LLM API pricing — 253 models compared
Live per-model API pricing across every major model — GPT, Claude, Gemini, DeepSeek, GLM, Qwen, Llama, Mistral, Kimi — in one table, quoted per 1M tokens (input / output), cheapest first. Call any of them with one OpenAI-compatible key through UberLLM; prices include UberLLM’s 10% fee, so the price you see is the price you pay.
| Model | Input / 1M | Output / 1M | Context |
|---|---|---|---|
| JEV 1.13 (TypeSafe) typesafe/jev-1.13 | $0.0005 | $0.0000 | 0K |
| Qwen: Qwen3.8 Omni Flash qwen/qwen3.8-omni-flash | $0.0002 | $0.0005 | 1000K |
| DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash | $0.0002 | $0.0006 | 1049K |
| Tencent HY3 tencent/hy3 | $0.0002 | $0.0007 | 262K |
| Gemma 3 4B IT google/gemma-3-4b-it | $0.0005 | $0.0007 | 128K |
| GPT-OSS 20B openai/gpt-oss-20b | $0.0002 | $0.0009 | 131K |
| GLM 5.3 Flash z-ai/glm-5.3-flash | $0.0004 | $0.0012 | 1049K |
| Ministral 3B mistralai/ministral-3-3b-instruct | $0.0011 | $0.0011 | 128K |
| MiniMax M3 minimax/minimax-m3 | $0.0004 | $0.0015 | 200K |
| MiniMax M2.7 minimax/minimax-m2.7 | $0.0004 | $0.0015 | 198K |
| DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 | $0.0004 | $0.0015 | 1049K |
| MiniMax M2.5 minimax/minimax-m2.5 | $0.0004 | $0.0015 | 198K |
| MiniMax M2.1 minimax/minimax-m2.1 | $0.0004 | $0.0016 | 198K |
| Gemma 4 26B A4B IT google/gemma-4-26b-a4b-it | $0.0005 | $0.0016 | 262K |
| Gemma 3 12B IT google/gemma-3-12b-it | $0.0005 | $0.0016 | 128K |
| DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731 | $0.0010 | $0.0020 | 1049K |
| GLM 4.7 Flash z-ai/glm-4.7-flash | $0.0003 | $0.0022 | 198K |
| Gemma 3 27B google/gemma-3-27b-it | $0.0009 | $0.0022 | 40K |
| DeepSeek V4 Pro deepseek/deepseek-v4-pro | $0.0011 | $0.0022 | 1049K |
| Meta: Muse Spark 1.3 Contributor meta-llama/muse-spark-1.3-contributor | $0.0011 | $0.0022 | 1049K |
| GLM-5.2 z-ai/glm-5.2 | $0.0006 | $0.0024 | 1049K |
| Ministral 3 8B mistralai/ministral-3-8b-instruct | $0.0020 | $0.0020 | 128K |
| Ministral 14B 3.0 mistralai/ministral-3-14b-instruct | $0.0022 | $0.0022 | 128K |
| GPT-OSS 120B openai/gpt-oss-120b | $0.0007 | $0.0029 | 131K |
| GPT OSS Safeguard 20B openai/gpt-oss-safeguard-20b | $0.0008 | $0.0030 | 128K |
| Qwen3 Coder 30B A3B Instruct qwen/qwen3-coder-30b-a3b-instruct | $0.0008 | $0.0030 | 256K |
| Qwen3 32B qwen/qwen3-32b | $0.0009 | $0.0030 | 32K |
| Gemma 4 31B IT google/gemma-4-31b-it | $0.0010 | $0.0030 | 262K |
| Gemma 4 31B google/gemma-4-31b | $0.0010 | $0.0030 | 256K |
