Verified model pricing
LLM API Price Index
Compare official provider list prices with LLMHub prices in one dataset. LLMHub savings reach up to 65%; actual prices and savings vary by model, provider, service tier, context length, region, and modality.
Last verified:
- Comparable models
- 216
- Manufacturers
- 19
- Modalities
- 5
Official vs LLMHub
Current model price comparison
216 comparable prices
| Model | Type | Official price | LLMHub price | Saving | Source |
|---|---|---|---|---|---|
| Nova 2 SonicAmazonText is $0.319 input / $2.651 output per 1M tokens | Audio | Speech: $3 input / $12 output per 1M tokens | Speech: $1.05 input / $4.20 output per 1M tokens | 65% | Official source ↗ |
| Nova SonicAmazonText is $0.06 input / $0.24 output per 1M tokens | Audio | Speech: $3.40 input / $13.60 output per 1M tokens | Speech: $1.19 input / $4.76 output per 1M tokens | 65% | Official source ↗ |
| Chirp 3 HDGoogleFirst 1M characters each month are free | Audio | $30 / 1M characters | $15.00 / 1M characters | 50% | Official source ↗ |
| Gemini 2.5 Flash LiveGoogleText is $0.50 input / $2 output per 1M tokens | Audio | Audio: $3 input / $12 output per 1M tokens | Audio: $1.50 input / $6.00 output per 1M tokens | 50% | Official source ↗ |
| Lyria 2Google | Audio | $0.06 / generation | $0.03 / generation | 50% | Official source ↗ |
| Lyria 3 ClipGoogle | Audio | $0.04 / 30-second clip | $0.02 / 30-second clip | 50% | Official source ↗ |
| Lyria 3 ProGoogle | Audio | $0.08 / full song | $0.04 / full song | 50% | Official source ↗ |
| gpt-4o-mini-transcribeOpenAI$1.25 input / $5 output per 1M tokens | Audio | $0.003 / minute | $0.00165 / minute | 45% | Official source ↗ |
| gpt-4o-mini-ttsOpenAI | Audio | Text input: $0.60 / 1M tokens; audio output: $12 / 1M tokens | Text input: $0.33 / 1M tokens; audio output: $6.60 / 1M tokens | 45% | Official source ↗ |
| gpt-4o-transcribeOpenAI$2.50 input / $10 output per 1M tokens | Audio | $0.006 / minute | $0.0033 / minute | 45% | Official source ↗ |
| gpt-4o-transcribe-diarizeOpenAIAudio tokens | Audio | $2.50 input$10.00 outputper 1M tokens | $1.375 input$5.50 outputper 1M tokens | 45% | Official source ↗ |
| gpt-audioOpenAIText is $2.50 input / $10 output per 1M tokens; deprecated | Audio | Audio: $32 input / $64 output per 1M tokens | Audio: $17.60 input / $35.20 output per 1M tokens | 45% | Official source ↗ |
| gpt-audio-1.5OpenAIText is $2.50 input / $10 output per 1M tokens | Audio | Audio: $32 input / $64 output per 1M tokens | Audio: $17.60 input / $35.20 output per 1M tokens | 45% | Official source ↗ |
| gpt-audio-miniOpenAIDeprecated; official model page does not publish separate audio-token rates | Audio | Text: $0.60 input / $2.40 output per 1M tokens | Text: $0.33 input / $1.32 output per 1M tokens | 45% | Official source ↗ |
| gpt-live-transcribeOpenAI | Audio | $0.017 / minute | $0.00935 / minute | 45% | Official source ↗ |
| gpt-realtimeOpenAIText is $4 input / $16 output per 1M tokens; deprecated | Audio | Audio: $32 input / $64 output per 1M tokens | Audio: $17.60 input / $35.20 output per 1M tokens | 45% | Official source ↗ |
| gpt-realtime-1.5OpenAIText is $4 input / $16 output per 1M tokens | Audio | Audio: $32 input / $64 output per 1M tokens | Audio: $17.60 input / $35.20 output per 1M tokens | 45% | Official source ↗ |
| gpt-realtime-2OpenAIText is $4 input / $24 output per 1M tokens | Audio | Audio: $32 input / $64 output per 1M tokens | Audio: $17.60 input / $35.20 output per 1M tokens | 45% | Official source ↗ |
| gpt-realtime-2.1OpenAIText is $4 input / $24 output per 1M tokens | Audio | Audio: $32 input / $64 output per 1M tokens | Audio: $17.60 input / $35.20 output per 1M tokens | 45% | Official source ↗ |
| gpt-realtime-2.1-miniOpenAIText is $0.60 input / $2.40 output per 1M tokens | Audio | Audio: $10 input / $20 output per 1M tokens | Audio: $5.50 input / $11.00 output per 1M tokens | 45% | Official source ↗ |
| gpt-realtime-miniOpenAIDeprecated; official model page does not publish separate audio-token rates | Audio | Text: $0.60 input / $2.40 output per 1M tokens | Text: $0.33 input / $1.32 output per 1M tokens | 45% | Official source ↗ |
