llmka.dev
All models and prices
Every model behind one OpenAI-compatible API. Prices are per million tokens for text models and per unit of work for image, audio and embedding models. Open a model for context limits, billing details and FAQ.
Text125
- Abliterated Large V2$4.17 in · $6.95 out / 1M
- Aion 2.0$1.78 in · $3.56 out / 1M
- Aion 3.0$4.05 in · $8.09 out / 1M
- Aion 3.0 Mini$0.9487 in · $1.90 out / 1M
- Aion 3.5$5.06 in · $10.13 out / 1M
- Aion 3.5 Mini$1.18 in · $2.36 out / 1M
- Claude Opus 4.5$3.38 in · $16.88 out / 1M
- Claude Opus 4.6$1.19 in · $4.75 out / 1M
- Claude Opus 4.7$2.41 in · $9.64 out / 1M
- Claude Opus 4.8$2.89 in · $11.56 out / 1M
- Claude Opus 4.8 Fast$25.68 in · $102.72 out / 1M
- Claude Opus 5$19.27 in · $77.09 out / 1M
- Claude Sonnet 4.5$1.68 in · $8.42 out / 1M
- Claude Sonnet 4.6$2.39 in · $9.57 out / 1M
- Claude Sonnet 5$1.80 in · $9.00 out / 1M
- DeepSeek R1$0.5568 in · $2.22 out / 1M
- DeepSeek V3.1$0.006066 in · $0.0231 out / 1M
- DeepSeek V3.2$0.0529 in · $0.0774 out / 1M
- DeepSeek V4 Flash$0.3602 in · $1.44 out / 1M
- DeepSeek V4 Flash 0731$0.0305 in · $0.1216 out / 1M
- DeepSeek V4 Flash 0731 Fast$0.4451 in · $1.78 out / 1M
- DeepSeek V4 Flash E2EE$0.2454 in · $0.5031 out / 1M
- DeepSeek V4 Pro$0.2143 in · $0.4286 out / 1M
- DeepSeek V4 Pro 0813$0.0308 in · $1.23 out / 1M
- DeepSeek V4.1 Flash Uncensored$0.5603 in · $2.24 out / 1M
- Devstral 2 123B$0.009 in · $0.0450 out / 1M
- Gemini 3 Flash Preview$0.0057 in · $0.0338 out / 1M
- Gemini 3.1 Pro Preview$0.2475 in · $1.49 out / 1M
- Gemma 3 27B$0.0018 in · $0.0045 out / 1M
- Gemma 3 27B E2EE$0.1260 in · $0.4500 out / 1M
- Gemma 4 26B A4B Uncensored (E2EE)$0.2163 in · $1.00 out / 1M
- Gemma 4 31B (E2EE)$0.2250 in · $0.6750 out / 1M
- GLM 4.5$0.0132 in · $0.0485 out / 1M
- GLM 4.5 Air$0.0003 in · $0.00195 out / 1M
- GLM 4.6$0.00945 in · $0.0382 out / 1M
- GLM 4.7$0.007678 in · $0.0307 out / 1M
- GLM 4.7 Flash$0.0057 in · $0.0228 out / 1M
- GLM 4.7 Flash Heretic$0.0785 in · $0.4486 out / 1M
- GLM 5$0.1131 in · $0.4522 out / 1M
- GLM 5 (Web)$1.66 in · $6.26 out / 1M
- GLM 5.1$0.1464 in · $0.5853 out / 1M
- GLM 5.1 E2EE$0.9900 in · $3.73 out / 1M
- GLM 5.2$0.0006 in · $0.0453 out / 1M
- GLM 5.2 E2EE$2.36 in · $7.75 out / 1M
- GLM 5.3$0.0177 in · $0.0709 out / 1M
- GLM-5 Turbo$0.0267 in · $0.0891 out / 1M
- GPT 5 Mini$0.1331 in · $1.06 out / 1M
- GPT 5 Nano$0.0131 in · $0.1048 out / 1M