| NVIDIA Nemotron 3 Nano 30B nvidia/nemotron-3-nano-30b-a3b | $0.0008 | $0.0033 | 128K |
| Qwen 3 235B A22B Instruct 2507 qwen/qwen3-235b-a22b-2507 | $0.0006 | $0.0038 | 128K |
| Gemma 4 E2B google/gemma-4-e2b | $0.0022 | $0.0044 | 128K |
| Meta: Muse Spark 1.2 Contributor meta-llama/muse-spark-1.2-contributor | $0.0022 | $0.0044 | 1049K |
| NVIDIA Nemotron Nano 9B v2 nvidia/nemotron-nano-9b-v2 | $0.0012 | $0.0048 | 128K |
| GLM 4.5 Air z-ai/glm-4.5-air | $0.0008 | $0.0049 | 128K |
| NVIDIA Nemotron 3 Super 120B nvidia/nemotron-3-super-120b | $0.0009 | $0.0050 | 256K |
| DeepSeek V3.2 deepseek/deepseek-v3.2 | $0.0029 | $0.0043 | 164K |
| Qwen3.8 Flash qwen/qwen3.8-flash | $0.0016 | $0.0051 | 1000K |
| Kimi K2.7 Code moonshotai/kimi-k2.7-code | $0.0011 | $0.0054 | 262K |
| Kimi K2.6 moonshotai/kimi-k2.6 | $0.0012 | $0.0065 | 262K |
| GPT-6 Luna Decisions (OpenAI) openai/gpt-6-luna-decisions | $0.0220 | $0.0000 | 0K |
| DeepSeek V4 Flash deepseek/deepseek-v4-flash | $0.0032 | $0.0064 | 1049K |
| GLM 5.3 z-ai/glm-5.3 | $0.0004 | $0.0077 | 1000K |
| Qwen: Qwen3.8 Max (0902) qwen/qwen3.8-max-0902 | $0.0024 | $0.0071 | 1000K |
| NVIDIA Nemotron Nano 12B v2 VL BF16 nvidia/nemotron-nano-12b-v2 | $0.0024 | $0.0073 | 128K |
| Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b | $0.0025 | $0.0074 | 1000K |
| Qwen3 Coder Next qwen/qwen3-coder-next | $0.0013 | $0.0087 | 256K |
| JEV 1.14 (TypeSafe) typesafe/jev-1.14 | $0.0300 | $0.0000 | 0K |
| Qwen3 Next 80B A3B qwen/qwen3-next-80b-a3b-instruct | $0.0009 | $0.0104 | 262K |
| MiniMax M2 minimax/minimax-m2 | $0.0026 | $0.0102 | 1000K |
| Qwen 3.8 27B qwen/qwen-3-8-27b | $0.0009 | $0.0108 | 262K |
| DeepSeek V3.1 deepseek/deepseek-v3.1 | $0.0027 | $0.0103 | 128K |
| Qwen 3 Coder 480b qwen/qwen3-coder | $0.0033 | $0.0109 | 256K |
| GPT OSS Safeguard 120B openai/gpt-oss-safeguard-120b | $0.0028 | $0.0112 | 128K |
| GLM-4.7 z-ai/glm-4.7 | $0.0031 | $0.0112 | 205K |
| GPT-5.6 Luna openai/gpt-5.6-luna | $0.0022 | $0.0133 | 1050K |
| Mistral Small 3.2 24B Instruct mistralai/mistral-small-3.2-24b-instruct | $0.0051 | $0.0137 | 256K |
| Palmyra Vision 7B writer/palmyra-vision-7b | $0.0037 | $0.0148 | 4K |
| Gemini 3.1 Flash Lite google/gemini-3.1-flash-lite | $0.0027 | $0.0163 | 1049K |
| GPT-6 Luna openai/gpt-6-luna | $0.0032 | $0.0162 | 1050K |
| GLM-4.6 z-ai/glm-4.6 | $0.0047 | $0.0191 | 205K |
| GPT-4o Mini openai/gpt-4o-mini | $0.0049 | $0.0197 | 128K |
| GLM-5 z-ai/glm-5 | $0.0060 | $0.0194 | 205K |
| Qwen3 VL 235B A22B qwen/qwen3-vl-235b-a22b-instruct | $0.0023 | $0.0207 | 256K |
| Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 | $0.0041 | $0.0206 | 1000K |
| Kimi K2.5 moonshotai/kimi-k2.5 | $0.0046 | $0.0228 | 256K |
| GLM 4.5 z-ai/glm-4.5 | $0.0065 | $0.0237 | 128K |
| Magistral Small 2509 mistralai/magistral-small-2509 | $0.0080 | $0.0240 | 128K |
| Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct | $0.0164 | $0.0220 | 131K |
| Gemini 2.5 Flash google/gemini-2.5-flash | $0.0033 | $0.0272 | 1049K |
| Nano Banana (Gemini 2.5 Flash Image) google/gemini-2.5-flash-image | $0.0033 | $0.0275 | 8K |
| NVIDIA Nemotron 3 Ultra 550B nvidia/nemotron-3-ultra-550b-a55b | $0.0055 | $0.0275 | 1000K |
| Kimi K2 Thinking moonshotai/kimi-k2-thinking | $0.0065 | $0.0272 | 262K |
| Grok 4.3 x-ai/grok-4.3 | $0.0136 | $0.0272 | 1000K |
| Gemini 3 Flash Preview google/gemini-3-flash-preview | $0.0055 | $0.0330 | 256K |
| Qwen: Qwen3.7 Flash qwen/qwen3.7-flash | $0.0083 | $0.0357 | 1000K |
| GLM 5.1 z-ai/glm-5.1 | $0.0118 | $0.0372 | 200K |
| Gemini 3.8 Flash google/gemini-3.8-flash | $0.0079 | $0.0393 | 1049K |
| Qwen 2.5 7B qwen/e2ee-qwen-2-5-7b-p | $0.0157 | $0.0408 | 32K |
| Thinking Machines: Inkling thinking-machines/inkling | $0.0103 | $0.0441 | 1049K |
| GLM-5 Turbo z-ai/glm-5-turbo | $0.0131 | $0.0436 | 200K |
| Devstral 2 123B mistralai/devstral-2-123b | $0.0091 | $0.0453 | 256K |
| Meta: Muse Spark 1.3 meta-llama/muse-spark-1.3 | $0.0138 | $0.0467 | 1049K |
| GPT 5 Nano openai/gpt-5-nano | $0.0066 | $0.0528 | 400K |
| Grok 4.7 x-ai/grok-4.7 | $0.0169 | $0.0508 | 500K |
| GPT OSS 20B openai/e2ee-gpt-oss-20b-p | $0.0138 | $0.0522 | 128K |
| Grok 4.5 x-ai/grok-4.5 | $0.0172 | $0.0517 | 500K |
| Kimi K3 moonshotai/kimi-k3 | $0.0013 | $0.0575 | 1049K |
| Claude Haiku 5.5 anthropic/claude-haiku-5.5 | $0.0110 | $0.0550 | 100K |
| MiMo-V2.6-Flash xiaomi/mimo-v2.6-flash | $0.0252 | $0.0504 | 1049K |
| Qwen 3 235B A22B Thinking 2507 qwen/qwen3-235b-a22b-thinking-2507 | $0.0550 | $0.0550 | 128K |
| Gemini 3.7 Flash google/gemini-3.7-flash | $0.0165 | $0.0825 | 1049K |
| Mistral Large 3 mistralai/mistral-large-3 | $0.0272 | $0.0817 | 256K |
| Qwen 3.5 9B qwen/qwen3.5-9b | $0.0275 | $0.0825 | 256K |
| Inception: Mercury 2.5 inception/mercury-2.5 | $0.0242 | $0.0907 | 260K |
| Meta: Muse Spark 1.1 meta-llama/muse-spark-1.1 | $0.0275 | $0.0935 | 1049K |
| Meta: Muse Spark 1.2 meta-llama/muse-spark-1.2 | $0.0275 | $0.0935 | 1049K |
| Gemini 3.5 Flash google/gemini-3.5-flash | $0.0165 | $0.0990 | 1049K |
