Prix des API LLM : 237 modèles comparés
Moins cher que OpenRouter sur 149 modèles sur 150, jusqu’à 99% de moins, au meilleur prix actuel d’UberLLM (vérifié le 2 novembre 2026).
Prix API en direct, modèle par modèle, pour GPT, Claude, Gemini, DeepSeek, GLM, Qwen, Llama, Mistral, Kimi et d’autres, pour 1M de tokens d’entrée et de sortie. Tous les modèles fonctionnent avec une seule clé API, et UberLLM n’ajoute aucuns frais à ces prix.
Combien vous coûterait votre mois ?
Sur UberLLM
$21.98
OpenRouter : $400.00Prix officiel : $400.00Vous économisez $378.02 par mois
UberLLM face à OpenRouter, modèle par modèle
| Modèle | UberLLM entrée / sortie | OpenRouter entrée / sortie | Sur UberLLM |
|---|---|---|---|
| GLM-5.2 z-ai/glm-5.2 | $0.00056 / $0.0022 | $0.0060 / $6.80 | 99% moins cher |
| GPT-OSS 120B openai/gpt-oss-120b | $0.000069 / $0.00030 | $0.1500 / $0.6000 | 99% moins cher |
| GPT-OSS 20B openai/gpt-oss-20b | $0.000018 / $0.000089 | $0.0300 / $0.1300 | 99% moins cher |
| GPT OSS Safeguard 20B openai/gpt-oss-safeguard-20b | $0.000074 / $0.00030 | $0.0750 / $0.3000 | 99% moins cher |
| GLM 4.5 Air z-ai/glm-4.5-air | $0.00013 / $0.00084 | $0.1300 / $0.8500 | 99% moins cher |
| DeepSeek V4 Pro deepseek/deepseek-v4-pro | $0.0016 / $0.0032 | $1.60 / $3.20 | 99% moins cher |
| Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b | $0.0021 / $0.0063 | $2.00 / $6.00 | 99% moins cher |
| Qwen: Qwen3.8 Max (0902) qwen/qwen3.8-max-0902 | $0.0022 / $0.0065 | $2.00 / $6.00 | 99% moins cher |
| Qwen: Qwen3.8 Omni Flash qwen/qwen3.8-omni-flash | $0.00018 / $0.00056 | $0.1500 / $0.4700 | 99% moins cher |
| MiniMax M2.1 minimax/minimax-m2.1 | $0.00036 / $0.0014 | $0.3000 / $1.20 | 99% moins cher |
| Kimi K2.7 Code moonshotai/kimi-k2.7-code | $0.00097 / $0.0056 | $0.6000 / $3.50 | 99% moins cher |
| Kimi K2.6 moonshotai/kimi-k2.6 | $0.0013 / $0.0067 | $0.6500 / $3.41 | 99% moins cher |
| DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash | $0.00018 / $0.0014 | $0.0450 / $0.5000 | 99% moins cher |
| GLM 5.3 z-ai/glm-5.3 | $0.00070 / $0.0141 | $0.0800 / $3.60 | 99% moins cher |
| GLM-4.7 z-ai/glm-4.7 | $0.0028 / $0.0102 | $0.6000 / $2.20 | 99% moins cher |
| Gemma 4 26B A4B IT google/gemma-4-26b-a4b-it | $0.00045 / $0.0015 | $0.1000 / $0.3000 | 99% moins cher |
| GLM 4.7 Flash z-ai/glm-4.7-flash | $0.00031 / $0.0020 | $0.0605 / $0.4000 | 99% moins cher |
| Kimi K3 moonshotai/kimi-k3 | $0.0010 / $0.0788 | $0.1920 / $15.00 | 99% moins cher |
| GLM-5 z-ai/glm-5 | $0.0054 / $0.0174 | $1.00 / $3.20 | 99% moins cher |
| Gemma 3 27B google/gemma-3-27b-it | $0.00079 / $0.0020 | $0.0800 / $0.3500 | 99% moins cher |
| Gemma 3 4B IT google/gemma-3-4b-it | $0.00046 / $0.00058 | $0.0500 / $0.1000 | 99% moins cher |
