Skip to main content

LLM models

797 large language models, ranked by quality, with prices from every provider that serves them.

/
DeepSeek V4 Flash 0731Prompt cachingJSON$1.32/1Mvia EmpirioLabs AI1M$0.44/1M$1.32/1M——
DeepSeek V4 Flash Vision ExpMITPrompt caching+4$0.48/1Mvia CometAPI1.05M$0.12/1M$0.48/1M——
DeepSeek V4 ProMITPrompt caching+3$1.58/1Mvia CometAPI1M$0.66/1M$1.98/1M——
DeepSeek V4 ProPrompt cachingJSON$4.80/1Mvia EmpirioLabs AI1M$2.40/1M$4.80/1M——
DeepSeek V4 ProPrompt cachingJSON$3.30/1Mvia EmpirioLabs AI1M$1.65/1M$3.30/1M——
DeepSeek V4 ProPrompt cachingJSON$4.80/1Mvia EmpirioLabs AI1M$2.40/1M$4.80/1M——
DeepSeek V4 Pro 0423Prompt cachingJSON+2$2.60/1Mvia Requesty1.05M$1.30/1M$2.60/1M——
DeepSeek V4.1 Flash Economy 261017$0.48/1Mvia BytePlus—$0.12/1M$0.48/1M——
DeepSeek Vl2Open weights · with terms$0.16/1Mvia AIHubMix—$0.16/1M$0.16/1M——
DeepSeek-OCRMITVision$0.02/1Mvia AIHubMix8K$0.02/1M$0.02/1M——
DeepSeek-V3.1MITPrompt caching+3$0.798/1Mvia Poe164K$0.212/1M$0.798/1M1420—
DeepSeek-V3.2-ExpMITJSON+2$0.308/1Mvia APIMart164K$0.206/1M$0.308/1M1425—
DeepSeek-V3.2-SpecialeMIT$1.68/1Mvia Impossibl—$0.58/1M$1.68/1M——
DeplotApache 2.0Free/1Mvia Nvidia—Free/1MFree/1M——
Devstral-2-123B-Instruct-2512-int4-AutoRoundPrompt cachingJSON+1$2/1Mvia Amazon Bedrock262K$0.40/1M$2/1M——
DiffusionGemmaApache 2.0Free/1Mvia Nvidia—Free/1MFree/1M——
Doubao 1.5 Pro 32k$0.335/1Mvia AIHubMix—$0.134/1M$0.335/1M——
Doubao 1.5 Thinking Pro$2.48/1Mvia AIHubMix—$0.62/1M$2.48/1M——
Doubao 1.5 Thinking Vision Pro 250428$2/1Mvia AIHubMix—$2/1M$2/1M——
Doubao 1.5 Vision Pro 32K$1.38/1Mvia AIHubMix—$0.46/1M$1.38/1M——
Doubao Lite 128K$0.28/1Mvia AIHubMix—$0.14/1M$0.28/1M——
Doubao Lite 32K$0.12/1Mvia AIHubMix—$0.06/1M$0.12/1M——
Doubao Lite 4K$0.12/1Mvia AIHubMix—$0.06/1M$0.12/1M——
Doubao Pro 128K$1.44/1Mvia AIHubMix—$0.80/1M$1.44/1M——
Doubao Pro 256K$1.44/1Mvia AIHubMix—$0.80/1M$1.44/1M——
Doubao Pro 32K$0.35/1Mvia AIHubMix—$0.14/1M$0.35/1M——
Doubao Pro 4K$0.35/1Mvia AIHubMix—$0.14/1M$0.35/1M——
Doubao Seed 1.6 LitePrompt cachingJSON+3$0.656/1Mvia AIHubMix256K$0.082/1M$0.656/1M——
Doubao Seed 2.0 Code PreviewPrompt cachingReasoning+2$2.24/1Mvia ZenMux256K$0.50/1M$3/1M——
Doubao Seed 2.0 Lite 260428JSONReasoning+2$0.51/1Mvia ZenMux256K$0.25/1M$2/1M——
Doubao Seed 2.0 Mini 260428JSONReasoning+2$0.10/1Mvia Fal256K$0.10/1M$0.40/1M——
Doubao Seed 2.0 ProPrompt cachingJSON+3$2/1Mvia CometAPI256K$0.50/1M$3/1M——
Doubao Seed 2.1 ProPrompt cachingJSON+3$3.33/1Mvia CometAPI256K$0.667/1M$3.33/1M——
Doubao Seed CharacterPrompt cachingJSON+3$0.295/1Mvia ZenMux256K$0.118/1M$0.295/1M——
Doubao-Seed-1.8Prompt cachingReasoning+2$0.28/1Mvia ZenMux256K$0.11/1M$0.28/1M——
Ember-1Prompt cachingJSON+3$15/1Mvia Fireworks AI1.05M$3/1M$15/1M——
ERNIE 4.5JSONTool calling+1$0.272/1Mvia AIHubMix160K$0.068/1M$0.272/1M——
ERNIE 4.5 0.3bJSONTool calling+1$0.054/1Mvia AIHubMix—$0.014/1M$0.054/1M——
ERNIE 4.5 21B A3BApache 2.0$0.28/1Mvia Helicone—$0.07/1M$0.28/1M——
ERNIE 4.5 300B A47BJSONTool calling+1$1.10/1Mvia Jiekou.AI—$0.28/1M$1.10/1M——
ERNIE 4.5 Turbo 128K PreviewJSONTool calling+1$0.432/1Mvia AIHubMix—$0.108/1M$0.432/1M——
ERNIE 4.5 Turbo VLJSONTool calling+1$1.20/1Mvia AIHubMix139K$0.40/1M$1.20/1M——
ERNIE 4.5 VL 424B A47B$1.25/1Mvia Jiekou.AI—$0.42/1M$1.25/1M——
ERNIE 5.0Prompt cachingJSON+3$3.29/1Mvia AIHubMix183K$0.822/1M$3.29/1M——
ERNIE 5.0 Thinking ExpPrompt cachingReasoning$3.29/1Mvia AIHubMix119K$0.822/1M$3.29/1M——
ERNIE X1 TurboJSONReasoning+1$0.544/1Mvia AIHubMix51K$0.136/1M$0.544/1M——
ERNIE X1.1 PreviewJSONReasoning+1$0.544/1Mvia AIHubMix119K$0.136/1M$0.544/1M——
RFlint 40B FreeJSONReasoning+1Free/1Mvia OpenCode262KFree/1MFree/1M——
Fugu UltraPrompt cachingJSON+3$30/1Mvia EmpirioLabs AI1M$5/1M$30/1M——
Fugu Ultra v1.1Prompt cachingVision$30.30/1Mvia Poe1M$5.05/1M$30.30/1M——

Frequently asked questions




Can't find what you're looking for? Contact us