| Qwen 3.6 35B A3B qwen/qwen3-6-35b-a3b | $0.0103 | $0.1034 | 262K |
| DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813 | $0.0358 | $0.1073 | 1049K |
| MoonshotAI: Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | $0.0227 | $0.1136 | 1049K |
| Z.ai: GLM 5.3 Prime z-ai/glm-5.3-prime | $0.0375 | $0.1179 | 1000K |
| GPT 5 Mini openai/gpt-5-mini | $0.0165 | $0.1319 | 400K |
| GPT-5.3 Codex openai/gpt-5.3-codex | $0.0186 | $0.1485 | 400K |
| Llama 3.2 3B meta-llama/llama-3.2-3b-instruct | $0.0224 | $0.1474 | 128K |
| Claude Opus 4.6 anthropic/claude-opus-4.6 | $0.0296 | $0.1479 | 1000K |
| Qwen 3.5 397B qwen/qwen3.5-397b-a17b | $0.0212 | $0.1525 | 128K |
| GLM 4.7 Flash Heretic z-ai/glm-4.7-flash-heretic | $0.0285 | $0.1631 | 200K |
| MiMo-V2.5 xiaomi/mimo-v2-5 | $0.0757 | $0.1514 | 1000K |
| NVIDIA Nemotron 3.5 Lightning 30B nvidia/nemotron-3-5-lightning-30b-a3b | $0.0704 | $0.1760 | 1000K |
| Mistral Small 3.2 24B Instruct (Morpheus Web) mistralai/mistral-small-3.2-24b-instruct:web | $0.0691 | $0.1842 | 256K |
| MiMo-V2.6-Pro xiaomi/mimo-v2.6-pro | $0.0944 | $0.1887 | 1049K |
| Mistral Small 4 mistralai/mistral-small-4 | $0.0516 | $0.2062 | 256K |
| OpenAI GPT OSS 120B (Morpheus Web) openai/gpt-oss-120b:web | $0.0516 | $0.2211 | 128K |
| DeepSeek V4 Flash E2EE deepseek/e2ee-deepseek-v4-flash | $0.1001 | $0.2051 | 1000K |
| Gemma 3 27B E2EE google/e2ee-gemma-3-27b | $0.0616 | $0.2200 | 40K |
| GPT-6 Sol openai/gpt-6-sol | $0.0452 | $0.2260 | 1050K |
| GPT OSS 120B openai/e2ee-gpt-oss-120b-p | $0.0470 | $0.2350 | 128K |
| Qwen 3.6 27B qwen/qwen3.6-27b | $0.0328 | $0.2624 | 256K |
| GPT-6.1 Sol openai/gpt-6.1-sol | $0.0513 | $0.2567 | 1050K |
| inclusionAI: Ling 3.1 Flash inclusionai/ling-3.1-flash | $0.0825 | $0.2475 | 262K |
| Mercury 3 inception/mercury-3 | $0.0748 | $0.2618 | 1000K |
| GPT-5.6 Terra openai/gpt-5.6-terra | $0.0453 | $0.2719 | 1050K |
| GPT 5.4 Nano openai/gpt-5.4-nano | $0.0440 | $0.2750 | 400K |
| Claude Opus 4.7 anthropic/claude-opus-4.7 | $0.0545 | $0.2727 | 1000K |
| Claude Haiku 5.5 (batch) anthropic/claude-haiku-5.5:batch | $0.0550 | $0.2750 | 100K |
| DeepSeek V4 Flash (Morpheus Web) deepseek/deepseek-v4-flash:web | $0.1253 | $0.2580 | 1000K |
| Gemma 4 Uncensored google/gemma-4-uncensored | $0.0885 | $0.2722 | 256K |
| Gemma 4 26B A4B Uncensored (E2EE) google/e2ee-gemma-4-26b-a4b-uncensored-p | $0.0658 | $0.3045 | 262K |
| Venice Uncensored 1.2 venice/uncensored-1.2 | $0.0679 | $0.3055 | 128K |
| MiMo-V2.5-Pro xiaomi/mimo-v2.5-pro | $0.1436 | $0.2871 | 1050K |