| Qwen 3 235B A22B Instruct 2507 qwen/qwen3-235b-a22b-2507 | $0.00057 / $0.0035 | $0.0900 / $0.5500 | 99% moins cher |
| Gemini 3 Flash Preview google/gemini-3-flash-preview | $0.0036 / $0.0216 | $0.5000 / $3.00 | 99% moins cher |
| DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731 | $0.00090 / $0.0018 | $0.1190 / $0.2380 | 99% moins cher |
| Gemma 4 31B IT google/gemma-4-31b-it | $0.00090 / $0.0034 | $0.2000 / $0.4000 | 99% moins cher |
Voir les 150 modèles
| Modèle | UberLLM entrée / sortie | OpenRouter entrée / sortie | Sur UberLLM |
|---|---|---|---|
| GPT-6 Astra openai/gpt-6-astra | $0.0799 / $0.3993 | $10.00 / $50.00 | 99% moins cher |
| Claude Opus 4.7 anthropic/claude-opus-4.7 | $0.0400 / $0.2000 | $5.00 / $25.00 | 99% moins cher |
| Kimi K2.5 moonshotai/kimi-k2.5 | $0.0041 / $0.0205 | $0.5000 / $2.50 | 99% moins cher |
| Grok 4.5 x-ai/grok-4.5 | $0.0168 / $0.0505 | $2.00 / $6.00 | 99% moins cher |
| GLM-4.6 z-ai/glm-4.6 | $0.0042 / $0.0170 | $0.5000 / $2.00 | 99% moins cher |
| Qwen3 Next 80B A3B qwen/qwen3-next-80b-a3b-instruct | $0.00086 / $0.0095 | $0.0900 / $1.10 | 99% moins cher |
| MiniMax M2.5 minimax/minimax-m2.5 | $0.0024 / $0.0086 | $0.2700 / $0.9500 | 99% moins cher |
| Gemini 3.8 Flash google/gemini-3.8-flash | $0.0074 / $0.0372 | $0.8250 / $4.13 | 99% moins cher |
| MiniMax M2 minimax/minimax-m2 | $0.0023 / $0.0093 | $0.2550 / $1.02 | 99% moins cher |
| Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 | $0.0285 / $0.1425 | $3.00 / $15.00 | 99% moins cher |
| Qwen3.8 Flash qwen/qwen3.8-flash | $0.0014 / $0.0045 | $0.1500 / $0.4700 | 99% moins cher |
| GLM 4.5 z-ai/glm-4.5 | $0.0059 / $0.0216 | $0.6000 / $2.20 | 99% moins cher |
| Gemma 3 12B IT google/gemma-3-12b-it | $0.00049 / $0.0015 | $0.0500 / $0.1500 | 99% moins cher |
| Qwen3 Coder 30B A3B Instruct qwen/qwen3-coder-30b-a3b-instruct | $0.00069 / $0.0028 | $0.0700 / $0.2800 | 99% moins cher |
| Qwen3 32B qwen/qwen3-32b | $0.00079 / $0.0028 | $0.0800 / $0.2800 | 99% moins cher |
| Qwen3 Coder Next qwen/qwen3-coder-next | $0.0012 / $0.0079 | $0.1200 / $0.8000 | 99% moins cher |
| Qwen 3 Coder 480b qwen/qwen3-coder | $0.0030 / $0.0099 | $0.3000 / $1.00 | 99% moins cher |
| Gemini 3.1 Flash Lite google/gemini-3.1-flash-lite | $0.0025 / $0.0149 | $0.2500 / $1.50 | 99% moins cher |
| Qwen3 VL 235B A22B qwen/qwen3-vl-235b-a22b-instruct | $0.0021 / $0.0188 | $0.2100 / $1.90 | 99% moins cher |
| Gemini 2.5 Flash google/gemini-2.5-flash | $0.0030 / $0.0248 | $0.3000 / $2.50 | 99% moins cher |
| Kimi K2 Thinking moonshotai/kimi-k2-thinking | $0.0059 / $0.0248 | $0.6000 / $2.50 | 99% moins cher |
| Grok 4.3 x-ai/grok-4.3 | $0.0124 / $0.0248 | $1.25 / $2.50 | 99% moins cher |
| GLM-5 Turbo z-ai/glm-5-turbo | $0.0119 / $0.0396 | $1.20 / $4.00 | 99% moins cher |
| Gemini 3.7 Flash google/gemini-3.7-flash | $0.0075 / $0.0375 | $0.7500 / $3.75 | 99% moins cher |