| gpt-realtime-translateOpenAI | Audio | $0.034 / minute | $0.0187 / minute | 45% | Official source ↗ |
| gpt-realtime-whisperOpenAI | Audio | $0.017 / minute | $0.00935 / minute | 45% | Official source ↗ |
| gpt-transcribeOpenAI | Audio | $0.0045 / minute | $0.002475 / minute | 45% | Official source ↗ |
| ttsOpenAICatalog alias for the official TTS-1 rate | Audio | $15 / 1M characters | $8.25 / 1M characters | 45% | Official source ↗ |
| tts-hdOpenAICatalog alias for the official TTS-1 HD rate | Audio | $30 / 1M characters | $16.50 / 1M characters | 45% | Official source ↗ |
| whisperOpenAI | Audio | $0.006 / minute | $0.0033 / minute | 45% | Official source ↗ |
| Nova Multimodal EmbeddingsAmazonVideo is $0.0007 / second; audio is $0.00014 / second | Embedding | $0.135 / 1M text tokens; $0.00006 / image | $0.04725 / 1M text tokens; $0.000021 / image | 65% | Official source ↗ |
| Titan Embeddings G1 TextAmazonUS on-demand | Embedding | $0.10 inputNo output chargeper 1M tokens | $0.035 inputNo output chargeper 1M tokens | 65% | Official source ↗ |
| Titan Embeddings G1 Text v2AmazonUS on-demand | Embedding | $0.02 inputNo output chargeper 1M tokens | $0.007 inputNo output chargeper 1M tokens | 65% | Official source ↗ |
| Titan Multimodal Embeddings G1AmazonUS on-demand | Embedding | $0.0008 / 1K text tokens; $0.00006 / image | $0.00028 / 1K text tokens; $0.000021 / image | 65% | Official source ↗ |
| Titan Text Embeddings V2AmazonUS on-demand | Embedding | $0.02 inputNo output chargeper 1M tokens | $0.007 inputNo output chargeper 1M tokens | 65% | Official source ↗ |
| Embed 3 EnglishCohereUS on-demand | Embedding | $0.10 inputNo output chargeper 1M tokens | $0.035 inputNo output chargeper 1M tokens | 65% | Official source ↗ |
| Embed 3 MultilingualCohereUS on-demand | Embedding | $0.10 inputNo output chargeper 1M tokens | $0.035 inputNo output chargeper 1M tokens | 65% | Official source ↗ |
| Embed v4CohereUS on-demand | Embedding | $0.12 inputNo output chargeper 1M tokens | $0.042 inputNo output chargeper 1M tokens | 65% | Official source ↗ |
| gemini-embedding-001GoogleOnline requests; output is free | Embedding | $0.00015 / 1K input count | $0.000075 / 1K input count | 50% | Official source ↗ |
| multilingual-e5-largeGoogleOnline requests | Embedding | $0.025 inputNo output chargeper 1M tokens | $0.0125 inputNo output chargeper 1M tokens | 50% | Official source ↗ |
| multilingual-e5-smallGoogleOnline requests | Embedding | $0.015 inputNo output chargeper 1M tokens | $0.0075 inputNo output chargeper 1M tokens | 50% | Official source ↗ |
| text-embedding-005GoogleOnline requests; output is free | Embedding | $0.000025 / 1K input count | $0.0000125 / 1K input count | 50% | Official source ↗ |
| text-multilingual-embedding-002GoogleOnline requests; output is free | Embedding | $0.000025 / 1K input count | $0.0000125 / 1K input count | 50% | Official source ↗ |
| text-embedding-3-largeOpenAI | Embedding | $0.13 inputNo output chargeper 1M tokens | $0.0715 inputNo output chargeper 1M tokens | 45% | Official source ↗ |
| text-embedding-3-smallOpenAI | Embedding | $0.02 inputNo output chargeper 1M tokens | $0.011 inputNo output chargeper 1M tokens | 45% | Official source ↗ |
| text-embedding-ada-002OpenAI | Embedding | $0.10 inputNo output chargeper 1M tokens | $0.055 inputNo output chargeper 1M tokens | 45% | Official source ↗ |
| Marengo EmbedTwelveLabs$0.0001 per image; $0.00007 per text request | Embedding | $0.0007 / video second; $0.00014 / audio second | $0.000245 / video second; $0.000049 / audio second | 65% | Official source ↗ |
| Nova CanvasAmazonPrice varies by resolution and quality | Image | $0.04–$0.08 / image | $0.014–$0.028 / image | 65% | Official source ↗ |
| Titan Image Generator G1 v2AmazonPrice varies by resolution and quality | Image | $0.008–$0.012 / image | $0.0028–$0.0042 / image | 65% | Official source ↗ |
| FLUX 1.1 ProBlack Forest Labs | Image | $0.04 / image | $0.014 / image | 65% | Official source ↗ |
| FLUX.1 Kontext ProBlack Forest Labs | Image | $0.04 / image | $0.014 / image | 65% | Official source ↗ |
| FLUX.2 FlexBlack Forest LabsText-to-image; editing is $0.10 / MP | Image | $0.05 / MP | $0.0175 / MP | 65% | Official source ↗ |