| Mistral Large mistralai/mistral-large | $0.1021 | $0.3062 | 262K |
| Claude Haiku 4.5 anthropic/claude-haiku-4.5 | $0.0653 | $0.3267 | 200K |
| GPT-4o openai/gpt-4o | $0.0819 | $0.3278 | 128K |
| GPT-5.6 Sol openai/gpt-5.6-sol | $0.0667 | $0.3334 | 1050K |
| Mercury 2 inception/mercury-2 | $0.1091 | $0.3274 | 128K |
| Qwen 3.5 35B A3B qwen/qwen3.5-35b-a3b | $0.0520 | $0.3466 | 256K |
| Gemma 4 31B (E2EE) google/e2ee-gemma-4-31b | $0.1100 | $0.3300 | 262K |
| Qwen3.5 Flash qwen/qwen3.5-flash | $0.0935 | $0.3740 | 1000K |
| Gemma 4 26B A4B IT (Morpheus Web) google/gemma-4-26b-a4b-it:web | $0.1198 | $0.3685 | 262K |
| Gemma 4 31B IT (Morpheus Web) google/gemma-4-31b-it:web | $0.1290 | $0.3685 | 262K |
| GPT-5.4 openai/gpt-5.4 | $0.0657 | $0.3944 | 1000K |
| Grok 4.20 Multi-Agent Beta x-ai/grok-4.20-multi-agent-beta | $0.1925 | $0.3850 | 2000K |
| Grok 4.20 Beta x-ai/grok-4.20-beta | $0.1925 | $0.3850 | 2000K |
| DeepSeek V4 Flash 0731 Fast deepseek/deepseek-v4-flash-0731-fast | $0.1925 | $0.3850 | 1000K |
| Qwen3 30B A3B qwen/qwen3-30b-a3b | $0.1010 | $0.4208 | 256K |
| Qwen 3.6 35B A3B (E2EE) qwen/e2ee-qwen3-6-35b-a3b | $0.0680 | $0.4412 | 128K |
| Meta: Muse Wonder meta-llama/muse-wonder | $0.0880 | $0.4400 | 1049K |
| GPT-6 Astra openai/gpt-6-astra | $0.0885 | $0.4423 | 1050K |
| Llama 3.2 3B (Morpheus Web) meta-llama/llama-3.2-3b-instruct:web | $0.1105 | $0.4422 | 128K |
| MiniMax M3.1 Flash minimax/minimax-m3-1-flash | $0.1125 | $0.4500 | 1000K |
| GLM 4.7 Flash (Morpheus Web) z-ai/glm-4.7-flash:web | $0.1072 | $0.4537 | 198K |
| GPT-5.4 Mini openai/gpt-5.4-mini | $0.0823 | $0.4940 | 400K |
| Qwen3 VL 30B A3B qwen/qwen3-vl-30b-a3b-thinking | $0.1100 | $0.4950 | 128K |
| Hermes 3 Llama 3.1 405b nousresearch/hermes-3-llama-3.1-405b | $0.4396 | $0.4396 | 128K |
| GPT-6 Luna Pro openai/gpt-6-luna-pro | $0.1100 | $0.5500 | 1050K |
| GLM 4.7 Flash E2EE z-ai/e2ee-glm-4.7-flash | $0.1287 | $0.5445 | 198K |
| Qwen 3 235B A22B Instruct 2507 (Morpheus Web) qwen/qwen3-235b-a22b-2507:web | $0.1105 | $0.5527 | 128K |
| NVIDIA: Nemotron 3.5 Super VL nvidia/nemotron-3.5-super-vl | $0.1650 | $0.5500 | 262K |
| GPT-5.6 Luna Pro openai/gpt-5.6-luna-pro | $0.1066 | $0.6398 | 1050K |
| Claude Sonnet 5 anthropic/claude-sonnet-5 | $0.1291 | $0.6457 | 1000K |
| Venice Uncensored 1.1 venice/uncensored | $0.1474 | $0.6633 | 32K |
| MiniMax M3 Preview minimax/minimax-m3-preview | $0.1650 | $0.6600 | 524K |
| DeepSeek V4.1 Flash Uncensored deepseek/deepseek-v4.1-flash-uncensored | $0.1650 | $0.6600 | 1049K |