- GPT OSS 120B$0.1461 in · $0.7305 out / 1M
- GPT OSS 20B$0.0282 in · $0.1070 out / 1M
- GPT OSS Safeguard 120B$0.00345 in · $0.0135 out / 1M
- GPT OSS Safeguard 20B$0.00015 in · $0.0006 out / 1M
- GPT-4o$0.2250 in · $0.9000 out / 1M
- GPT-4o Mini$0.0101 in · $0.0405 out / 1M
- GPT-5.2$0.2067 in · $1.65 out / 1M
- GPT-5.2 Codex$0.9845 in · $7.88 out / 1M
- GPT-5.3 Codex$0.6688 in · $2.68 out / 1M
- GPT-5.4$0.7674 in · $3.07 out / 1M
- GPT-5.4 Mini$0.1633 in · $0.9801 out / 1M
- GPT-5.4 Pro$59.27 in · $237.08 out / 1M
- GPT-6 Luna Decisions (OpenAI)$0.1277 in · $0 out / 1M
- gpt-oss-20b$0 in · $0.00015 out / 1M
- Grok 4.20 Beta$0.3629 in · $1.45 out / 1M
- Grok 4.20 Multi-Agent Beta$0.3937 in · $0.7875 out / 1M
- Grok Build 0.1$1.65 in · $3.30 out / 1M
- Hermes 3 Llama 3.1 405b$1.37 in · $5.49 out / 1M
- Inception: Mercury 2.5$0.0855 in · $0.3207 out / 1M
- inclusionAI: Ling 3.1 Flash$0.1002 in · $0.3008 out / 1M
- JEV 1.14 (TypeSafe)$0.0936 in · $0 out / 1M
- Kimi K2$0.8978 in · $3.62 out / 1M
- Kimi K2 Thinking$0.0149 in · $0.0622 out / 1M
- Kimi K2.5$0.0093 in · $0.0462 out / 1M
- LiquidAI: LFM2.5-24B-A2B$0.1114 in · $1.56 out / 1M
- Llama 3.2 3B$0.0563 in · $0.3713 out / 1M
- Llama 3.3 70B$0.0355 in · $0.1046 out / 1M
- Llama 3.3 70B (Web)$1.06 in · $4.22 out / 1M
- Medium$0.2088 in · $0.6264 out / 1M
- Mercury 2$0.4210 in · $1.26 out / 1M
- Mercury 3$0.1350 in · $0.4723 out / 1M
- MiMo-V2.5-Pro$1.07 in · $4.01 out / 1M
- MiniMax M2$0.00525 in · $0.0209 out / 1M
- MiniMax M2.1$0.00075 in · $0.00315 out / 1M
- MiniMax M2.5$0.006069 in · $0.0214 out / 1M
- MiniMax M2.5 (Web)$0.5125 in · $1.79 out / 1M
- MiniMax M2.7$0.3375 in · $1.35 out / 1M
- MiniMax M2.7 Highspeed$1.30 in · $5.18 out / 1M
- MiniMax M3$0.1059 in · $0.4234 out / 1M
- Mistral Small 3.2 24B Instruct$0.0305 in · $0.0810 out / 1M
- Mistral Small 3.2 24B Instruct (Web)$0.1413 in · $0.3770 out / 1M
- NVIDIA Nemotron 3 Nano 30B$0.00165 in · $0.00675 out / 1M
- NVIDIA Nemotron 3 Super 120B$0.00165 in · $0.009 out / 1M
- NVIDIA Nemotron 3 Ultra 550B$0.1691 in · $0.8451 out / 1M
- NVIDIA Nemotron 3.5 Lightning 30B$0.1310 in · $0.3743 out / 1M
- NVIDIA Nemotron Nano 9B v2$0.00135 in · $0.00525 out / 1M
- OpenAI GPT OSS 120B$0.00015 in · $0.0006 out / 1M
- Qwen 2.5 7B$0.0485 in · $0.1258 out / 1M
- Qwen 3 235B A22B Instruct 2507$0.0051 in · $0.0205 out / 1M
- Qwen 3 235B A22B Instruct 2507 (Web)$0.2262 in · $1.13 out / 1M
