Prices · Every Tracked Model

Every AI model Tokenando tracks, grouped by provider, each linking to its full pricing and benchmark profile. For an interactive, sortable view of the whole market in one table, open the AI model prices.

As of September 2026, this directory covers 651 AI models from 70 providers, each with its published input and output price per million tokens. 8 of them are currently priced at zero on both input and output. The largest published context window is 2,000,000 tokens.

01.AI

9 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Yi-Lightningefficient$0.14$0.14$0.1416K
• Yi-6Befficient$0.15$0.15$0.154K
• Yi-9Befficient$0.30$0.30$0.304K
• Yi-VL-6Bmultimodal$0.30$0.30$0.304K
• Yi-Large-Turboefficient$0.38$0.38$0.3816K
• Yi-34B-Chatfrontier$0.80$0.80$0.804K
• Yi-34Bfrontier$0.80$0.80$0.804K
• Yi-Largefrontier$3.00$3.00$3.0032K
• Yi-VL-34Bmultimodal$3.50$3.50$3.504K

AI21 Labs

3 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Jamba 1.5 Miniefficient$0.20$0.40$0.26256K
• Jamba Instructfrontier$0.50$0.70$0.56256K
• Jamba 1.5 Largefrontier$2.00$8.00$3.80256K

Amazon

14 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Titan Embeddings V2embed$0.02——8K
• Nova Microefficient$0.04$0.14$0.07128K
• Nova Micro 1.0text->text$0.04$0.14$0.07128K
• Nova Canvasmultimodal$0.08———
• Nova Liteefficient$0.06$0.24$0.11300K
• Nova Lite 1.0text+image->text$0.06$0.24$0.11300K
• Titan Text Liteefficient$0.15$0.20$0.164K
• Titan Text Premierefficient$0.50$1.50$0.8032K
• Nova 2 Liteefficient$0.30$2.50$0.961.0M
• Nova 2 Profrontier$0.80$3.20$1.521.0M
• Nova Promultimodal$0.80$3.20$1.52300K
• Nova Pro 1.0text+image->text$0.80$3.20$1.52300K
• Nova Premierfrontier$2.50$12.50$5.50300K
• Nova Premier 1.0text+image->text$2.50$12.50$5.501.0M

Anthropic

30 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Claude Haiku 4.5 (batch)text+image+file->text$0.50$2.50$1.10200K
• Claude Haiku 4.5efficient$0.80$4.00$1.76200K
• Claude Haiku 3.5efficient$0.80$4.00$1.76200K
• Claude Sonnet 5 (batch)text+image+file->text$1.00$5.00$2.201.0M
• Claude Sonnet 4.6 (batch)text+image+file->text$1.50$7.50$3.301.0M
• Claude Sonnet 4.5 (batch)text+image+file->text$1.50$7.50$3.301.0M
• Claude Sonnet 5multimodal$2.00$10.00$4.401.0M
• Claude Opus 5.5 (batch)text+image+file->text$2.00$10.00$4.401.0M
• Claude Opus 5 (batch)text+image+file->text$2.50$12.50$5.501.0M
• Claude Opus 4.8 (batch)text+image+file->text$2.50$12.50$5.501.0M
• Claude Opus 4.7 (batch)text+image+file->text$2.50$12.50$5.501.0M
• Claude Opus 4.6 (batch)text+image+file->text$2.50$12.50$5.501.0M
• Claude Opus 4.5 (batch)text+image+file->text$2.50$12.50$5.50200K
• Claude Sonnet 4.6multimodal$3.00$15.00$6.601.0M
• Claude Sonnet 4.5multimodal$3.00$15.00$6.60200K
• Claude Sonnet 3.7reasoning$3.00$15.00$6.60200K
• Claude Sonnet 3.5multimodal$3.00$15.00$6.60200K
• Claude Sonnet 4text+image+file->text$3.00$15.00$6.60200K
• Claude Opus 5.5text+image+file->text$4.00$20.00$8.801.0M
• Claude Opus 5frontier$5.00$25.00$11.001.0M
• Claude Opus 4.8frontier$5.00$25.00$11.001.0M
• Claude Opus 4.7frontier$5.00$25.00$11.001.0M
• Claude Opus 4.6frontier$5.00$25.00$11.001.0M
• Claude Fable 5.1 (batch)text+image+file->text$5.00$25.00$11.001.0M
• Claude Fable 5 (batch)text+image+file->text$5.00$25.00$11.001.0M
• Claude Opus 4.1 (batch)text+image+file->text$7.50$37.50$16.50200K
• Claude Fable 5frontier$10.00$50.00$22.001.0M
• Claude Fable 5.1text+image+file->text$10.00$50.00$22.001.0M
• Claude Opus 4.5frontier$15.00$75.00$33.00200K
• Claude Opus 4.1text+image+file->text$15.00$75.00$33.00200K

Anyscale

4 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Mistral 7B (Anyscale)efficient$0.15$0.15$0.1532K
• Mixtral 8x7B (Anyscale)efficient$0.50$0.50$0.5032K
• Llama 3.1 70B (Anyscale)efficient$1.00$1.00$1.00128K
• CodeLlama 70B (Anyscale)efficient$1.00$1.00$1.0016K

Baidu

4 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• ERNIE 4.5 VL 424B A47Btext+image->text$0.42$1.25$0.67123K
• ERNIE 3.5 8Kefficient$0.55$1.10$0.728K
• ERNIE 4.0 Turbo 8Kfrontier$3.50$10.50$5.608K
• ERNIE 4.0 8Kfrontier$4.20$12.60$6.728K

ByteDance

6 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Doubao-Lite-128kefficient$0.04$0.09$0.05128K
• Doubao-Lite-32kefficient$0.04$0.09$0.0532K
• UI-TARS 7Btext+image->text$0.10$0.20$0.13128K
• Doubao-Pro-32kefficient$0.11$0.28$0.1632K
• Doubao-Pro-256kfrontier$0.56$1.40$0.81256K
• Doubao-Pro-128kfrontier$0.56$1.40$0.81128K

Cerebras

4 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Llama-3.1-8B (Cerebras)efficient$0.10$0.10$0.10128K
• DeepSeek-R1 (Cerebras)reasoning$0.55$0.99$0.6864K
• Llama-3.3-70B (Cerebras)efficient$0.59$0.99$0.71128K
• Llama-3.1-405B (Cerebras)frontier$0.99$0.99$0.99128K

Cohere

12 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• North Mini Code (free)text->text$0.00$0.00$0.00256K
• Command R7Befficient$0.04$0.15$0.07128K
• Embed v3 Englishembed$0.10——1K
• Embed v3 Multilingualembed$0.10——1K
• Command Refficient$0.15$0.60$0.28128K
• Aya Expanse 32Bfrontier$0.50$1.50$0.80128K
• Aya Expanse 8Befficient$0.50$1.50$0.808K
• Rerank v3.5embed$2.00———
• Rerank v3 Multilingualembed$2.00———
• Command A+frontier$2.50$10.00$4.75256K
• Command Afrontier$2.50$10.00$4.75256K
• Command R+frontier$2.50$10.00$4.75128K