| FLUX.2 ProBlack Forest LabsText-to-image; editing starts at $0.045 / MP | Image | From $0.03 / MP | From $0.0105 / MP | 65% | Official source ↗ |
| Gemini 2.5 Flash ImageGoogleDeprecated; scheduled for shutdown on October 2, 2026 | Image | $0.30 input / $0.039 per image | $0.15 input / $0.0195 per image | 50% | Official source ↗ |
| Gemini 3 Pro ImageGoogleText and thinking output is $12 / 1M tokens | Image | $2 input / $120 image output per 1M tokens | $1.00 input / $60.00 image output per 1M tokens | 50% | Official source ↗ |
| Gemini 3.1 Flash ImageGoogleImage output starts at $0.045 per 0.5K image | Image | $0.50 input / $60 image output per 1M tokens | $0.25 input / $30.00 image output per 1M tokens | 50% | Official source ↗ |
| Gemini 3.1 Flash-Lite ImageGoogleImage output is $30 / 1M tokens | Image | $0.25 input / $0.0336 per 1K image | $0.125 input / $0.0168 per 1K image | 50% | Official source ↗ |
| gpt-image-1OpenAIImage tokens; text input is $5 / 1M tokens | Image | $10.00 input$40.00 outputper 1M tokens | $5.50 input$22.00 outputper 1M tokens | 45% | Official source ↗ |
| gpt-image-1-miniOpenAIImage tokens; text input is $2 / 1M tokens | Image | $2.50 input$8.00 outputper 1M tokens | $1.375 input$4.40 outputper 1M tokens | 45% | Official source ↗ |
| gpt-image-1.5OpenAIImage tokens; text is $5 input / $10 output per 1M tokens | Image | $8.00 input$32.00 outputper 1M tokens | $4.40 input$17.60 outputper 1M tokens | 45% | Official source ↗ |
| gpt-image-2OpenAIImage tokens; text input is $2.50 / 1M tokens | Image | $4.00 input$15.00 outputper 1M tokens | $2.20 input$8.25 outputper 1M tokens | 45% | Official source ↗ |
| gpt-image-2.5-flareOpenAIImage tokens; text input is $5 / 1M tokens | Image | $8.00 input$30.00 outputper 1M tokens | $4.40 input$16.50 outputper 1M tokens | 45% | Official source ↗ |
| gpt-image-2.5-sunburstOpenAIImage tokens; text input is $5 / 1M tokens | Image | $8.00 input$30.00 outputper 1M tokens | $4.40 input$16.50 outputper 1M tokens | 45% | Official source ↗ |
| Stable Image Conservative UpscaleStability AI | Image | $0.40 / generation | $0.14 / generation | 65% | Official source ↗ |
| Stable Image Control SketchStability AI | Image | $0.07 / generation | $0.0245 / generation | 65% | Official source ↗ |
| Stable Image Control StructureStability AI | Image | $0.07 / generation | $0.0245 / generation | 65% | Official source ↗ |
| Stable Image Creative UpscaleStability AI | Image | $0.60 / generation | $0.21 / generation | 65% | Official source ↗ |
| Stable Image Erase ObjectStability AI | Image | $0.07 / generation | $0.0245 / generation | 65% | Official source ↗ |
| Stable Image Fast UpscaleStability AI | Image | $0.03 / generation | $0.0105 / generation | 65% | Official source ↗ |
| Stable Image InpaintStability AI | Image | $0.07 / generation | $0.0245 / generation | 65% | Official source ↗ |
| Stable Image OutpaintStability AI | Image | $0.06 / generation | $0.021 / generation | 65% | Official source ↗ |
| Stable Image Remove BackgroundStability AI | Image | $0.07 / generation | $0.0245 / generation | 65% | Official source ↗ |
| Stable Image Search and RecolorStability AI | Image | $0.07 / generation | $0.0245 / generation | 65% | Official source ↗ |
| Stable Image Search and ReplaceStability AI | Image | $0.07 / generation | $0.0245 / generation | 65% | Official source ↗ |
| Stable Image Style GuideStability AI | Image | $0.07 / generation | $0.0245 / generation | 65% | Official source ↗ |
| Stable Image Style TransferStability AI | Image | $0.08 / generation | $0.028 / generation | 65% | Official source ↗ |
| Jamba 1.5 LargeAI21 LabsUS on-demand | Text | $2.00 input$8.00 outputper 1M tokens | $0.70 input$2.80 outputper 1M tokens | 65% | Official source ↗ |
| Jamba 1.5 MiniAI21 LabsUS on-demand | Text | $0.20 input$0.40 outputper 1M tokens | $0.07 input$0.14 outputper 1M tokens | 65% | Official source ↗ |
| Nova 2 LiteAmazonGlobal cross-region | Text | $0.30 input$2.50 outputper 1M tokens | $0.105 input$0.875 outputper 1M tokens | 65% | Official source ↗ |
| Nova LiteAmazonUS on-demand | Text | $0.06 input$0.24 outputper 1M tokens | $0.021 input$0.084 outputper 1M tokens | 65% | Official source ↗ |