| Gemini 3.5 Flash google/gemini-3.5-flash | $0.0150 / $0.0900 | $1.50 / $9.00 | 99% moins cher |
| GPT-5.6 Luna openai/gpt-5.6-luna | $0.0020 / $0.0121 | $0.2000 / $1.20 | 98% moins cher |
| DeepSeek V3.2 deepseek/deepseek-v3.2 | $0.0026 / $0.0039 | $0.2600 / $0.3800 | 98% moins cher |
| NVIDIA Nemotron 3 Ultra 550B nvidia/nemotron-3-ultra-550b-a55b | $0.0050 / $0.0250 | $0.6000 / $2.40 | 98% moins cher |
| GLM 5.1 z-ai/glm-5.1 | $0.0152 / $0.0479 | $1.40 / $4.40 | 98% moins cher |
| GLM 5.3 Flash z-ai/glm-5.3-flash | $0.00033 / $0.0011 | $0.0285 / $0.0923 | 98% moins cher |
| Z.ai: GLM 5.3 Prime z-ai/glm-5.3-prime | $0.0338 / $0.1063 | $2.80 / $8.80 | 98% moins cher |
| NVIDIA Nemotron 3 Nano 30B nvidia/nemotron-3-nano-30b-a3b | $0.00074 / $0.0030 | $0.0600 / $0.2400 | 98% moins cher |
| DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 | $0.0045 / $0.0180 | $0.3000 / $1.20 | 98% moins cher |
| GPT-5.6 Sol openai/gpt-5.6-sol | $0.0641 / $0.3205 | $4.00 / $20.00 | 98% moins cher |
| Claude Opus 4.6 anthropic/claude-opus-4.6 | $0.0889 / $0.4444 | $5.00 / $25.00 | 98% moins cher |
| Claude Opus 5 anthropic/claude-opus-5 | $0.0900 / $0.4500 | $5.00 / $25.00 | 98% moins cher |
| GPT-5.6 Terra openai/gpt-5.6-terra | $0.0378 / $0.2267 | $2.00 / $12.00 | 98% moins cher |
| OpenAI: GPT-6.1 Terra openai/gpt-6.1-terra | $0.0196 / $0.0982 | $1.00 / $5.00 | 98% moins cher |
| Claude Opus 4.5 anthropic/claude-opus-4.5 | $0.0985 / $0.4925 | $5.00 / $25.00 | 98% moins cher |
| GPT-6 Sol openai/gpt-6-sol | $0.0403 / $0.2013 | $2.00 / $10.00 | 97% moins cher |
| GPT-4o Mini openai/gpt-4o-mini | $0.0035 / $0.0138 | $0.1500 / $0.6000 | 97% moins cher |
| GPT-4o openai/gpt-4o | $0.0589 / $0.2355 | $2.50 / $10.00 | 97% moins cher |
| GPT-5.4 openai/gpt-5.4 | $0.0608 / $0.3648 | $2.50 / $15.00 | 97% moins cher |
| GPT-5.5 openai/gpt-5.5 | $0.1250 / $0.7500 | $5.00 / $30.00 | 97% moins cher |
| GPT-6 Luna openai/gpt-6-luna | $0.0030 / $0.0149 | $0.1000 / $0.5000 | 97% moins cher |
| DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813 | $0.0035 / $0.1206 | $0.1150 / $4.00 | 96% moins cher |
| Qwen 3 235B A22B Thinking 2507 qwen/qwen3-235b-a22b-thinking-2507 | $0.0910 / $0.0910 | $0.4500 / $3.50 | 96% moins cher |
| Qwen 3.5 397B qwen/qwen3.5-397b-a17b | $0.0179 / $0.1289 | $0.5000 / $3.60 | 96% moins cher |
| Claude Opus 5.5 anthropic/claude-opus-5.5 | $0.1579 / $0.7897 | $4.00 / $20.00 | 96% moins cher |
| GPT-6.1 Sol openai/gpt-6.1-sol | $0.0819 / $0.4094 | $2.00 / $10.00 | 95% moins cher |
| Claude Sonnet 5 anthropic/claude-sonnet-5 | $0.0904 / $0.4520 | $2.00 / $10.00 | 95% moins cher |
| Qwen: Qwen3.7 Flash qwen/qwen3.7-flash | $0.0014 / $0.0060 | $0.0300 / $0.1300 | 95% moins cher |