Databricks

3 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• DBRX Instructfrontier$0.75$2.25$1.2032K
• DBRX Basefrontier$0.75$2.25$1.2032K
• Llama 3.1 70B (DB)efficient$1.00$3.00$1.60128K

DeepInfra

11 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Gemma 2 9B (DI)efficient$0.06$0.06$0.068K
• Mistral 7B (DI)efficient$0.07$0.07$0.0732K
• Mixtral 8x7B (DI)efficient$0.24$0.24$0.2432K
• Llama 3.3 70B (DI)efficient$0.23$0.40$0.28128K
• Llama 3.1 70B (DI)efficient$0.35$0.40$0.36128K
• Qwen2.5-72B (DI)frontier$0.35$0.40$0.36128K
• Phind-CodeLlama-34B (DI)efficient$0.60$0.60$0.6016K
• Yi-34B-Chat (DI)frontier$0.60$0.60$0.604K
• WizardLM-2 8x22B (DI)frontier$0.63$0.63$0.6364K
• Llama 3.1 405B (DI)frontier$0.80$0.80$0.80128K
• DeepSeek-R1 (DI)reasoning$0.55$2.19$1.0464K

DeepSeek

25 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• DeepSeek V4 Flash 0731text->text$0.06$0.12$0.081.3M
• DeepSeek-R1-Distill-8Breasoning$0.07$0.20$0.11128K
• DeepSeek V4 Flash 0423text->text$0.09$0.17$0.111.0M
• DeepSeek-R1-Distill-14Breasoning$0.10$0.35$0.17128K
• DeepSeek V4.1 Flash (batch)text+image->text$0.11$0.34$0.181.0M
• DeepSeek-V4-Flashefficient$0.14$0.28$0.181.0M
• DeepSeek-Coder-V2efficient$0.14$0.28$0.18128K
• DeepSeek-R1-Distill-32Breasoning$0.20$0.50$0.29128K
• DeepSeek V3.2text->text$0.27$0.40$0.31164K
• DeepSeek V3.2 Exptext->text$0.27$0.41$0.31164K
• DeepSeek V4 Flash Vision Exptext+image->text$0.22$0.66$0.351.0M
• DeepSeek V3.1text->text$0.25$0.95$0.46164K
• DeepSeek V3.1 Terminustext->text$0.27$1.00$0.49164K
• DeepSeek-R1-Distill-70Breasoning$0.35$0.88$0.51128K
• DeepSeek-V3frontier$0.27$1.10$0.5264K
• DeepSeek-V3-0324frontier$0.27$1.10$0.52128K
• DeepSeek V4.1 Flashtext+image->text$0.30$1.20$0.571.0M
• R1 Distill Llama 70Btext->text$0.80$0.80$0.808K
• R1 0528text->text$0.50$2.15$0.99164K
• DeepSeek-R1reasoning$0.55$2.19$1.0464K
• DeepSeek-R1-0528reasoning$0.55$2.19$1.0464K
• R1text->text$0.70$2.50$1.2464K
• DeepSeek V4 Pro 0813text->text$0.98$2.95$1.571.0M
• DeepSeek V4 Pro 0423text->text$1.60$3.20$2.081.0M
• DeepSeek-V4-Profrontier$1.74$3.48$2.261.0M

Fireworks AI

10 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Mercury 2.5text->text$0.04$0.15$0.07260K
• Llama 3.1 8B (fw)efficient$0.10$0.10$0.10131K
• Mixtral 8x7B (fw)efficient$0.20$0.20$0.2032K
• Mercury 2text->text$0.25$0.75$0.40128K
• Phind-CodeLlama-34B (fw)efficient$0.80$0.80$0.8016K
• Qwen2.5-72B (fw)frontier$0.90$0.90$0.9032K
• Yi-34B (fw)frontier$0.90$0.90$0.904K
• Llama 3.1 405B (fw)frontier$3.00$3.00$3.00131K
• DeepSeek-R1 (fw)reasoning$3.00$8.00$4.5064K
• Ember-1text+image->text$3.00$15.00$6.601.0M

Google

52 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Lyria 3 Pro Previewtext+image->text+audio$0.00$0.00$0.001.0M
• Lyria 3 Clip Previewtext+image->text+audio$0.00$0.00$0.001.0M
• Gemma 2 2Befficient$0.02$0.02$0.028K
• text-embedding-004embed$0.03——2K
• Gemma 3 4Btext+image->text$0.05$0.10$0.07131K
• Gemini 1.5 Flash-8Befficient$0.04$0.15$0.071.0M
• Gemma 3 12Btext+image->text$0.05$0.15$0.08131K
• Gemma 3 9Befficient$0.09$0.09$0.09128K
• Gemma 2 9Befficient$0.09$0.09$0.098K
• Gemini 2.5 Flash Lite (batch)text+image+file+audio+video->text$0.05$0.20$0.101.0M
• Gemma 4 26B A4Btext+image+video->text$0.07$0.23$0.11262K
• Gemini 2.0 Flash Liteefficient$0.07$0.30$0.141.0M
• Gemini 1.5 Flashefficient$0.07$0.30$0.141.0M
• Gemma 4 31Btext+image+video->text$0.09$0.34$0.17262K
• Gemini 2.0 Flashefficient$0.10$0.40$0.191.0M
• Gemini 2.5 Flash Litetext+image+file+audio+video->text$0.10$0.40$0.191.0M
• Gemma 3 27Bfrontier$0.27$0.27$0.27128K
• Gemma 2 27Befficient$0.27$0.27$0.278K
• Gemini 2.5 Flashmultimodal$0.15$0.60$0.281.0M
• Gemini 3.1 Flash Lite (batch)text+image+file+audio+video->text$0.13$0.75$0.311.0M
• Gemini 3.5 Flash Lite (batch)text+image+file+audio+video->text$0.15$1.25$0.481.0M
• Gemini 2.5 Flash (batch)text+image+file+audio+video->text$0.15$1.25$0.481.0M
• Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image)text+image->text+image$0.25$1.50$0.6366K
• Gemini 3.1 Flash Litetext+image+file+audio+video->text$0.25$1.50$0.631.0M
• Gemini 3.1 Flash Lite Previewtext+image+file+audio+video->text$0.25$1.50$0.631.0M
• Gemini 3 Flash Preview (batch)text+image+file+audio+video->text$0.25$1.50$0.631.0M
• Gemini 3.8 Flash (batch)text+image+file+audio+video->text$0.38$1.88$0.821.0M
• Gemini 3.7 Flash (batch)text+image+file+audio+video->text$0.38$1.88$0.821.0M
• Gemini 3.6 Flash (batch)text+image+file+audio+video->text$0.38$1.88$0.821.0M
• Gemini 3.5 Flash Litetext+image+file+audio+video->text$0.30$2.50$0.961.0M
• Nano Banana (Gemini 2.5 Flash Image)text+image->text+image$0.30$2.50$0.9633K
• Gemini 3 Flashefficient$0.50$3.00$1.251.0M
• Nano Banana 2 (Gemini 3.1 Flash Image)text+image->text+image$0.50$3.00$1.25131K
• Nano Banana 2 (Gemini 3.1 Flash Image Preview)text+image->text+image$0.50$3.00$1.2566K
• Gemini 3 Flash Previewtext+image+file+audio+video->text$0.50$3.00$1.251.0M
• Gemini 3.8 Flashtext+image+file+audio+video->text$0.75$3.75$1.651.0M
• Gemini 3.7 Flashtext+image+file+audio+video->text$0.75$3.75$1.651.0M
• Gemini 3.5 Flash (batch)text+image+file+audio+video->text$0.75$4.50$1.871.0M
• Gemini 2.5 Pro (batch)text+image+file+audio+video->text$0.63$5.00$1.941.0M
• Gemini 1.5 Profrontier$1.25$5.00$2.382.0M
• Gemini 3.1 Pro Preview (batch)text+image+file+audio+video->text$1.00$6.00$2.501.0M
• Gemini 3.6 Flashmultimodal$1.50$7.50$3.301.1M
• Gemini 3.5 Flashmultimodal$1.50$9.00$3.751.0M
• Gemini 2.5 Profrontier$1.25$10.00$3.881.0M
• Gemini 2.5 Pro Preview 06-05text+image+file+audio->text$1.25$10.00$3.881.0M
• Gemini 3.5 Profrontier$2.00$12.00$5.001.0M
• Gemini 3.1 Profrontier$2.00$12.00$5.001.0M
• Gemini 3 Profrontier$2.00$12.00$5.001.0M
• Nano Banana Pro (Gemini 3 Pro Image)text+image->text+image$2.00$12.00$5.00131K
• Gemini 3.1 Pro Preview Custom Toolstext+image+file+audio+video->text$2.00$12.00$5.001.0M
• Gemini 3.1 Pro Previewtext+image+file+audio+video->text$2.00$12.00$5.001.0M
• Nano Banana Pro (Gemini 3 Pro Image Preview)text+image->text+image$2.00$12.00$5.0066K