| Nova MicroAmazonUS on-demand | Text | $0.035 input$0.14 outputper 1M tokens | $0.01225 input$0.049 outputper 1M tokens | 65% | Official source ↗ |
| Nova PremierAmazonUS on-demand | Text | $2.50 input$12.50 outputper 1M tokens | $0.875 input$4.375 outputper 1M tokens | 65% | Official source ↗ |
| Nova ProAmazonUS on-demand | Text | $0.80 input$3.20 outputper 1M tokens | $0.28 input$1.12 outputper 1M tokens | 65% | Official source ↗ |
| Claude 3 HaikuAnthropic | Text | $0.25 input$1.25 outputper 1M tokens | $0.175 input$0.875 outputper 1M tokens | 30% | Official source ↗ |
| Claude 3.5 HaikuAnthropic | Text | $0.80 input$4.00 outputper 1M tokens | $0.56 input$2.80 outputper 1M tokens | 30% | Official source ↗ |
| Claude Fable 5Anthropic | Text | $10.00 input$50.00 outputper 1M tokens | $7.00 input$35.00 outputper 1M tokens | 30% | Official source ↗ |
| Claude Fable 5.1Anthropic | Text | $10.00 input$50.00 outputper 1M tokens | $7.00 input$35.00 outputper 1M tokens | 30% | Official source ↗ |
| Claude Haiku 4.5Anthropic | Text | $1.00 input$5.00 outputper 1M tokens | $0.70 input$3.50 outputper 1M tokens | 30% | Official source ↗ |
| Claude Mythos 5AnthropicLimited availability | Text | $10.00 input$50.00 outputper 1M tokens | $7.00 input$35.00 outputper 1M tokens | 30% | Official source ↗ |
| Claude Mythos 5.1AnthropicLimited availability | Text | $10.00 input$50.00 outputper 1M tokens | $7.00 input$35.00 outputper 1M tokens | 30% | Official source ↗ |
| Claude Opus 4.1Anthropic | Text | $15.00 input$75.00 outputper 1M tokens | $10.50 input$52.50 outputper 1M tokens | 30% | Official source ↗ |
| Claude Opus 4.5Anthropic | Text | $5.00 input$25.00 outputper 1M tokens | $3.50 input$17.50 outputper 1M tokens | 30% | Official source ↗ |
| Claude Opus 4.6Anthropic | Text | $5.00 input$25.00 outputper 1M tokens | $3.50 input$17.50 outputper 1M tokens | 30% | Official source ↗ |
| Claude Opus 4.7Anthropic | Text | $5.00 input$25.00 outputper 1M tokens | $3.50 input$17.50 outputper 1M tokens | 30% | Official source ↗ |
| Claude Opus 4.8Anthropic | Text | $5.00 input$25.00 outputper 1M tokens | $3.50 input$17.50 outputper 1M tokens | 30% | Official source ↗ |
| Claude Opus 5Anthropic | Text | $5.00 input$25.00 outputper 1M tokens | $3.50 input$17.50 outputper 1M tokens | 30% | Official source ↗ |
| Claude Opus 5.5Anthropic | Text | $4.00 input$20.00 outputper 1M tokens | $2.80 input$14.00 outputper 1M tokens | 30% | Official source ↗ |
| Claude Sonnet 4Anthropic | Text | $3.00 input$15.00 outputper 1M tokens | $2.10 input$10.50 outputper 1M tokens | 30% | Official source ↗ |
| Claude Sonnet 4.5Anthropic | Text | $3.00 input$15.00 outputper 1M tokens | $2.10 input$10.50 outputper 1M tokens | 30% | Official source ↗ |
| Claude Sonnet 4.6Anthropic | Text | $3.00 input$15.00 outputper 1M tokens | $2.10 input$10.50 outputper 1M tokens | 30% | Official source ↗ |
| Claude Sonnet 5Anthropic | Text | $2.00 input$10.00 outputper 1M tokens | $1.40 input$7.00 outputper 1M tokens | 30% | Official source ↗ |
| Claude Sonnet 5.5Anthropic | Text | $2.00 input$10.00 outputper 1M tokens | $1.40 input$7.00 outputper 1M tokens | 30% | Official source ↗ |
| Command ACohere | Text | $2.50 input$10.00 outputper 1M tokens | $0.875 input$3.50 outputper 1M tokens | 65% | Official source ↗ |
| Command A Plus 05-2026CohereProduction through Model Vault uses contract pricing | Text | Free until API rate limits are reached | Free until API rate limits are reached | 65% | Official source ↗ |
| Command RCohereUS on-demand | Text | $0.50 input$1.50 outputper 1M tokens | $0.175 input$0.525 outputper 1M tokens | 65% | Official source ↗ |
| Command R+CohereUS on-demand | Text | $3.00 input$15.00 outputper 1M tokens | $1.05 input$5.25 outputper 1M tokens | 65% | Official source ↗ |
| DeepSeek R1DeepSeekUS on-demand | Text | $1.35 input$5.40 outputper 1M tokens | $0.4725 input$1.89 outputper 1M tokens | 65% | Official source ↗ |
| DeepSeek V3.1DeepSeekSydney on-demand | Text | $0.5974 input$1.7304 outputper 1M tokens | $0.20909 input$0.60564 outputper 1M tokens | 65% | Official source ↗ |
| DeepSeek V3.2DeepSeekUS on-demand | Text | $0.62 input$1.85 outputper 1M tokens | $0.217 input$0.6475 outputper 1M tokens | 65% | Official source ↗ |