| Qwen 3.6 35B A3B Uncensored (E2EE) qwen/e2ee-qwen3-6-35b-a3b-uncensored-p | $0.2200 | $0.6600 | 128K |
| Trinity Large Thinking arcee-ai/trinity-large-thinking | $0.2172 | $0.6952 | 256K |
| Qwen3 VL 235B qwen/qwen3-vl-235b-a22b-thinking | $0.0827 | $0.7486 | 256K |
| GPT-5 Image Mini openai/gpt-5-image-mini | $0.6875 | $0.5500 | 8K |
| Venice Role Play Uncensored venice/uncensored-role-play | $0.1813 | $0.7253 | 128K |
| Qwen 3.7 Plus qwen/qwen3.7-plus | $0.1813 | $0.7253 | 256K |
| LiquidAI: LFM2.5-24B-A2B liquid/lfm-2.5-24b-a2b | $0.0550 | $0.7700 | 128K |
| GPT-5.5 openai/gpt-5.5 | $0.1375 | $0.8249 | 1000K |
| GPT-5 Image openai/gpt-5-image | $0.6600 | $0.6600 | 8K |
| Qwen 3 Coder 480B Turbo qwen/qwen3-coder-turbo | $0.1925 | $0.8250 | 256K |
| Qwen 3.8 Max qwen/qwen-3-8-max | $0.2801 | $0.8404 | 1000K |
| MiniMax M2.5 (Morpheus Web) minimax/minimax-m2.5:web | $0.2506 | $0.8770 | 198K |
| GPT-5.2 openai/gpt-5.2 | $0.1153 | $0.9225 | 400K |
| Aion 3.0 Mini aion-labs/aion-3-0-mini | $0.4235 | $0.8470 | 128K |
| Trinity Large Thinking (Morpheus Web) arcee-ai/trinity-large-thinking:web | $0.2578 | $0.9281 | 256K |
| Claude Opus 5 anthropic/claude-opus-5 | $0.1925 | $0.9625 | 1000K |
| Seed 2.1 Turbo bytedance/seed-2-1-turbo | $0.2174 | $1.09 | 256K |
| Reflection: Beam 1.0 501B A23B reflection/beam-1.0-501b-a23b | $0.2750 | $1.10 | 1049K |
| Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 | $0.2245 | $1.12 | 1000K |
| Grok 4.6 x-ai/grok-4.6 | $0.3625 | $1.09 | 500K |
| Grok Build 0.1 x-ai/grok-build-0.1 | $0.5500 | $1.10 | 256K |
| Z.ai: GLM 5.3 FlashX z-ai/glm-5.3-flashx | $0.3459 | $1.17 | 1049K |
| MiniMax M2.7 (Morpheus Web) minimax/minimax-m2.7:web | $0.3094 | $1.24 | 198K |
| Gemini 3.5 Flash Lite google/gemini-3-5-flash-lite | $0.1591 | $1.33 | 1000K |
| Meta: Muse Glimmer 30B meta-llama/muse-glimmer-30b | $0.3300 | $1.32 | 131K |
| Qwen 3 Next 80b (Morpheus Web) qwen/qwen3-next-80b-a3b-instruct:web | $0.2580 | $1.40 | 256K |
| Gemini 3.1 Pro google/gemini-3.1-pro | $0.2415 | $1.45 | 1049K |
| Qwen3.5 Plus qwen/qwen3.5-plus | $0.2431 | $1.46 | 1000K |
| Aion 2.0 aion-labs/aion-2.0 | $0.7480 | $1.50 | 128K |
| GLM 5V Turbo z-ai/glm-5v-turbo | $0.4773 | $1.59 | 200K |
| Cohere: Command A+ cohere/command-a-plus | $0.3300 | $1.65 | 192K |
| GLM 4.7 Thinking z-ai/glm-4.7-thinking | $0.3713 | $1.65 | 128K |
| GLM 4.7 Thinking (Morpheus Web) z-ai/glm-4.7-thinking:web | $0.3713 | $1.65 | 128K |
| Mistral: Mistral Large 4 mistralai/mistral-large-4-0 | $0.5236 | $1.61 | 524K |