Groq

11 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Llama 3.1 8B (Groq)efficient$0.05$0.08$0.06128K
• Llama 3.2 3B (Groq)efficient$0.06$0.06$0.06128K
• Llama 3.2 11B Vision (Groq)multimodal$0.18$0.18$0.18128K
• Gemma 2 9B (Groq)efficient$0.20$0.20$0.208K
• Mixtral 8x7B (Groq)efficient$0.24$0.24$0.2432K
• Llama 3.3 70B (Groq)efficient$0.59$0.79$0.65128K
• Llama 3.1 70B (Groq)efficient$0.59$0.79$0.65128K
• Qwen2.5-72B (Groq)frontier$0.79$0.79$0.79128K
• Qwen2.5-Coder-32B (Groq)efficient$0.79$0.79$0.79128K
• DeepSeek-R1 (Groq)reasoning$0.75$0.99$0.82128K
• Llama 3.1 405B (Groq)frontier$2.99$2.99$2.99128K

Hyperbolic

4 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Llama 3.1 70B (Hyp)efficient$0.40$0.40$0.40128K
• Hermes-3-70B (Hyp)frontier$0.40$0.40$0.40128K
• Qwen2.5-72B (Hyp)frontier$0.40$0.40$0.40128K
• Llama 3.1 405B (Hyp)frontier$4.00$4.00$4.00128K

IBM

7 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Granite 4.0 Microtext->text$0.02$0.11$0.05131K
• Granite 3.1 2B Instructefficient$0.03$0.10$0.05128K
• Granite 3.1 8B Instructefficient$0.05$0.25$0.11128K
• Granite 3.0 8B Denseefficient$0.05$0.25$0.114K
• Granite 4.2 8Btext->text$0.06$0.25$0.12131K
• Granite 20B Multilingualefficient$0.40$0.40$0.408K
• Granite Code 34Befficient$0.35$1.05$0.568K

Inflection AI

1 model

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Pi (Inflection-2.5)frontier$2.50$10.00$4.7532K

Lepton AI

3 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Mistral 7B (Lepton)efficient$0.07$0.07$0.0732K
• Mixtral 8x7B (Lepton)efficient$0.50$0.50$0.5032K
• Llama 3.1 70B (Lepton)efficient$0.80$0.80$0.80128K

Meta

31 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Llama 3.2 1Befficient$0.04$0.04$0.04128K
• Llama 3.1 8B Instructtext->text$0.05$0.08$0.06131K
• Llama 3.2 3Befficient$0.06$0.06$0.06128K
• Llama 3.2 1B Instructtext->text$0.03$0.20$0.0860K
• Llama 3.1 8Befficient$0.10$0.10$0.10128K
• Muse Spark 1.3 Contributortext+image+file+audio+video->text$0.10$0.20$0.131.0M
• Muse Spark 1.2 Contributortext+image+file+audio+video->text$0.10$0.20$0.131.0M
• Llama 3.2 3B Instructtext->text$0.05$0.33$0.13131K
• Llama 3.2 11B Visionmultimodal$0.16$0.16$0.16128K
• Llama 3.3 70B Instructtext->text$0.10$0.32$0.17131K
• Llama 4 Scoutefficient$0.10$0.35$0.17512K
• Llama 2 7B Chatefficient$0.18$0.18$0.184K
• CodeLlama 7B Instructefficient$0.18$0.18$0.1816K
• Llama Guard 4 12Btext+image->text$0.18$0.18$0.18164K
• Llama 3 8Befficient$0.20$0.20$0.208K
• Llama 2 13B Chatefficient$0.22$0.22$0.224K
• CodeLlama 13B Instructefficient$0.22$0.22$0.2216K
• Llama 3.3 70Befficient$0.23$0.40$0.28128K
• Llama 4 Maverickfrontier$0.20$0.60$0.32128K
• CodeLlama 34B Instructefficient$0.35$0.35$0.3516K
• Llama 3.1 70Befficient$0.35$0.40$0.36128K
• Llama 3.1 70B Instructtext->text$0.40$0.40$0.40131K
• Muse Glimmer 30Btext+image->text$0.30$1.20$0.57131K
• Llama 3 70Befficient$0.59$0.79$0.658K
• Llama 3.1 405Bfrontier$0.80$0.80$0.80128K
• Llama 3.2 90B Visionmultimodal$0.88$0.88$0.88128K
• Llama 2 70B Chatefficient$0.90$0.90$0.904K
• CodeLlama 70B Instructefficient$0.90$0.90$0.9016K
• Muse Spark 1.2multimodal$1.25$4.25$2.151.0M
• Muse Spark 1.3text+image+file+audio+video->text$1.25$4.25$2.151.0M
• Muse Spark 1.1text+image+file+audio+video->text$1.25$4.25$2.151.0M