| Gemini 2.5 FlashGoogle | Text | $0.30 input$2.50 outputper 1M tokens | $0.15 input$1.25 outputper 1M tokens | 50% | Official source ↗ |
| Gemini 2.5 Flash-LiteGoogle | Text | $0.10 input$0.40 outputper 1M tokens | $0.05 input$0.20 outputper 1M tokens | 50% | Official source ↗ |
| Gemini 2.5 ProGooglePrompts up to 200K tokens | Text | $1.25 input$10.00 outputper 1M tokens | $0.625 input$5.00 outputper 1M tokens | 50% | Official source ↗ |
| Gemini 3 Flash PreviewGoogleText, image, and video input; audio input is $1 / 1M tokens | Text | $0.50 input$3.00 outputper 1M tokens | $0.25 input$1.50 outputper 1M tokens | 50% | Official source ↗ |
| Gemini 3.5 FlashGoogle | Text | $0.75 input$4.50 outputper 1M tokens | $0.375 input$2.25 outputper 1M tokens | 50% | Official source ↗ |
| Gemini 3.5 Flash-LiteGoogle | Text | $0.30 input$2.50 outputper 1M tokens | $0.15 input$1.25 outputper 1M tokens | 50% | Official source ↗ |
| Gemini 3.6 FlashGoogleStandard pricing through December 31, 2026 | Text | $0.75 input$3.75 outputper 1M tokens | $0.375 input$1.875 outputper 1M tokens | 50% | Official source ↗ |
| Gemma 3 12B ITGoogleUS on-demand | Text | $0.09 input$0.29 outputper 1M tokens | $0.045 input$0.145 outputper 1M tokens | 50% | Official source ↗ |
| Gemma 3 27B PTGoogleUS on-demand | Text | $0.23 input$0.38 outputper 1M tokens | $0.115 input$0.19 outputper 1M tokens | 50% | Official source ↗ |
| Gemma 3 4B ITGoogleUS on-demand | Text | $0.04 input$0.08 outputper 1M tokens | $0.02 input$0.04 outputper 1M tokens | 50% | Official source ↗ |
| Gemma 4 26B-A4BGoogleUS on-demand | Text | $0.13 input$0.40 outputper 1M tokens | $0.065 input$0.20 outputper 1M tokens | 50% | Official source ↗ |
| Gemma 4 31BGoogleUS on-demand | Text | $0.14 input$0.40 outputper 1M tokens | $0.07 input$0.20 outputper 1M tokens | 50% | Official source ↗ |
| Gemma 4 E2BGoogleUS on-demand | Text | $0.04 input$0.08 outputper 1M tokens | $0.02 input$0.04 outputper 1M tokens | 50% | Official source ↗ |
| Llama 3 70B InstructMetaUS on-demand | Text | $2.65 input$3.50 outputper 1M tokens | $0.9275 input$1.225 outputper 1M tokens | 65% | Official source ↗ |
| Llama 3 8B InstructMetaUS on-demand | Text | $0.30 input$0.60 outputper 1M tokens | $0.105 input$0.21 outputper 1M tokens | 65% | Official source ↗ |
| Llama 3.1 405B InstructMetaUS on-demand | Text | $2.40 input$2.40 outputper 1M tokens | $0.84 input$0.84 outputper 1M tokens | 65% | Official source ↗ |
| Llama 3.1 70B InstructMetaUS on-demand | Text | $0.72 input$0.72 outputper 1M tokens | $0.252 input$0.252 outputper 1M tokens | 65% | Official source ↗ |
| Llama 3.1 8B InstructMetaUS on-demand | Text | $0.22 input$0.22 outputper 1M tokens | $0.077 input$0.077 outputper 1M tokens | 65% | Official source ↗ |
| Llama 3.2 11B InstructMetaUS on-demand | Text | $0.16 input$0.16 outputper 1M tokens | $0.056 input$0.056 outputper 1M tokens | 65% | Official source ↗ |
| Llama 3.2 1B InstructMetaUS on-demand | Text | $0.10 input$0.10 outputper 1M tokens | $0.035 input$0.035 outputper 1M tokens | 65% | Official source ↗ |
| Llama 3.2 3B InstructMetaUS on-demand | Text | $0.15 input$0.15 outputper 1M tokens | $0.0525 input$0.0525 outputper 1M tokens | 65% | Official source ↗ |
| Llama 3.2 90B InstructMetaUS on-demand | Text | $0.72 input$0.72 outputper 1M tokens | $0.252 input$0.252 outputper 1M tokens | 65% | Official source ↗ |
| Llama 3.3 70B InstructMetaUS on-demand | Text | $0.72 input$0.72 outputper 1M tokens | $0.252 input$0.252 outputper 1M tokens | 65% | Official source ↗ |
| Llama 4 Maverick 17B InstructMetaUS on-demand | Text | $0.24 input$0.97 outputper 1M tokens | $0.084 input$0.3395 outputper 1M tokens | 65% | Official source ↗ |
| Llama 4 Scout 17B InstructMetaUS on-demand | Text | $0.17 input$0.66 outputper 1M tokens | $0.0595 input$0.231 outputper 1M tokens | 65% | Official source ↗ |
| MiniMax M2MiniMaxUS on-demand | Text | $0.30 input$1.20 outputper 1M tokens | $0.105 input$0.42 outputper 1M tokens | 65% | Official source ↗ |
| MiniMax M2.1MiniMaxUS on-demand | Text | $0.30 input$1.20 outputper 1M tokens | $0.105 input$0.42 outputper 1M tokens | 65% | Official source ↗ |