- Qwen 3 235B A22B Thinking 2507$0.2137 in · $0.2137 out / 1M
- Qwen 3 Coder 480b$0.007598 in · $0.0253 out / 1M
- Qwen 3 Coder 480B Turbo$0.0703 in · $0.2811 out / 1M
- Qwen 3 Next 80b$0.00195 in · $0.0237 out / 1M
- Qwen 3.5 35B A3B$0.1830 in · $1.22 out / 1M
- Qwen 3.5 9B$0.1002 in · $0.3004 out / 1M
- Qwen 3.6 35B A3B (E2EE)$0.1869 in · $1.21 out / 1M
- Qwen 3.6 35B A3B Uncensored (E2EE)$0.4500 in · $1.35 out / 1M
- Qwen 3.7 Max$2.25 in · $6.75 out / 1M
- Qwen 3.7 Plus$0.5608 in · $2.24 out / 1M
- Qwen 3.8 Max$0.4268 in · $1.71 out / 1M
- Qwen3 30B A3B$0.1890 in · $0.7875 out / 1M
- Qwen3 32B$0.0018 in · $0.0063 out / 1M
- Qwen3 Coder 30B A3B Instruct$0.0015 in · $0.0063 out / 1M
- Qwen3 Coder Next$0.004791 in · $0.0319 out / 1M
- Qwen3 VL 235B$0.2358 in · $2.13 out / 1M
- Qwen3 VL 30B A3B$0.3150 in · $1.42 out / 1M
- Qwen3.5 Flash$0.2160 in · $0.8640 out / 1M
- Qwen3.5 Plus$0.5616 in · $3.37 out / 1M
- Qwen3.8 2.4T A95B$0.0712 in · $0.2848 out / 1M
- Reflection: Beam 1.0 501B A23B$0.6683 in · $2.23 out / 1M
- Role Play Uncensored$0.5608 in · $2.24 out / 1M
- Tencent HY3$0.0742 in · $0.2970 out / 1M
- Tencent: Hy4 preview$1.69 in · $5.06 out / 1M
- Thinking Machines: Inkling$0.0211 in · $0.0901 out / 1M
- Uncensored 1.1$0.1512 in · $0.6805 out / 1M
- Z.ai: GLM 5.3 Prime$0.2058 in · $0.8232 out / 1M
Multimodal118
- Abliterated Large Flash$1.28 in · $5.11 out / 1M
- ByteDance Seed: Seed-2.0-Code$1.11 in · $6.68 out / 1M
- Claude Fable 5$20.61 in · $82.44 out / 1M
- Claude Fable 5.1$16.13 in · $64.50 out / 1M
- Claude Haiku 4.5$2.43 in · $9.72 out / 1M
- Claude Haiku 5.5$0.4155 in · $1.66 out / 1M
- Claude Opus 5 (Fast)$26.22 in · $104.88 out / 1M
- Claude Opus 5.5$3.26 in · $16.28 out / 1M
- Claude Sonnet 5.5$1.37 in · $6.84 out / 1M
- Cohere: Command A+$0.6683 in · $3.34 out / 1M
- DeepSeek V4.1 Flash$0.0027 in · $0.0145 out / 1M
- DeepSeek V4.1 Flash 1017$0.1591 in · $0.6364 out / 1M
- DeepSeek: DeepSeek V4 Flash Vision Exp$0.9801 in · $2.94 out / 1M
- Elorian: Glimpse$1.34 in · $6.68 out / 1M
- Fireworks: Ember-1$6.68 in · $33.41 out / 1M
- Gemini 2.5 Flash$0.00345 in · $0.0282 out / 1M
- Gemini 2.5 Pro$0.6750 in · $5.40 out / 1M
- Gemini 3.1 Flash Lite$0.0165 in · $0.0660 out / 1M
- Gemini 3.1 Pro$4.32 in · $25.92 out / 1M
- Gemini 3.5 Flash$0.0662 in · $0.2645 out / 1M
- Gemini 3.5 Flash Lite$0.2700 in · $2.25 out / 1M