Microsoft

8 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Phi-4 Minireasoning$0.04$0.16$0.08128K
• Phi-4reasoning$0.07$0.28$0.1316K
• Phi-3.5 Miniefficient$0.13$0.52$0.25128K
• Phi-3 Miniefficient$0.13$0.52$0.25128K
• Phi-3 Smallefficient$0.15$0.60$0.28128K
• Phi-3.5 MoEefficient$0.16$0.64$0.30128K
• Phi-3 Mediumefficient$0.17$0.68$0.32128K
• WizardLM-2 8x22Btext->text$0.62$0.62$0.6266K

MiniMax

13 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• ABAB 5.5cefficient$0.05$0.05$0.0516K
• ABAB 5.5sefficient$0.15$0.75$0.3316K
• ABAB 6.5tefficient$0.45$0.45$0.458K
• MiniMax-01text+image->text$0.20$1.10$0.471.0M
• MiniMax M2.5text->text$0.27$1.08$0.51205K
• MiniMax M3text+image+video->text$0.30$1.20$0.571.0M
• MiniMax M2.7text->text$0.30$1.20$0.57205K
• MiniMax M2-hertext->text$0.30$1.20$0.5766K
• MiniMax M2.1text->text$0.30$1.20$0.57205K
• MiniMax M2text->text$0.30$1.20$0.57205K
• MiniMax M1text->text$0.40$2.20$0.941.0M
• MiniMax-Text-01frontier$0.70$2.80$1.331.0M
• ABAB 6.5sfrontier$1.00$5.00$2.208K

Mistral

36 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Mistral Small 3text->text$0.05$0.08$0.0633K
• Ministral 3 8B 2512 (batch)text+image->text$0.07$0.07$0.07262K
• Mistral 7B v0.3efficient$0.08$0.08$0.0832K
• Ministral 3 3B 2512text+image->text$0.10$0.10$0.10131K
• mistral-embedembed$0.10——8K
• Mistral Small 3.2 24Btext+image->text$0.09$0.25$0.14256K
• Mistral Small 4 (batch)text+image->text$0.07$0.30$0.14262K
• Pixtral 12Bmultimodal$0.15$0.15$0.15128K
• Mistral Nemoefficient$0.15$0.15$0.15128K
• Ministral 3 8B 2512text+image->text$0.15$0.15$0.15262K
• Mistral Small 4efficient$0.10$0.30$0.16128K
• Mistral Small 3.2efficient$0.10$0.30$0.16128K
• Voxtral Small 24B 2507text+file+audio->text$0.10$0.30$0.1633K
• Ministral 3 14B 2512text+image->text$0.20$0.20$0.20262K
• Mixtral 8x7B v0.1efficient$0.24$0.24$0.2432K
• Codestral 2508 (batch)text+file->text$0.15$0.45$0.24256K
• Codestral Mambaefficient$0.25$0.25$0.25256K
• Codestralefficient$0.20$0.60$0.32256K
• Sabatext+file->text$0.20$0.60$0.3233K
• Mistral Large 3 2512 (batch)text+image+file->text$0.25$0.75$0.40262K
• Mistral Small 3.1 24Btext+image->text$0.35$0.56$0.41128K
• Mistral Medium 3.1 (batch)text+image+file->text$0.20$1.00$0.44131K
• Codestral 2508text+file->text$0.30$0.90$0.48256K
• Mistral Large 3frontier$0.50$1.50$0.80256K
• Mistral Large 3 2512text+image+file->text$0.50$1.50$0.80262K
• Devstral 2 2512text+file->text$0.40$2.00$0.88262K
• Mistral Medium 3.1text+image+file->text$0.40$2.00$0.88131K
• Mistral Medium 3text+image+file->text$0.40$2.00$0.88131K
• Mixtral 8x22Befficient$0.90$0.90$0.9064K
• Mistral Medium 3.5 (batch)text+image+file->text$0.75$3.75$1.65262K
• Mistral Large 2frontier$2.00$6.00$3.20128K
• Pixtral Largemultimodal$2.00$6.00$3.20128K
• Mistral Large 2407text+file->text$2.00$6.00$3.20131K
• Mixtral 8x22B Instructtext+file->text$2.00$6.00$3.2066K
• Mistral Largetext+file->text$2.00$6.00$3.20128K
• Mistral Medium 3.5multimodal$1.50$7.50$3.30256K

Moonshot AI

12 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Moonshot v1 8kefficient$0.12$0.12$0.128K
• Moonshot v1 32kefficient$0.40$0.40$0.4032K
• Kimi K2.5text+image->text$0.45$2.25$0.99262K
• Kimi K2 0711text->text$0.57$2.30$1.09131K
• Kimi K2 Thinkingtext->text$0.60$2.50$1.17262K
• Kimi K2 0905text->text$0.60$2.50$1.17262K
• Kimi K2.7 Codetext+image->text$0.66$3.30$1.45262K
• Moonshot v1 128kfrontier$1.80$1.80$1.80128K
• Kimi K2.6text+image->text$0.95$4.00$1.86262K
• Kimi k1.5reasoning$2.50$10.00$4.75128K
• Kimi K3 (batch)text+image+video->text$2.28$11.40$5.021.0M
• Kimi K3frontier$3.00$15.00$6.601.0M

Nvidia

12 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Nemotron 3 Nano Omni (free)text+image+audio+video->text$0.00$0.00$0.00256K
• Phi-3-Mini-4K (NIM)efficient$0.04$0.04$0.044K
• Nemotron 3 Nano 30B A3Btext->text$0.05$0.20$0.10262K
• Nemotron 3.5 Lightningtext->text$0.08$0.20$0.121.0M
• Mistral-NeMo-12B (NIM)efficient$0.15$0.15$0.15128K
• Nemotron 3 Supertext->text$0.08$0.45$0.19262K
• Nemotron 3.5 Content Safetytext+image->text$0.20$0.20$0.20131K
• Llama-3.1-Nemotron-70Bfrontier$0.35$0.40$0.36128K
• Nemotron 3 Ultratext->text$0.63$3.13$1.38262K
• Llama-3.1-Nemotron-Ultra-253Bfrontier$1.60$1.60$1.60128K
• Mistral-Large-2 (NIM)frontier$2.00$6.00$3.20128K
• Nemotron-4-340Bfrontier$4.20$4.20$4.204K