| MiniMax M2.5MiniMaxUS on-demand | Text | $0.30 input$1.20 outputper 1M tokens | $0.105 input$0.42 outputper 1M tokens | 65% | Official source ↗ |
| Devstral 2 123BMistral AIUS on-demand | Text | $0.40 input$2.00 outputper 1M tokens | $0.14 input$0.70 outputper 1M tokens | 65% | Official source ↗ |
| Ministral 14B 3.0Mistral AI | Text | $0.20 input$0.20 outputper 1M tokens | $0.07 input$0.07 outputper 1M tokens | 65% | Official source ↗ |
| Ministral 3 8BMistral AI | Text | $0.15 input$0.15 outputper 1M tokens | $0.0525 input$0.0525 outputper 1M tokens | 65% | Official source ↗ |
| Ministral 3BMistral AI | Text | $0.10 input$0.10 outputper 1M tokens | $0.035 input$0.035 outputper 1M tokens | 65% | Official source ↗ |
| Mistral 7B InstructMistral AIUS on-demand | Text | $0.15 input$0.20 outputper 1M tokens | $0.0525 input$0.07 outputper 1M tokens | 65% | Official source ↗ |
| Mistral LargeMistral AIMistral Large 24.02, US on-demand; retired upstream | Text | $4.00 input$12.00 outputper 1M tokens | $1.40 input$4.20 outputper 1M tokens | 65% | Official source ↗ |
| Mistral Large 3Mistral AI | Text | $0.50 input$1.50 outputper 1M tokens | $0.175 input$0.525 outputper 1M tokens | 65% | Official source ↗ |
| Mistral SmallMistral AIMistral Small 24.02, US on-demand; retired upstream | Text | $1.00 input$3.00 outputper 1M tokens | $0.35 input$1.05 outputper 1M tokens | 65% | Official source ↗ |
| mistral-medium-3-5Mistral AI | Text | $1.50 input$7.50 outputper 1M tokens | $0.525 input$2.625 outputper 1M tokens | 65% | Official source ↗ |
| mistral-ocr-4-0Mistral AI | Text | $4 / 1K pages | $1.40 / 1K pages | 65% | Official source ↗ |
| Pixtral LargeMistral AIPixtral Large 25.02, US on-demand; retired upstream | Text | $2.00 input$6.00 outputper 1M tokens | $0.70 input$2.10 outputper 1M tokens | 65% | Official source ↗ |
| Kimi K2 ThinkingMoonshot AIUS on-demand | Text | $0.60 input$2.50 outputper 1M tokens | $0.21 input$0.875 outputper 1M tokens | 65% | Official source ↗ |
| Kimi K2.5Moonshot AIUS on-demand | Text | $0.60 input$3.00 outputper 1M tokens | $0.21 input$1.05 outputper 1M tokens | 65% | Official source ↗ |
| Nemotron Nano 3 30BNVIDIAUS on-demand | Text | $0.06 input$0.24 outputper 1M tokens | $0.021 input$0.084 outputper 1M tokens | 65% | Official source ↗ |
| NVIDIA Nemotron 3 Super 120BNVIDIAUS on-demand | Text | $0.15 input$0.65 outputper 1M tokens | $0.0525 input$0.2275 outputper 1M tokens | 65% | Official source ↗ |
| NVIDIA Nemotron Nano 12B v2 VL BF16NVIDIAUS on-demand | Text | $0.20 input$0.60 outputper 1M tokens | $0.07 input$0.21 outputper 1M tokens | 65% | Official source ↗ |
| NVIDIA Nemotron Nano 9B v2NVIDIAUS on-demand | Text | $0.06 input$0.23 outputper 1M tokens | $0.021 input$0.0805 outputper 1M tokens | 65% | Official source ↗ |
| codex-miniOpenAILLMHub alias for codex-mini-latest | Text | $1.50 input$6.00 outputper 1M tokens | $0.825 input$3.30 outputper 1M tokens | 45% | Official source ↗ |
| computer-use-previewOpenAI | Text | $3.00 input$12.00 outputper 1M tokens | $1.65 input$6.60 outputper 1M tokens | 45% | Official source ↗ |
| gpt-4.1OpenAI | Text | $2.00 input$8.00 outputper 1M tokens | $1.10 input$4.40 outputper 1M tokens | 45% | Official source ↗ |
| gpt-4.1-miniOpenAI | Text | $0.40 input$1.60 outputper 1M tokens | $0.22 input$0.88 outputper 1M tokens | 45% | Official source ↗ |
| gpt-4.1-nanoOpenAI | Text | $0.10 input$0.40 outputper 1M tokens | $0.055 input$0.22 outputper 1M tokens | 45% | Official source ↗ |
| gpt-4oOpenAI | Text | $2.50 input$10.00 outputper 1M tokens | $1.375 input$5.50 outputper 1M tokens | 45% | Official source ↗ |