| Kimi K2 moonshotai/kimi-k2 | $0.4389 | $1.77 | 256K |
| GLM 5.1 E2EE z-ai/e2ee-glm-5.1 | $0.4840 | $1.83 | 200K |
| Claude Opus 5.5 anthropic/claude-opus-5.5 | $0.4052 | $2.03 | 1000K |
| Gemini 3.6 Flash google/gemini-3-6-flash | $0.4066 | $2.03 | 1000K |
| Qwen 3.6 Plus Uncensored qwen/qwen3.6-plus-uncensored | $0.3438 | $2.06 | 1000K |
| Llama 3.3 70B (Morpheus Web) meta-llama/llama-3.3-70b-instruct:web | $0.5159 | $2.06 | 128K |
| Claude Opus 4.8 anthropic/claude-opus-4.8 | $0.4351 | $2.18 | 1000K |
| MiniMax M2.7 Highspeed minimax/minimax-m2.7-highspeed | $0.5610 | $2.24 | 205K |
| Hermes 3 Llama 3.1 405b (Morpheus Web) meta-llama/hermes-3-llama-3.1-405b:web | $0.8107 | $2.21 | 128K |
| Kimi K2.7 Code (Morpheus Web) moonshotai/kimi-k2.7-code:web | $0.5012 | $2.51 | 262K |
| Kimi K2.5 (Morpheus Web) moonshotai/kimi-k2.5:web | $0.4127 | $2.58 | 256K |
| Gemini 2.5 Pro google/gemini-2.5-pro | $0.3300 | $2.64 | 1049K |
| GLM 5.2 E2EE z-ai/e2ee-glm-5-2-p | $0.7685 | $2.52 | 524K |
| Meta: Muse Spark Open meta-llama/muse-spark-open | $0.7562 | $2.57 | 1049K |
| Moondream: Moondream 3.1 moondream/moondream3.1-9b-a2b | $0.3300 | $2.75 | 32K |
| Moondream: Moondream 3 Preview moondream/moondream3-preview | $0.3300 | $2.75 | 32K |
| Claude Opus 4.5 anthropic/claude-opus-4.5 | $0.5599 | $2.80 | 198K |
| Aion 3.0 aion-labs/aion-3-0 | $1.29 | $2.59 | 128K |
| DeepSeek V4 Pro (Morpheus Web) deepseek/deepseek-v4-pro:web | $1.28 | $2.80 | 1000K |
| GLM 5.2 (Morpheus Web) z-ai/glm-5.2:web | $0.8844 | $3.02 | 1049K |
| GLM 5 (Morpheus Web) z-ai/glm-5:web | $0.8107 | $3.06 | 198K |
| Nano Banana 2 (Venice) venice/nano-banana-2 | $0.5445 | $3.27 | 8K |
| ByteDance Seed: Seed-2.0-Code bytedance/seed-2.0-code | $0.5500 | $3.30 | 262K |
| Google: Gemini 4 Argon google/gemini-4-argon | $0.6593 | $3.30 | 1049K |
| Elorian: Glimpse elorian/glimpse | $0.6600 | $3.30 | 262K |
| Abliterated Large V2 abliteration-ai/abliteration-abliterated-model-large-v2 | $1.80 | $2.99 | 1000K |
| Kimi K2.6 (Morpheus Web) moonshotai/kimi-k2.6:web | $0.6264 | $3.43 | 256K |
| Qwen3.7 Max qwen/qwen3.7-max | $1.10 | $3.30 | 1000K |
| GLM 4.7 (Morpheus Web) z-ai/glm-4.7:web | $0.9075 | $3.42 | 128K |
| GPT-5.2 Codex openai/gpt-5.2-codex | $0.4813 | $3.85 | 256K |
| GLM 5.1 Non-thinking (Morpheus Web) z-ai/glm-5.1-non-thinking:web | $1.11 | $3.69 | 200K |
| GLM 5.1 Non-thinking z-ai/glm-5.1-non-thinking | $1.11 | $3.69 | 200K |
| Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview | $0.6600 | $3.96 | 1000K |