OpenAI

98 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• text-embedding-3-smallembed$0.02——8K
• gpt-oss-20btext->text$0.03$0.13$0.06131K
• gpt-oss-120btext->text$0.04$0.17$0.08131K
• GPT-5 Nano (batch)text+image+file->text$0.03$0.20$0.08400K
• gpt-oss-20b (batch)text->text$0.05$0.20$0.10131K
• GPT-4.1 Nano (batch)text+image+file->text$0.05$0.20$0.101.0M
• GPT-6 Luna Pro (batch)text+image+file->text$0.05$0.25$0.111.1M
• GPT-6 Luna (batch)text+image+file->text$0.05$0.25$0.111.1M
• text-embedding-3-largeembed$0.13——8K
• gpt-oss-safeguard-20btext->text$0.07$0.30$0.14131K
• GPT-4o-mini (batch)text+image+file->text$0.07$0.30$0.14128K
• GPT-5 Nanotext+image+file->text$0.05$0.40$0.15400K
• GPT-4.1 nanoefficient$0.10$0.40$0.191.0M
• GPT-6 Luna Protext+image+file->text$0.10$0.50$0.221.1M
• GPT-6 Lunatext+image+file->text$0.10$0.50$0.221.1M
• GPT-5.6 Luna Pro (batch)text+image+file->text$0.10$0.60$0.251.1M
• GPT-5.6 Luna (batch)text+image+file->text$0.10$0.60$0.251.1M
• GPT-5.4 Nano (batch)text+image+file->text$0.10$0.63$0.26400K
• GPT-4o miniefficient$0.15$0.60$0.28128K
• gpt-oss-120b (batch)text->text$0.15$0.60$0.28131K
• GPT-4.1 Mini (batch)text+image+file->text$0.20$0.80$0.381.0M
• GPT-5 Mini (batch)text+image+file->text$0.13$1.00$0.39400K
• GPT-3.5 Turbo (batch)text->text$0.25$0.75$0.4016K
• GPT-5.6 Lunaefficient$0.20$1.20$0.501.1M
• GPT-5.6 Luna Protext+image+file->text$0.20$1.20$0.501.1M
• GPT-5.4 Nanotext+image+file->text$0.20$1.25$0.52400K
• GPT-4.1 miniefficient$0.40$1.60$0.761.0M
• GPT-5.1-Codex-Minitext+image->text$0.25$2.00$0.77400K
• GPT-5 Minitext+image+file->text$0.25$2.00$0.77400K
• GPT-3.5 Turbotext->text$0.50$1.50$0.8016K
• GPT-5.4 Mini (batch)text+image+file->text$0.38$2.25$0.94400K
• o4 Mini (batch)text+image+file->text$0.55$2.20$1.04200K
• o3 Mini (batch)text+file->text$0.55$2.20$1.04200K
• GPT Audio Minitext+audio->text+audio$0.60$2.40$1.14128K
• GPT-3.5 Turbo (older v0613)text->text$1.00$2.00$1.304K
• GPT-3.5 Turbo Instructtext->text$1.50$2.00$1.654K
• GPT-5.4 Minitext+image+file->text$0.75$4.50$1.87400K
• o3 (batch)text+image+file->text$1.00$4.00$1.90200K
• GPT-4.1 (batch)text+image+file->text$1.00$4.00$1.901.0M
• GPT-5.1 (batch)text+image+file->text$0.63$5.00$1.94400K
• GPT-5 (batch)text+image+file->text$0.63$5.00$1.94400K
• o3-minireasoning$1.10$4.40$2.09200K
• o4-minireasoning$1.10$4.40$2.09200K
• o4 Mini Hightext+image+file->text$1.10$4.40$2.09200K
• o3 Mini Hightext+file->text$1.10$4.40$2.09200K
• GPT-6 Sol Pro (batch)text+image+file->text$1.00$5.00$2.201.1M
• GPT-6 Sol (batch)text+image+file->text$1.00$5.00$2.201.1M
• GPT-5.6 Sol Pro (batch)text+image+file->text$1.00$5.00$2.201.1M
• GPT-5.6 Sol (batch)text+image+file->text$1.00$5.00$2.201.1M
• GPT-5 Image Minitext+image+file->text+image$2.50$2.00$2.35400K
• GPT-4o (batch)text+image+file->text$1.25$5.00$2.38128K
• GPT-5.6 Terra Pro (batch)text+image+file->text$1.00$6.00$2.501.1M
• GPT-5.6 Terra (batch)text+image+file->text$1.00$6.00$2.501.1M
• GPT-5.2 (batch)text+image+file->text$0.88$7.00$2.71400K
• GPT-5.4 (batch)text+image+file->text$1.25$7.50$3.131.1M
• GPT-3.5 Turbo 16ktext->text$3.00$4.00$3.3016K
• GPT-4.1multimodal$2.00$8.00$3.801.0M
• GPT-5frontier$1.25$10.00$3.88400K
• GPT-5.1-Codex-Maxtext+image->text$1.25$10.00$3.88400K
• GPT-5.1text+image+file->text$1.25$10.00$3.88400K
• GPT-5.1-Codextext+image->text$1.25$10.00$3.88400K
• GPT-6 Sol Protext+image+file->text$2.00$10.00$4.401.1M
• GPT-6 Soltext+image+file->text$2.00$10.00$4.401.1M
• GPT-5.6 Sol Protext+image+file->text$2.00$10.00$4.401.1M
• GPT-4omultimodal$2.50$10.00$4.75128K
• GPT Audiotext+audio->text+audio$2.50$10.00$4.75128K
• GPT-5.6 Terrafrontier$2.00$12.00$5.001.1M
• GPT-5.6 Terra Protext+image+file->text$2.00$12.00$5.001.1M
• GPT-5.2frontier$1.75$14.00$5.42400K
• GPT-5.2-Codexreasoning$1.75$14.00$5.42400K
• GPT-5.3-Codextext+image+file->text$1.75$14.00$5.42400K
• GPT-5.2 Chattext+image+file->text$1.75$14.00$5.42128K
• GPT-5.5 (batch)text+image+file->text$2.50$15.00$6.251.1M
• GPT-5.4text+image+file->text$2.50$15.00$6.251.1M
• GPT-4 Turbo (batch)text+image->text$5.00$15.00$8.00128K
• GPT-5 Imagetext+image+file->text+image$10.00$10.00$10.00400K
• GPT-5.4 Image 2text+image+file->text+image$8.00$15.00$10.10272K
• GPT-6 Astra (batch)text+image+file->text$5.00$25.00$11.001.1M
• GPT-6 Astra Pro (batch)text+image+file->text$5.00$25.00$11.001.1M
• GPT-5.6 Solfrontier$5.00$30.00$12.501.1M
• GPT-5.5frontier$5.00$30.00$12.501.1M
• GPT Chat Latesttext+image+file->text$5.00$30.00$12.50400K
• GPT-4 Turbomultimodal$10.00$30.00$16.00128K
• o3reasoning$10.00$40.00$19.00200K
• GPT-6 Astratext+image+file->text$10.00$50.00$22.001.1M
• GPT-6 Astra Protext+image+file->text$10.00$50.00$22.001.1M
• GPT-5 Pro (batch)text+image+file->text$7.50$60.00$23.25400K
• o1reasoning$15.00$60.00$28.50200K
• GPT-5.2 Pro (batch)text+image+file->text$10.50$84.00$32.55400K
• GPT-5.5 Pro (batch)text+image+file->text$15.00$90.00$37.501.1M
• GPT-5.4 Pro (batch)text+image+file->text$15.00$90.00$37.501.1M
• o3 Protext+image+file->text$20.00$80.00$38.00200K
• GPT-4text->text$30.00$60.00$39.008K
• GPT-5 Protext+image+file->text$15.00$120.00$46.50400K
• GPT-5.2 Protext+image+file->text$21.00$168.00$65.10400K
• GPT-5.5 Protext+image+file->text$30.00$180.00$75.001.1M
• GPT-5.4 Protext+image+file->text$30.00$180.00$75.001.1M
• o1-protext+image+file->text$150.00$600.00$285.00200K