- Gemini 3.6 Flash$0.5062 in · $2.53 out / 1M
- Gemini 3.7 Flash$0.0987 in · $0.3947 out / 1M
- Gemini 3.8 Flash$0.0543 in · $0.2169 out / 1M
- Gemma 3 12B IT$0.006977 in · $0.0209 out / 1M
- Gemma 3 4B IT$0.003671 in · $0.007341 out / 1M
- Gemma 4 26B A4B IT$0.00123 in · $0.004098 out / 1M
- Gemma 4 31B$0.0021 in · $0.00615 out / 1M
- Gemma 4 31B IT$0.0021 in · $0.00615 out / 1M
- Gemma 4 E2B$0.0009 in · $0.0018 out / 1M
- Gemma 4 Uncensored$0.3471 in · $1.39 out / 1M
- GLM 5.3 Flash$0.00825 in · $0.0333 out / 1M
- GLM 5V Turbo$1.53 in · $5.11 out / 1M
- Google: Gemini 4 Argon$0.3604 in · $1.80 out / 1M
- GPT 5.4 Nano$0.0877 in · $0.5484 out / 1M
- GPT-5 Image$6.75 in · $6.75 out / 1M
- GPT-5 Image Mini$3.09 in · $2.48 out / 1M
- GPT-5.4 Image 2$3.60 in · $6.75 out / 1M
- GPT-5.5$3.33 in · $13.32 out / 1M
- GPT-5.5 Pro$15.96 in · $95.74 out / 1M
- GPT-5.6 Luna$0.1938 in · $0.7749 out / 1M
- GPT-5.6 Luna Pro$0.1635 in · $0.6540 out / 1M
- GPT-5.6 Sol$2.43 in · $9.72 out / 1M
- GPT-5.6 Sol Pro$6.29 in · $25.15 out / 1M
- GPT-5.6 Terra$0.0531 in · $0.3189 out / 1M
- GPT-5.6 Terra Pro$2.69 in · $16.17 out / 1M
- GPT-6 Astra$6.73 in · $33.67 out / 1M
- GPT-6 Luna$0.00675 in · $0.0336 out / 1M
- GPT-6 Luna Pro$0.2228 in · $1.11 out / 1M
- GPT-6 Sol$1.09 in · $5.43 out / 1M
- GPT-6 Sol Pro$0.6453 in · $2.58 out / 1M
- GPT-6.1 Sol$0.7980 in · $3.19 out / 1M
- Grok 4.3$0.0279 in · $0.0556 out / 1M
- Grok 4.5$1.46 in · $5.83 out / 1M
- Grok 4.6$1.20 in · $4.80 out / 1M
- Grok 4.7$2.43 in · $9.71 out / 1M
- Kimi K2.6$0.1464 in · $0.6165 out / 1M
- Kimi K2.6 (Web)$1.28 in · $7.02 out / 1M
- Kimi K2.7 Code$0.0504 in · $0.2013 out / 1M
- Kimi K2.7 Code (Web)$1.03 in · $5.14 out / 1M
- Kimi K3$0.2637 in · $1.05 out / 1M
- Kimi K3 Fast$6.07 in · $30.37 out / 1M
- Kimi K3.1 Pro$4.19 in · $16.75 out / 1M
- Magistral Small 2509$0.0112 in · $0.0338 out / 1M
- Meta: Muse Glimmer 30B$0.7087 in · $2.83 out / 1M
- Meta: Muse Spark 1.1$2.65 in · $9.00 out / 1M
- Meta: Muse Spark 1.2$2.65 in · $9.00 out / 1M
- Meta: Muse Spark 1.2 Contributor$0.0225 in · $0.0450 out / 1M
- Meta: Muse Spark 1.3$2.78 in · $9.47 out / 1M
- Meta: Muse Spark 1.3 Contributor$0.0081 in · $0.0321 out / 1M
- Meta: Muse Spark Open$2.11 in · $7.17 out / 1M
- Meta: Muse Wonder$6.75 in · $33.75 out / 1M
- MiMo-V2.5$0.5399 in · $2.70 out / 1M
- MiMo-V2.6-Flash$0.3119 in · $0.6237 out / 1M
- MiMo-V2.6-Pro$0.9689 in · $3.68 out / 1M