| Mistral Large mistralai/mistral-large | $0.0928 / $0.2784 | $2.00 / $6.00 | 95% moins cher |
| GPT-5.3 Codex openai/gpt-5.3-codex | $0.0839 / $0.6711 | $1.75 / $14.00 | 95% moins cher |
| Claude Fable 5 anthropic/claude-fable-5 | $0.4800 / $2.40 | $10.00 / $50.00 | 95% moins cher |
| Qwen 3.6 27B qwen/qwen3.6-27b | $0.0159 / $0.1323 | $0.4500 / $2.70 | 95% moins cher |
| MoonshotAI: Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | $0.0999 / $0.4995 | $2.00 / $10.00 | 95% moins cher |
| Claude Opus 4.8 anthropic/claude-opus-4.8 | $0.2592 / $1.30 | $5.00 / $25.00 | 94% moins cher |
| GPT-5.2 openai/gpt-5.2 | $0.0927 / $0.7420 | $1.75 / $14.00 | 94% moins cher |
| Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 | $0.1099 / $0.5495 | $2.00 / $10.00 | 94% moins cher |
| Claude Haiku 4.5 anthropic/claude-haiku-4.5 | $0.0581 / $0.2907 | $1.00 / $5.00 | 94% moins cher |
| MiniMax M3 minimax/minimax-m3 | $0.0180 / $0.0719 | $0.3000 / $1.20 | 94% moins cher |
| Grok 4.7 x-ai/grok-4.7 | $0.1200 / $0.3600 | $2.00 / $6.00 | 94% moins cher |
| MiniMax M2.7 minimax/minimax-m2.7 | $0.0192 / $0.0769 | $0.3000 / $1.20 | 93% moins cher |
| Claude Haiku 5.5 anthropic/claude-haiku-5.5 | $0.0071 / $0.0355 | $0.1000 / $0.5000 | 92% moins cher |
| Tencent HY3 tencent/hy3 | $0.0095 / $0.0380 | $0.1320 / $0.5280 | 92% moins cher |
| Claude Fable 5.1 anthropic/claude-fable-5.1 | $0.7868 / $3.93 | $10.00 / $50.00 | 92% moins cher |
| Google: Gemini 4 Argon google/gemini-4-argon | $0.1593 / $0.7963 | $2.00 / $10.00 | 92% moins cher |
| GPT-5.4 Mini openai/gpt-5.4-mini | $0.0733 / $0.4401 | $0.7500 / $4.50 | 90% moins cher |
| GPT 5 Nano openai/gpt-5-nano | $0.0059 / $0.0471 | $0.0500 / $0.4000 | 88% moins cher |
| GPT-5.4 Pro openai/gpt-5.4-pro | $4.11 / $24.64 | $30.00 / $180.00 | 86% moins cher |
| Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct | $0.0145 / $0.0465 | $0.1000 / $0.3200 | 85% moins cher |
| MiMo-V2.6-Flash xiaomi/mimo-v2.6-flash | $0.0208 / $0.0416 | $0.1400 / $0.2800 | 85% moins cher |
| Grok 4.6 x-ai/grok-4.6 | $0.3564 / $1.07 | $2.00 / $6.00 | 82% moins cher |
| Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 | $0.5505 / $2.75 | $3.00 / $15.00 | 81% moins cher |
| MiMo-V2.6-Pro xiaomi/mimo-v2.6-pro | $0.0851 / $0.1701 | $0.4350 / $0.8700 | 80% moins cher |
| GPT 5.4 Nano openai/gpt-5.4-nano | $0.0396 / $0.2475 | $0.2000 / $1.25 | 80% moins cher |
| DeepSeek V4 Flash deepseek/deepseek-v4-flash | $0.0182 / $0.0364 | $0.0910 / $0.1820 | 80% moins cher |
| Gemini 2.5 Pro google/gemini-2.5-pro | $0.3000 / $2.40 | $1.25 / $10.00 | 76% moins cher |
| GPT 5 Mini openai/gpt-5-mini | $0.0612 / $0.4900 | $0.2500 / $2.00 | 75% moins cher |
| GPT-5.2 Codex openai/gpt-5.2-codex | $0.4375 / $3.50 | $1.75 / $14.00 | 75% moins cher |
| GPT-5.6 Luna Pro openai/gpt-5.6-luna-pro | $0.0599 / $0.3593 | $0.2000 / $1.20 | 70% moins cher |
| Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview | $0.6000 / $3.60 | $2.00 / $12.00 | 70% moins cher |
| GPT-5.5 Pro openai/gpt-5.5-pro | $9.00 / $54.00 | $30.00 / $180.00 | 70% moins cher |
| Qwen 3.5 35B A3B qwen/qwen3.5-35b-a3b | $0.0473 / $0.3151 | $0.1400 / $1.00 | 68% moins cher |
| Qwen 3.5 9B qwen/qwen3.5-9b | $0.0300 / $0.0900 | $0.1700 / $0.2500 | 67% moins cher |
| Aion 2.0 aion-labs/aion-2.0 | $0.2800 / $0.5600 | $0.8000 / $1.60 | 65% moins cher |
| Mistral Small 3.2 24B Instruct mistralai/mistral-small-3.2-24b-instruct | $0.0299 / $0.0798 | $0.0750 / $0.2000 | 60% moins cher |
| Z.ai: GLM 5.3 FlashX z-ai/glm-5.3-flashx | $0.1480 / $0.5000 | $0.3700 / $1.25 | 60% moins cher |
| GPT-6 Sol Pro openai/gpt-6-sol-pro | $0.8000 / $4.00 | $2.00 / $10.00 | 60% moins cher |
| OpenAI: GPT-6.1 Sol Pro openai/gpt-6.1-sol-pro | $0.8000 / $4.00 | $2.00 / $10.00 | 60% moins cher |
| GPT-6 Luna Pro openai/gpt-6-luna-pro | $0.0400 / $0.2000 | $0.1000 / $0.5000 | 59% moins cher |
| GLM 5V Turbo z-ai/glm-5v-turbo | $0.4896 / $1.63 | $1.20 / $4.00 | 59% moins cher |
| Hermes 3 Llama 3.1 405b nousresearch/hermes-3-llama-3.1-405b | $0.4496 / $0.4496 | $1.00 / $1.00 | 55% moins cher |
| inclusionAI: Ling 3.1 Flash inclusionai/ling-3.1-flash | $0.0338 / $0.1013 | $0.0750 / $0.2250 | 55% moins cher |
| MiMo-V2.5-Pro xiaomi/mimo-v2.5-pro | $0.2160 / $0.8100 | $0.4800 / $1.80 | 55% moins cher |
| Sakana: Fugu Max sakana/fugu-max | $0.9200 / $2.76 | $2.00 / $6.00 | 54% moins cher |
| Sakana: Fugu Ultra v2 sakana/fugu-ultra-v2 | $2.30 / $13.80 | $5.00 / $30.00 | 54% moins cher |
| Qwen 3.7 Plus qwen/qwen3.7-plus | $0.1648 / $0.6593 | $0.3200 / $1.28 | 48% moins cher |
| Qwen3 VL 30B A3B qwen/qwen3-vl-30b-a3b-thinking | $0.1525 / $0.5490 | $0.2900 / $1.00 | 45% moins cher |
| Mercury 2 inception/mercury-2 | $0.1525 / $0.4575 | $0.2500 / $0.7500 | 38% moins cher |
| GPT-5.6 Sol Pro openai/gpt-5.6-sol-pro | $2.68 / $13.40 | $4.00 / $20.00 | 32% moins cher |
| Llama 3.2 3B meta-llama/llama-3.2-3b-instruct | $0.0350 / $0.2310 | $0.0509 / $0.3350 | 31% moins cher |
| Grok Build 0.1 x-ai/grok-build-0.1 | $0.6965 / $1.39 | $1.00 / $2.00 | 30% moins cher |
| Qwen3 30B A3B qwen/qwen3-30b-a3b | $0.0840 / $0.3500 | $0.1200 / $0.5000 | 30% moins cher |
| Kimi K2 moonshotai/kimi-k2 | $0.3990 / $1.61 | $0.5700 / $2.30 | 29% moins cher |
| GPT-5.6 Terra Pro openai/gpt-5.6-terra-pro | $1.58 / $9.49 | $2.00 / $12.00 | 20% moins cher |
| DeepSeek: DeepSeek V4 Flash Vision Exp deepseek/deepseek-v4-flash-vision-exp | $0.1725 / $0.5174 | $0.2156 / $0.6468 | 20% moins cher |
| Mercury 3 inception/mercury-3 | $0.0800 / $0.2800 | $0.1000 / $0.3500 | 19% moins cher |
| Inception: Mercury 2.5 inception/mercury-2.5 | $0.0380 / $0.1425 | $0.0400 / $0.1500 | 4% moins cher |