Perplexity

7 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Sonarefficient$1.00$1.00$1.00127K
• Sonar Reasoningreasoning$1.00$5.00$2.20127K
• Sonar Reasoning Proreasoning$2.00$8.00$3.80127K
• Sonar Deep Researchreasoning$2.00$8.00$3.80127K
• Sonar Hugefrontier$5.00$5.00$5.00127K
• Sonar Profrontier$3.00$15.00$6.60200K
• Sonar Pro Searchtext+image->text$3.00$15.00$6.60200K

Qwen

65 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Qwen2.5-1.5B-Instructefficient$0.03$0.03$0.0332K
• Qwen2.5-3B-Instructefficient$0.05$0.05$0.0532K
• Qwen3.7 Flashtext+image+video->text$0.03$0.13$0.061.0M
• Qwen3 30B A3B Instruct 2507text->text$0.05$0.19$0.09262K
• Qwen2.5-7B-Instructefficient$0.10$0.10$0.10128K
• Qwen2.5-Coder-7Befficient$0.10$0.10$0.10128K
• Qwen3.5-9Btext+image+video->text$0.10$0.15$0.11262K
• Qwen3.5-Flashtext+image+video->text$0.07$0.26$0.121.0M
• Qwen3 Coder 30B A3B Instructtext->text$0.07$0.28$0.13262K
• Qwen3 32Btext->text$0.08$0.28$0.14131K
• Qwen3 14Btext->text$0.12$0.24$0.16131K
• Qwen3 235B A22B Instruct 2507text->text$0.09$0.35$0.17262K
• Qwen3 VL 32B Instructtext+image->text$0.10$0.42$0.20131K
• Qwen3 VL 8B Instructtext+image->text$0.12$0.46$0.22262K
• Qwen3 8Btext->text$0.12$0.46$0.22131K
• Qwen3 30B A3Btext->text$0.12$0.50$0.23131K
• Qwen3.8 Omni Flashtext+image+audio+video->text$0.15$0.47$0.251.0M
• Qwen3.8 Flashtext+image+video->text$0.15$0.47$0.251.0M
• Qwen3 VL 30B A3B Instructtext+image->text$0.15$0.60$0.28262K
• Qwen2-VL-7Bmultimodal$0.30$0.30$0.3032K
• Qwen3 Coder Nexttext->text$0.12$0.80$0.32262K
• Qwen3.6 35B A3Btext+image+video->text$0.10$0.90$0.34262K
• Qwen2.5-14B-Instructefficient$0.35$0.35$0.35128K
• Qwen2.5-Coder-14Befficient$0.35$0.35$0.35128K
• Qwen3 Next 80B A3B Instructtext->text$0.10$1.10$0.40262K
• Qwen Plus 0728text->text$0.26$0.78$0.421.0M
• Qwen-Plustext->text$0.26$0.78$0.421.0M
• Qwen3 Coder Flashtext->text$0.20$0.97$0.431.0M
• Qwen3 Next 80B A3B Thinkingtext->text$0.15$1.20$0.46262K
• Qwen3.6 Flashtext+image+video->text$0.19$1.13$0.471.0M
• Qwen3.5-35B-A3Btext+image+video->text$0.16$1.30$0.50262K
• Qwen3 Coder 480B A35Btext->text$0.30$1.00$0.51262K
• Qwen3.5-27Btext+image+video->text$0.20$1.56$0.60262K
• Qwen2-57B-A14Bfrontier$0.65$0.65$0.6564K
• Qwen2.5-32B-Instructefficient$0.70$0.70$0.70128K
• Qwen2.5-Coder-32Befficient$0.70$0.70$0.70128K
• Qwen3 VL 235B A22B Instructtext+image->text$0.21$1.90$0.72262K
• Qwen3.5 Plus 2026-04-20text+image+video->text$0.30$1.80$0.751.0M
• Qwen3 VL 8B Thinkingtext+image->text$0.18$2.10$0.76131K
• Qwen3.7-Plusmultimodal$0.40$1.60$0.761.0M
• Qwen2.5 Coder 32B Instructtext->text$0.66$1.00$0.7633K
• Qwen3.5-122B-A10Btext+image+video->text$0.26$2.08$0.81262K
• Qwen3.6 27Btext+image+video->text$0.30$2.00$0.81262K
• Qwen3.6 Plustext+image+video->text$0.33$1.95$0.811.0M
• Qwen3 235B A22B Thinking 2507text->text$0.23$2.30$0.85131K
• Qwen2.5 VL 72B Instructtext+image->text$0.80$1.00$0.86128K
• Qwen3 VL 30B A3B Thinkingtext+image->text$0.20$2.40$0.86262K
• Qwen3 30B A3B Thinking 2507text->text$0.20$2.40$0.8682K
• Qwen3 235B A22Btext->text$0.46$1.82$0.86131K
• Qwen2-72B-Instructfrontier$0.90$0.90$0.90128K
• Qwen3.8 27Btext+image+video->text$0.21$2.55$0.911.0M
• QwQ-32Breasoning$0.60$2.40$1.14131K
• Qwen2.5-72B-Instructfrontier$1.20$1.20$1.20128K
• Qwen3 Coder Plustext->text$0.65$3.25$1.431.0M
• Qwen3.5 397B A17Btext+image+video->text$0.55$3.50$1.44262K
• Qwen3 VL 235B A22B Thinkingtext+image->text$0.40$4.00$1.48131K
• Qwen3 Max Thinkingtext->text$0.78$3.90$1.72262K
• Qwen3 Maxtext->text$0.78$3.90$1.72262K
• Qwen2-VL-72Bmultimodal$2.00$2.00$2.0032K
• Qwen3.6 Max Previewtext->text$1.03$6.16$2.57262K
• Qwen2.5-Maxfrontier$1.60$6.40$3.0432K
• Qwen3.8 Max (0902)text+image+video->text$2.00$6.00$3.201.0M
• Qwen3.8 2.4T A95Btext->text$2.00$6.00$3.201.0M
• Qwen3.7-Maxfrontier$2.50$7.50$4.001.0M
• Qwen3.8 Max Primetext+image+video->text$4.00$12.00$6.401.0M