- MiMo-V2.6-Pro-UltraSpeed$9.69 in · $19.38 out / 1M
- MiniMax M3 Preview$0.4050 in · $1.62 out / 1M
- MiniMax M3.1 Flash$0.0232 in · $0.0930 out / 1M
- Ministral 14B 3.0$0.0045 in · $0.0045 out / 1M
- Ministral 3 8B$0.00345 in · $0.00345 out / 1M
- Ministral 3B$0.00225 in · $0.00225 out / 1M
- Mistral Large 3$0.0112 in · $0.0338 out / 1M
- Mistral Small 4$0.1055 in · $0.4219 out / 1M
- Mistral: Mistral Large 4$0.1575 in · $0.4725 out / 1M
- Moondream: Moondream 3 Preview$0.6683 in · $5.57 out / 1M
- Moondream: Moondream 3.1$0.6683 in · $5.57 out / 1M
- Nano Banana (Gemini 2.5 Flash Image)$0.00345 in · $0.0282 out / 1M
- NVIDIA Nemotron Nano 12B v2 VL BF16$0.0045 in · $0.0135 out / 1M
- NVIDIA: Nemotron 3.5 Super VL$0.0675 in · $0.2250 out / 1M
- OpenAI: GPT-6.1 Sol Pro$4.28 in · $21.38 out / 1M
- OpenAI: GPT-6.1 Terra$1.07 in · $4.28 out / 1M
- OpenAI: GPT-6.1 Terra Pro$2.23 in · $11.14 out / 1M
- OrcaCyber: DeepSeek V4.1 Flash Abliterated / Uncensored$1.71 in · $3.42 out / 1M
- OrcaCyber: GLM 5.3 Flash Abliterated / Uncensored$1.71 in · $3.42 out / 1M
- OrcaCyber: MiMo V2.6 Flash Abliterated / Uncensored$1.71 in · $3.42 out / 1M
- OrcaCyber: MiniMax M3.1 Flash Abliterated / Uncensored$1.71 in · $3.42 out / 1M
- OrcaCyber: Qwen3.8 Flash Next Abliterated / Uncensored$1.71 in · $3.42 out / 1M
- Palmyra Vision 7B$0.00345 in · $0.0135 out / 1M
- Pareto 26.9$5.57 in · $16.71 out / 1M
- Particle AI: Particle-1$0.1114 in · $1.11 out / 1M
- Qwen 3.5 397B$0.6558 in · $4.72 out / 1M
- Qwen 3.6 27B$0.3666 in · $3.04 out / 1M
- Qwen 3.6 35B A3B$0.1575 in · $1.13 out / 1M
- Qwen 3.6 Plus Uncensored$2.27 in · $9.08 out / 1M
- Qwen 3.8 27B$0.000465 in · $0.005812 out / 1M
- Qwen: Qwen3.7 Flash$0.0135 in · $0.0585 out / 1M
- Qwen: Qwen3.8 Max (0902)$0.9000 in · $2.70 out / 1M
- Qwen: Qwen3.8 Max Prime$1.80 in · $5.40 out / 1M
- Qwen: Qwen3.8 Omni Flash$0.0675 in · $0.2115 out / 1M
- Qwen3 VL 235B A22B$0.004697 in · $0.0425 out / 1M
- Qwen3.8 Flash$0.00375 in · $0.0149 out / 1M
- Sakana: Fugu Max$4.46 in · $13.37 out / 1M
- Sakana: Fugu Ultra v2$11.14 in · $66.83 out / 1M
- Seed 2.1 Turbo$0.6513 in · $3.26 out / 1M
- Tencent: Hy4$0.9288 in · $2.79 out / 1M
- Uncensored 1.2$0.2248 in · $1.01 out / 1M
- Z.ai: GLM 5.3 FlashX$1.03 in · $4.11 out / 1M
- Z.ai: GLM 5.3 FlashX Legal$0.5827 in · $1.97 out / 1M
Images46
- Anime WAI$0 in · $0 out / 1M
- Chroma$0 in · $0 out / 1M