| gpt-4o-miniOpenAI | Text | $0.15 input$0.60 outputper 1M tokens | $0.0825 input$0.33 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5OpenAI | Text | $1.25 input$10.00 outputper 1M tokens | $0.6875 input$5.50 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5-codexOpenAI | Text | $1.25 input$10.00 outputper 1M tokens | $0.6875 input$5.50 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5-miniOpenAI | Text | $0.25 input$2.00 outputper 1M tokens | $0.1375 input$1.10 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5-nanoOpenAI | Text | $0.05 input$0.40 outputper 1M tokens | $0.0275 input$0.22 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5-proOpenAI | Text | $15.00 input$120.00 outputper 1M tokens | $8.25 input$66.00 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5.1OpenAI | Text | $1.25 input$10.00 outputper 1M tokens | $0.6875 input$5.50 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5.1-codexOpenAI | Text | $1.25 input$10.00 outputper 1M tokens | $0.6875 input$5.50 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5.1-codex-maxOpenAI | Text | $1.25 input$10.00 outputper 1M tokens | $0.6875 input$5.50 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5.1-codex-miniOpenAI | Text | $0.25 input$2.00 outputper 1M tokens | $0.1375 input$1.10 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5.2OpenAI | Text | $1.75 input$14.00 outputper 1M tokens | $0.9625 input$7.70 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5.2-codexOpenAI | Text | $1.75 input$14.00 outputper 1M tokens | $0.9625 input$7.70 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5.3-codexOpenAI | Text | $1.75 input$14.00 outputper 1M tokens | $0.9625 input$7.70 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5.4OpenAIStandard, under 272K context | Text | $2.50 input$15.00 outputper 1M tokens | $1.375 input$8.25 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5.4-miniOpenAI | Text | $0.75 input$4.50 outputper 1M tokens | $0.4125 input$2.475 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5.4-nanoOpenAI | Text | $0.20 input$1.25 outputper 1M tokens | $0.11 input$0.6875 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5.4-proOpenAIStandard, under 272K context | Text | $30.00 input$180.00 outputper 1M tokens | $16.50 input$99.00 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5.5OpenAIStandard, under 272K context | Text | $5.00 input$30.00 outputper 1M tokens | $2.75 input$16.50 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5.6-lunaOpenAIStandard, short context | Text | $0.20 input$1.20 outputper 1M tokens | $0.11 input$0.66 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5.6-solOpenAIStandard, short context | Text | $4.00 input$20.00 outputper 1M tokens | $2.20 input$11.00 outputper 1M tokens | 45% | Official source ↗ |
| gpt-5.6-terraOpenAIStandard, short context | Text | $2.00 input$12.00 outputper 1M tokens | $1.10 input$6.60 outputper 1M tokens | 45% | Official source ↗ |
| gpt-6-astraOpenAIStandard, short context | Text | $10.00 input$50.00 outputper 1M tokens | $5.50 input$27.50 outputper 1M tokens | 45% | Official source ↗ |
| gpt-6-lunaOpenAIStandard, short context | Text | $0.10 input$0.50 outputper 1M tokens | $0.055 input$0.275 outputper 1M tokens | 45% | Official source ↗ |
| gpt-6.1-solOpenAIStandard, short context | Text | $2.00 input$10.00 outputper 1M tokens | $1.10 input$5.50 outputper 1M tokens | 45% | Official source ↗ |
| gpt-chat-latestOpenAILLMHub alias for OpenAI's current chat-latest model | Text | $5.00 input$30.00 outputper 1M tokens | $2.75 input$16.50 outputper 1M tokens | 45% | Official source ↗ |
| gpt-oss-120bOpenAIUS on-demand | Text | $0.15 input$0.60 outputper 1M tokens | $0.0825 input$0.33 outputper 1M tokens | 45% | Official source ↗ |
| gpt-oss-20bOpenAIUS on-demand | Text | $0.07 input$0.30 outputper 1M tokens | $0.0385 input$0.165 outputper 1M tokens | 45% | Official source ↗ |
| o1OpenAI | Text | $15.00 input$60.00 outputper 1M tokens | $8.25 input$33.00 outputper 1M tokens | 45% | Official source ↗ |
| o3OpenAI | Text | $2.00 input$8.00 outputper 1M tokens | $1.10 input$4.40 outputper 1M tokens | 45% | Official source ↗ |
| o3-miniOpenAI | Text | $1.10 input$4.40 outputper 1M tokens | $0.605 input$2.42 outputper 1M tokens | 45% | Official source ↗ |
| o3-proOpenAI | Text | $20.00 input$80.00 outputper 1M tokens | $11.00 input$44.00 outputper 1M tokens | 45% | Official source ↗ |
| o4-miniOpenAI | Text | $1.10 input$4.40 outputper 1M tokens | $0.605 input$2.42 outputper 1M tokens | 45% | Official source ↗ |
| Qwen3 235B A22B 2507QwenSydney on-demand | Text | $0.2266 input$0.9064 outputper 1M tokens | $0.07931 input$0.31724 outputper 1M tokens | 65% | Official source ↗ |
| Qwen3 32BQwenSydney on-demand | Text | $0.1545 input$0.618 outputper 1M tokens | $0.054075 input$0.2163 outputper 1M tokens | 65% | Official source ↗ |