Reka AI

3 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Reka Edgeefficient$0.40$2.00$0.88128K
• Reka Flash 21Befficient$0.80$4.00$1.76128K
• Reka Corefrontier$3.00$15.00$6.60128K

Replicate

5 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Whisper Large v3multimodal$0.0036———
• SDXL (Rep)multimodal$0.04———
• Llama 3 8B (Rep)efficient$0.05$0.25$0.118K
• Mixtral 8x7B (Rep)efficient$0.30$1.00$0.5132K
• Llama 3.1 405B (Rep)frontier$9.50$9.50$9.50128K

Stability AI

3 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• StableLM 2 1.6Befficient$0.10$0.10$0.104K
• StableCode 3Befficient$0.10$0.10$0.1016K
• StableLM 2 12Befficient$0.30$0.30$0.304K

Tencent

11 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Hy-MT2-1.8Btext->text$0.04$0.18$0.088K
• Hy-MT2-30B-A3Btext->text$0.07$0.29$0.148K
• Hy-MT2-7Btext->text$0.07$0.29$0.148K
• Hy3text->text$0.13$0.53$0.25262K
• Hunyuan A13B Instructtext->text$0.14$0.57$0.27131K
• Hy3 previewtext->text$0.18$0.60$0.31262K
• Hunyuan-Standardefficient$0.35$0.70$0.45256K
• Hunyuan-Standard-256Kfrontier$0.70$1.40$0.91256K
• Hy4 previewtext->text$0.83$2.50$1.331.0M
• Hunyuan-Turbofrontier$3.50$7.00$4.55256K
• Hunyuan-Visionmultimodal$5.50$5.50$5.504K

TII / Falcon

4 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Falcon 7B Instructefficient$0.18$0.18$0.182K
• Falcon 11Befficient$0.20$0.20$0.208K
• Falcon 40B Instructefficient$0.90$0.90$0.902K
• Falcon 180Bfrontier$3.50$10.00$5.454K

Together AI

10 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Llama 3.1 8B (Together)efficient$0.10$0.10$0.10128K
• Nous-Hermes-2-Yi-34Bfrontier$0.80$0.80$0.804K
• Llama 3.3 70B (Together)efficient$0.88$0.88$0.88128K
• Falcon 40B (Together)efficient$0.90$0.90$0.902K
• Qwen2.5-72B (Together)frontier$1.20$1.20$1.2032K
• DBRX Instruct (Together)frontier$1.20$1.20$1.2032K
• Mixtral 8x22B (Together)frontier$1.20$1.20$1.2064K
• WizardLM-2 8x22Bfrontier$1.20$1.20$1.2064K
• Llama 3.1 405B (Together)frontier$3.50$3.50$3.50128K
• DeepSeek-R1 (Together)reasoning$3.00$7.00$4.2064K

Upstage

6 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Solar Mini 4text->text$0.05$0.20$0.10524K
• Solar Embeddingembed$0.10——4K
• Solar Pro 4text->text$0.09$0.36$0.17524K
• Solar Miniefficient$0.15$0.60$0.2832K
• Solar Pro 3text->text$0.15$0.60$0.28131K
• Solar Profrontier$1.50$6.00$2.8532K

Voyage AI

7 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• voyage-3-liteembed$0.07——32K
• voyage-3embed$0.12——32K
• voyage-finance-2embed$0.12——32K
• voyage-law-2embed$0.12——32K
• voyage-multilingual-2embed$0.12——32K
• voyage-3-largeembed$0.18——32K
• voyage-code-3embed$0.18——32K

Writer

6 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Palmyra X 004frontier$0.50$2.00$0.95128K
• Palmyra X 32kfrontier$1.00$3.00$1.6032K
• Palmyra Medfrontier$1.00$3.00$1.6032K
• Palmyra Finfrontier$1.00$3.00$1.6032K
• Palmyra Visionmultimodal$1.50$3.50$2.1032K
• Palmyra X5text->text$0.60$6.00$2.221.0M

xAI

15 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Grok 3 miniefficient$0.30$0.50$0.36131K
• SpaceXAI: Grok Build 0.1text+image+file->text$1.00$2.00$1.30256K
• SpaceXAI: Grok 4.3 (batch)text+image+file->text$1.00$2.00$1.301.0M
• Grok 4.3frontier$1.25$2.50$1.631.0M
• SpaceXAI: Grok 4.3text+image+file->text$1.25$2.50$1.631.0M
• SpaceXAI: Grok 4.20 Multi-Agenttext+image+file->text$1.25$2.50$1.632.0M
• SpaceXAI: Grok 4.20text+image+file->text$1.25$2.50$1.632.0M
• SpaceXAI: Grok 4.7text+image+file->text$1.60$4.80$2.56500K
• SpaceXAI: Grok 4.6text+image+file->text$2.00$6.00$3.20500K
• SpaceXAI: Grok 4.5text+image+file->text$2.00$6.00$3.20500K
• Grok 2frontier$2.00$10.00$4.40131K
• Grok 2 Visionmultimodal$2.00$10.00$4.4032K
• Grok 4frontier$3.00$15.00$6.60256K
• Grok 3frontier$3.00$15.00$6.60131K
• Grok 3 Fastmultimodal$5.00$25.00$11.00131K

Zhipu AI

4 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• GLM-4-Airefficient$0.14$0.14$0.14128K
• GLM-4-Longfrontier$0.70$0.70$0.701.0M
• GLM-4-Plusfrontier$7.00$7.00$7.00128K
• GLM-4Vmultimodal$7.00$7.00$7.002K

aion-labs

6 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• AionLabs: Aion 3.5 Minitext->text$0.70$1.40$0.91262K
• AionLabs: Aion-3.0-Minitext->text$0.70$1.40$0.91131K
• AionLabs: Aion-2.0text->text$0.80$1.60$1.04131K
• AionLabs: Aion-RP 1.0 (8B)text->text$0.80$1.60$1.0433K
• AionLabs: Aion 3.5text->text$3.00$6.00$3.90262K
• AionLabs: Aion-3.0text->text$3.00$6.00$3.90131K

anthracite-org

1 model

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Magnum v4 72Btext->text$2.50$5.00$3.2533K

arcee-ai

1 model

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Trinity Large Thinkingtext->text$0.25$0.80$0.41262K

