 3, 2026, 8:38 PM UTC
- MoonshotAI: Kimi LatestKilo GatewayInput / 1M$0.99$0.73▼ 26%Output / 1M$13.00Changed: Oct 3, 2026, 8:38 PM UTC
- Kimi K3Kilo GatewayInput / 1M$0.99$3.00▲ 203%Output / 1M$13.00$15.00▲ 15%Changed: Oct 3, 2026, 8:38 PM UTC
- MiMo-V2.6-FlashKilo GatewayInput / 1M$0.12$0.11▼ 8%Output / 1M$0.28Changed: Oct 3, 2026, 3:07 PM UTC
- Kimi K3Kilo GatewayInput / 1M$2.70$0.99▼ 63%Output / 1M$13.50$13.00▼ 4%Changed: Oct 3, 2026, 3:07 PM UTC
- DeepSeek: DeepSeek Pro LatestKilo GatewayInput / 1M$0.12$0.22▲ 83%Output / 1M$4.20Changed: Oct 3, 2026, 3:07 PM UTC
- MiMo-V2.6-ProKilo GatewayInput / 1M$0.435$0.43▼ 1%Output / 1M$0.87Changed: Oct 3, 2026, 12:15 PM UTC
- MoonshotAI: Kimi LatestKilo GatewayInput / 1M$0.79$0.99▲ 25%Output / 1M$13.00Changed: Oct 3, 2026, 12:15 PM UTC
- DeepSeek: DeepSeek V4 Flash LatestKilo GatewayInput / 1M$0.017$0.019▲ 10%Output / 1M$1.28Changed: Oct 3, 2026, 12:15 PM UTC
- DeepSeek: DeepSeek Pro LatestKilo GatewayInput / 1M$0.11$0.12▲ 9%Output / 1M$4.20Changed: Oct 3, 2026, 12:15 PM UTC
- DeepSeek V4.1 FlashVenice AIInput / 1M$0.375$0.30▼ 20%Output / 1M$1.50$1.20▼ 20%Changed: Oct 3, 2026, 7:32 AM UTC
- Z.ai: GLM LatestKilo GatewayInput / 1M$0.066$0.12▲ 82%Output / 1M$2.79$4.00▲ 43%Changed: Oct 3, 2026, 7:32 AM UTC
- Z.ai: GLM Flash LatestKilo GatewayInput / 1M$0.026$0.035▲ 33%Output / 1M$0.929$0.50▼ 46%Changed: Oct 3, 2026, 7:32 AM UTC
How this works
- Every price, limit and date comes from models.dev, an open-source (MIT-licensed) catalogue of AI models kept in public on GitHub and compiled from providers’ official pricing and documentation pages.
- We read it at most every 6 hours. Providers change prices without notice, so confirm on the provider’s own page (linked on each model) before you rely on a number.
- Prices are US dollars per 1 million tokens, exactly as the catalogue lists them. The blended price, (3 × input + output) ÷ 4, is our own estimate, used only to sort and compare.
- Anything the catalogue does not state is shown as “—”; we never guess. Flat-fee subscription plans, local-only runtimes and deprecated models are left out, and $0 offers are hidden unless you include them.
- No benchmark scores yet. When we add them, they will come only from official sources and be labelled as such.
Sources: models.dev · api.json · GitHub · MIT License
Wrong price, or a provider that wants its listing corrected or removed? Email ceo@uniholix.com. We reply within 5 business days.