| Qwen3 Coder 30B A3B InstructQwenSydney on-demand | Text | $0.1545 input$0.618 outputper 1M tokens | $0.054075 input$0.2163 outputper 1M tokens | 65% | Official source ↗ |
| Qwen3 Coder 480B A35B InstructQwenUS on-demand | Text | $0.45 input$1.80 outputper 1M tokens | $0.1575 input$0.63 outputper 1M tokens | 65% | Official source ↗ |
| Qwen3 Coder NextQwenUS on-demand | Text | $0.50 input$1.20 outputper 1M tokens | $0.175 input$0.42 outputper 1M tokens | 65% | Official source ↗ |
| Qwen3 Next 80B A3BQwenUS on-demand | Text | $0.15 input$1.20 outputper 1M tokens | $0.0525 input$0.42 outputper 1M tokens | 65% | Official source ↗ |
| Qwen3 VL 235B A22BQwenUS on-demand | Text | $0.53 input$2.66 outputper 1M tokens | $0.1855 input$0.931 outputper 1M tokens | 65% | Official source ↗ |
| Palmyra Vision 7BWriter | Text | $0.15 input$0.60 outputper 1M tokens | $0.0525 input$0.21 outputper 1M tokens | 65% | Official source ↗ |
| Palmyra X4Writer | Text | $2.50 input$10.00 outputper 1M tokens | $0.875 input$3.50 outputper 1M tokens | 65% | Official source ↗ |
| Palmyra X5Writer | Text | $0.60 input$6.00 outputper 1M tokens | $0.21 input$2.10 outputper 1M tokens | 65% | Official source ↗ |
| Grok 4xAIRetired grok-4-0709 alias; requests route to Grok 4.3 | Text | $1.25 input$2.50 outputper 1M tokens | $0.4375 input$0.875 outputper 1M tokens | 65% | Official source ↗ |
| Grok 4.1 Fast Non-ReasoningxAIRetired alias; requests route to Grok 4.3 with no reasoning effort | Text | $1.25 input$2.50 outputper 1M tokens | $0.4375 input$0.875 outputper 1M tokens | 65% | Official source ↗ |
| Grok 4.1 Fast ReasoningxAIRetired alias; requests route to Grok 4.3 with low reasoning effort | Text | $1.25 input$2.50 outputper 1M tokens | $0.4375 input$0.875 outputper 1M tokens | 65% | Official source ↗ |
| Grok 4.20 Non-ReasoningxAIPrompts under 200K tokens | Text | $1.25 input$2.50 outputper 1M tokens | $0.4375 input$0.875 outputper 1M tokens | 65% | Official source ↗ |
| Grok 4.20 ReasoningxAIPrompts under 200K tokens | Text | $1.25 input$2.50 outputper 1M tokens | $0.4375 input$0.875 outputper 1M tokens | 65% | Official source ↗ |
| Grok 4.3xAIPrompts under 200K tokens | Text | $1.25 input$2.50 outputper 1M tokens | $0.4375 input$0.875 outputper 1M tokens | 65% | Official source ↗ |
| Grok 4.6xAIPrompts under 200K tokens | Text | $2.00 input$6.00 outputper 1M tokens | $0.70 input$2.10 outputper 1M tokens | 65% | Official source ↗ |
| Grok 4.7xAIPrompts under 200K tokens | Text | $2.00 input$6.00 outputper 1M tokens | $0.70 input$2.10 outputper 1M tokens | 65% | Official source ↗ |
| Grok Code Fast 1xAIRetired alias; requests route to grok-build-0.1. Short-context rate shown | Text | $1.00 input$2.00 outputper 1M tokens | $0.35 input$0.70 outputper 1M tokens | 65% | Official source ↗ |
| GLM 4.7 FlashZ.aiUS on-demand | Text | $0.07 input$0.40 outputper 1M tokens | $0.0245 input$0.14 outputper 1M tokens | 65% | Official source ↗ |
| GLM 5.0Z.aiUS on-demand | Text | $1.00 input$3.20 outputper 1M tokens | $0.35 input$1.12 outputper 1M tokens | 65% | Official source ↗ |
| Nova ReelAmazon | Video | $0.08 / second (720p, 24 fps) | $0.028 / second (720p, 24 fps) | 65% | Official source ↗ |
| Gemini Omni FlashGoogle$1.50 input / $17.50 video output per 1M tokens | Video | $0.10 / second of 720p video output | $0.05 / second of 720p video output | 50% | Official source ↗ |
| Veo 3.1 FastGoogle | Video | $0.10 / second (720p) | $0.05 / second (720p) | 50% | Official source ↗ |
| Veo 3.1 GenerateGoogle | Video | $0.40 / second (720p or 1080p) | $0.20 / second (720p or 1080p) | 50% | Official source ↗ |
| Veo 3.1 LiteGoogle | Video | $0.05 / second (720p) | $0.025 / second (720p) | 50% | Official source ↗ |
| Sora 2OpenAI | Video | $0.10 / second (720p) | $0.055 / second (720p) | 45% | Official source ↗ |
Scope and limitations
How this price index is calculated
Official prices come from the provider source linked in each row. LLMHub prices apply the model manufacturer discount defined for the current catalog. Cache, batch, regional, long-context, and special service-tier prices may differ.
Read the pricing methodology