bytedance-seed

6 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Seed 1.6 Flashtext+image+video->text$0.07$0.30$0.14262K
• Seed-2.0-Minitext+image+video->text$0.10$0.40$0.19262K
• Seed-2.0-Litetext+image+video->text$0.25$2.00$0.77262K
• Seed 1.6text+image+video->text$0.25$2.00$0.77262K
• Seed 2.1 Turbotext+image+video->text$0.50$2.50$1.10262K
• Seed-2.0-Codetext+image+video->text$0.50$3.00$1.25262K

cognitivecomputations

1 model

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Venice: Uncensoredtext->text$0.20$0.90$0.41128K

dots-studio

1 model

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Dots3-Note Preview (free)text+image->text$0.00$0.00$0.00512K

gryphe

1 model

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• MythoMax 13Btext->text$0.08$0.11$0.098K

inclusionai

4 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Ling 3.0 Flash Sante (free)text->text$0.00$0.00$0.00262K
• Ling 3.0 Flashtext->text$0.02$0.06$0.03262K
• Ling 3.0 Flash VLtext+image+video->text$0.06$0.18$0.10262K
• Ling 3.0 Flash Fintext->text$0.06$0.18$0.10262K

inference-net

2 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Inference.net: Schematron V2 Turbotext->text$0.03$0.15$0.07128K
• Inference.net: Schematron V2 Smalltext->text$0.05$0.23$0.10128K

kwaipilot

1 model

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• KAT-Coder-Pro V2.5text->text$0.74$2.96$1.41262K

liquid

1 model

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• LiquidAI: LFM2.5-2.6B (free)text->text$0.00$0.00$0.0066K

mancer

1 model

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Weaver (alpha)text->text$0.40$0.75$0.508K

meituan

1 model

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• LongCat 2.0text->text$0.30$1.20$0.571.0M

morph

2 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Morph V3 Fasttext->text$0.80$1.20$0.9282K
• Morph V3 Largetext->text$0.90$1.90$1.20262K

nousresearch

3 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Nous: Hermes 3 70B Instructtext->text$0.70$0.70$0.70131K
• Nous: Hermes 3 405B Instructtext->text$1.00$1.00$1.00131K
• Nous: Hermes 4 405Btext->text$1.00$3.00$1.60131K

perceptron

2 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Perceptron Mk1.5text+image+audio+video->text$0.15$1.50$0.5537K
• Perceptron Mk1text+image+video->text$0.15$1.50$0.5533K

poolside

2 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Laguna XS 2.1text->text$0.06$0.12$0.08262K
• Laguna S 2.1text->text$0.09$0.18$0.121.0M

prism-ml

1 model

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• PrismML: Ternary Bonsai 2 27Btext+image->text$0.07$0.50$0.20262K

rekaai

2 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Reka Edgetext+image+video->text$0.10$0.10$0.1016K
• Reka Flash 3text->text$0.10$0.20$0.1366K

relace

2 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Relace Apply 3text->text$0.85$1.25$0.97256K
• Relace Searchtext->text$1.00$3.00$1.60256K

sakana

4 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Sakana Namazutext+image+file->text$0.95$4.00$1.86262K
• Fugu Maxtext+image+file->text$2.00$6.00$3.201.0M
• Fugu Ultra v2text+image+file->text$5.00$30.00$12.501.0M
• Fugu Ultratext+image->text$5.00$30.00$12.501.0M

sao10k

3 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Llama 3 8B Lunaristext->text$0.04$0.05$0.048K
• Llama 3.3 Euryale 70Btext->text$0.65$0.75$0.68131K
• Llama 3.1 Euryale 70B v2.2text->text$0.85$0.85$0.85131K

stealth

1 model

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Space Bunny Alphatext+image+video->text$0.00$0.00$0.001.0M

stepfun

2 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Step 3.5 Flashtext->text$0.10$0.30$0.16262K
• Step 3.7 Flashtext+image+video->text$0.20$1.15$0.48262K

thedrummer

3 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Cydonia 24B V4.1text->text$0.30$0.50$0.36131K
• UnslopNemo 12Btext->text$0.40$0.40$0.401.0M
• Skyfall 36B V2text->text$0.55$0.80$0.6333K

thinkingmachines

2 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Thinking Machines: Inkling Smalltext+image+audio->text$0.45$1.20$0.68524K
• Thinking Machines: Inklingtext+image+audio->text$1.00$4.05$1.91524K

typesafe

1 model

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Jev Routertext+image+file+audio+video->text———1.0M

unbiased

1 model

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Paretotext+image->text$2.50$7.50$4.00262K

undi95

1 model

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• ReMM SLERP 13Btext->text$0.35$0.65$0.446K

xiaomi

5 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• MiMo-V2.6-Flashtext+image+audio+video->text$0.14$0.28$0.181.0M
• MiMo-V2.5text+image+audio+video->text$0.14$0.28$0.181.1M
• MiMo-V2.6-Protext+image+audio+video->text$0.43$0.87$0.571.1M
• MiMo-V2.5-Protext->text$0.43$0.87$0.571.1M
• MiMo-V2.6-Pro-UltraSpeedtext+image+audio+video->text$4.35$8.70$5.651.0M

z-ai

18 models

Full provider profile

ModelInput $/MOutput $/MBlended $/MContext

• Z.ai: GLM 5.3 Flash (batch)text+image+video->text$0.06$0.20$0.101.0M
• Z.ai: GLM 5.3 Flashtext+image+video->text$0.09$0.30$0.151.3M
• Z.ai: GLM 4.7 Flashtext->text$0.06$0.40$0.16200K
• Z.ai: GLM 4.5 Airtext->text$0.13$0.85$0.35131K
• Z.ai: GLM 4.6Vtext+image+video->text$0.30$0.90$0.48131K
• Z.ai: GLM 5.3 FlashXtext+image+video->text$0.37$1.25$0.631.0M
• Z.ai: GLM 4.7text->text$0.40$1.75$0.80205K
• Z.ai: GLM 4.6text->text$0.43$1.75$0.83205K
• Z.ai: GLM 4.5Vtext+image->text$0.60$1.80$0.9666K
• Z.ai: GLM 5text->text$0.60$1.92$1.00205K
• Z.ai: GLM 4.5text->text$0.60$2.20$1.08131K
• Z.ai: GLM 5.3 (batch)text->text$0.72$2.40$1.221.0M
• Z.ai: GLM 5.1text->text$0.96$3.03$1.58205K
• Z.ai: GLM 5V Turbotext+image+video->text$1.20$4.00$2.04203K
• Z.ai: GLM 5 Turbotext->text$1.20$4.00$2.04203K
• Z.ai: GLM 5.3text->text$1.40$4.40$2.301.3M
• Z.ai: GLM 5.2text->text$1.40$4.40$2.301.0M
• Z.ai: GLM 5.3 Primetext->text$2.80$8.80$4.601.0M

Blended = 70% input + 30% output