- Firered Image (image-to-image)$0 in · $0 out / 1M
- Flux 1.1$0 in · $0 out / 1M
- Flux 1.1 Pro$0 in · $0 out / 1M
- Flux 2 Max$0 in · $0 out / 1M
- Flux 2 Max - Edit$0 in · $0 out / 1M
- Flux 2 Pro$0 in · $0 out / 1M
- FLUX.2 Flex$0 in · $0 out / 1M
- FLUX.2 Klein 4B$0 in · $0 out / 1M
- GPT Image 1.5$0 in · $0 out / 1M
- GPT Image 1.5 - Edit$0 in · $0 out / 1M
- GPT Image 2$0 in · $0 out / 1M
- GPT Image 2 - Edit$0 in · $0 out / 1M
- Grok Imagine$0 in · $0 out / 1M
- Grok Imagine 2.0$0 in · $0 out / 1M
- Grok Imagine High Quality$0 in · $0 out / 1M
- Hunyuan Image 3.0$0 in · $0 out / 1M
- Luma Uni 1 (image-to-image)$0 in · $0 out / 1M
- Luma Uni 1 Max (image-to-image)$0 in · $0 out / 1M
- Lustify SDXL$0 in · $0 out / 1M
- Lustify v7$0 in · $0 out / 1M
- Lustify v8$0 in · $0 out / 1M
- Nano Banana 2$0 in · $0 out / 1M
- Nano Banana 2 (image-to-image)$0 in · $0 out / 1M
- Nano Banana 2 Lite (image-to-image)$0 in · $0 out / 1M
- Nano Banana Pro$0 in · $0 out / 1M
- Nano Banana Pro (image-to-image)$0 in · $0 out / 1M
- Qwen Edit Uncensored (image-to-image)$0 in · $0 out / 1M
- Qwen Image$0 in · $0 out / 1M
- Qwen Image 2$0 in · $0 out / 1M
- Qwen Image 2 Pro$0 in · $0 out / 1M
- Qwen Image 2 Pro (image-to-image)$0 in · $0 out / 1M
- Recraft V4$0 in · $0 out / 1M
- Recraft V4 Pro$0 in · $0 out / 1M
- SD35$0 in · $0 out / 1M
- Seedream 4.5$0 in · $0 out / 1M
- Seedream v4 - Edit$0 in · $0 out / 1M
- Seedream V4.5$0 in · $0 out / 1M
- Seedream V5 Lite$0 in · $0 out / 1M
- Seedream V5 Lite (image-to-image)$0 in · $0 out / 1M
- Stable Diffusion XL$0 in · $0 out / 1M
- Wan 2.7$0 in · $0 out / 1M
- Wan 2.7 Pro$0 in · $0 out / 1M
- Wan 2.7 Pro (image-to-image)$0 in · $0 out / 1M
- Z-Image Turbo$0 in · $0 out / 1M
Audio17
- Chatterbox HD TTS$0 in · $0 out / 1M
- ElevenLabs Scribe v2 (STT)$0 in · $0 out / 1M
- ElevenLabs Turbo v2.5 TTS$0 in · $0 out / 1M
- fal.ai Wizper (STT)$0 in · $0 out / 1M
- Gemini 3.1 Flash TTS$0 in · $0 out / 1M
- Inworld 1.5 Max TTS$0 in · $0 out / 1M
- Kokoro Text to Speech$0 in · $0 out / 1M
- MiniMax Speech 02 HD TTS$0 in · $0 out / 1M
- Orpheus TTS$0 in · $0 out / 1M
- Parakeet ASR$0 in · $0 out / 1M
- Qwen3 0.6B TTS$0 in · $0 out / 1M
- Qwen3 1.7B TTS$0 in · $0 out / 1M
- TTS 1 (legacy alias)$0 in · $0 out / 1M
- Whisper 1$0 in · $0 out / 1M
- Whisper Large V3$0 in · $0 out / 1M
- xAI Speech to Text v1$0 in · $0 out / 1M
- xAI v1 TTS$0 in · $0 out / 1M