| GLM 5.1 (Morpheus Web) z-ai/glm-5.1:web | $1.29 | $4.05 | 200K |
| GPT-5.4 Image 2 openai/gpt-5.4-image-2 | $2.20 | $4.13 | 8K |
| Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 | $1.02 | $5.11 | 198K |
| Claude Fable 5 anthropic/claude-fable-5 | $1.06 | $5.29 | 1000K |
| Claude Fable 5.1 anthropic/claude-fable-5.1 | $1.14 | $5.70 | 1000K |
| Sakana: Fugu Max sakana/fugu-max | $2.20 | $6.60 | 1000K |
| GPT-5.6 Terra Pro openai/gpt-5.6-terra-pro | $1.21 | $7.26 | 1050K |
| MiMo-V2.6-Pro-UltraSpeed xiaomi/mimo-v2.6-pro-ultraspeed | $3.54 | $7.08 | 1049K |
| Pareto 26.9 unbiased/pareto-26.9 | $2.75 | $8.25 | 262K |
| GPT-5.6 Sol Pro openai/gpt-5.6-sol-pro | $1.74 | $8.69 | 1050K |
| GPT-6 Sol Pro openai/gpt-6-sol-pro | $2.20 | $11.00 | 1050K |
| OpenAI: GPT-6.1 Sol Pro openai/gpt-6.1-sol-pro | $2.20 | $11.00 | 1050K |
| Qwen: Qwen3.8 Max Prime qwen/qwen3.8-max-prime | $3.74 | $11.22 | 1000K |
| Kimi K3 Fast moonshotai/kimi-k3-fast-api | $2.37 | $11.86 | 1000K |
| Fireworks: Ember-1 fireworks/ember-1 | $3.30 | $16.50 | 1049K |
| Claude Opus 5 (Fast) anthropic/claude-opus-5-fast | $4.27 | $21.34 | 1000K |
| Claude Opus 4.8 Fast anthropic/claude-opus-4.8-fast | $4.55 | $22.76 | 1000K |
| GPT-5.4 Pro openai/gpt-5.4-pro | $4.56 | $27.38 | 1000K |
| Sakana: Fugu Ultra v2 sakana/fugu-ultra-v2 | $5.50 | $33.00 | 1000K |
| GPT-5.5 Pro openai/gpt-5.5-pro | $9.87 | $59.22 | 1000K |
| Claude Opus 4.7 Fast anthropic/claude-opus-4.7-fast | $19.80 | $99.00 | 1000K |
| Claude Opus 4.6 Fast anthropic/claude-opus-4.6-fast | $29.70 | $148.50 | 1000K |
LLM API pricing — FAQ
What is the cheapest LLM API?
Prices change constantly. UberLLM routes every request to the cheapest healthy seller for that model and bills the price shown, which includes UberLLM's 10% fee. Small open-weight models like DeepSeek and GLM run for a few cents per million tokens; frontier models (GPT, Claude, Gemini) cost more. See the live table for current per-model pricing.
How is LLM API pricing measured?
Pricing is quoted per 1 million tokens, split into input (prompt) and output (completion). The table shows the listed price for each model; a blended figure weights input and output 1:3 to rank models by real-world cost. Prices include UberLLM's 10% fee, so the price shown is what each request costs.
Can I use all these models with one API key?
Yes. UberLLM gives you one OpenAI-compatible key and base URL (https://api.uberllm.dev/v1) for every model listed here — no per-provider contracts. Change one line in the OpenAI or Anthropic SDK.