| Mistral: Mistral Large 4 mistralai/mistral-large-4-0 | $0.6930 / $2.08 | $0.7000 / $2.10 | 1% moins cher |
| Fireworks: Ember-1 fireworks/ember-1 | $2.97 / $14.85 | $3.00 / $15.00 | 1% moins cher |
| Particle AI: Particle-1 particle-ai/particle-1 | $0.0495 / $0.4950 | $0.0500 / $0.5000 | 1% moins cher |
| NVIDIA: Nemotron 3.5 Super VL nvidia/nemotron-3.5-super-vl | $0.1485 / $0.4950 | $0.1500 / $0.5000 | 1% moins cher |
| Reflection: Beam 1.0 501B A23B reflection/beam-1.0-501b-a23b | $0.2475 / $0.9900 | $0.2500 / $1.00 | 1% moins cher |
| Cohere: Command A+ cohere/command-a-plus | $0.2970 / $1.49 | $0.3000 / $1.50 | 1% moins cher |
| Elorian: Glimpse elorian/glimpse | $0.5940 / $2.97 | $0.6000 / $3.00 | 1% moins cher |
| Pareto 26.9 unbiased/pareto-26.9 | $2.48 / $7.42 | $2.50 / $7.50 | 1% moins cher |
| Qwen: Qwen3.8 Max Prime qwen/qwen3.8-max-prime | $3.96 / $11.88 | $4.00 / $12.00 | 1% moins cher |
| Moondream: Moondream 3.1 moondream/moondream3.1-9b-a2b | $0.2970 / $2.48 | $0.3000 / $2.50 | 0% moins cher |
| Moondream: Moondream 3 Preview moondream/moondream3-preview | $0.2970 / $2.48 | $0.3000 / $2.50 | 0% moins cher |
| OpenAI: GPT-6.1 Terra Pro openai/gpt-6.1-terra-pro | $0.9900 / $4.95 | $1.00 / $5.00 | 0% moins cher |
| MiMo-V2.6-Pro-UltraSpeed xiaomi/mimo-v2.6-pro-ultraspeed | $4.31 / $8.61 | $4.35 / $8.70 | 0% moins cher |
| LiquidAI: LFM2.5-24B-A2B liquid/lfm-2.5-24b-a2b | $0.0495 / $0.6930 | $0.0500 / $0.7000 | 0% moins cher |
| Qwen3.7 Max qwen/qwen3.7-max | $1.89 / $5.63 | $1.48 / $4.42 | 27% plus cher |
Prix en $ par million de tokens en entrée / sortie. La comparaison pondère l’entrée et la sortie à 1:3. Les prix UberLLM sont le meilleur prix du marché en ce moment ; Les prix de OpenRouter proviennent de sa liste publique de modèles. Les deux vérifiés le 2 novembre 2026. Tous les modèles vendus des deux côtés sont listés, y compris ceux qui coûtent autant ou plus cher ici. OpenRouter est une marque de son propriétaire ; les deux produits sont indépendants.
Tous les modèles de chat, du moins cher au plus cher
| Modèle | Entrée / 1M | Sortie / 1M | Contexte |
|---|---|---|---|
| GPT-OSS 20B openai/gpt-oss-20b | $0.000018 | $0.000089 | 128K |
| GPT-OSS 120B openai/gpt-oss-120b | $0.000069 | $0.00030 | 128K |
| GPT OSS Safeguard 20B openai/gpt-oss-safeguard-20b | $0.000074 | $0.00030 | 128K |
| Qwen: Qwen3.8 Omni Flash qwen/qwen3.8-omni-flash | $0.00018 | $0.00056 | 1000K |
| Gemma 3 4B IT google/gemma-3-4b-it | $0.00046 | $0.00058 | 128K |
| GLM 4.5 Air z-ai/glm-4.5-air | $0.00013 | $0.00084 | 128K |
| GLM 5.3 Flash z-ai/glm-5.3-flash | $0.00033 | $0.0011 | 1049K |
| Ministral 3B mistralai/ministral-3-3b-instruct | $0.0010 | $0.0010 | 128K |
| DeepSeek V4.1 Flash deepseek/deepseek-v4.1-flash | $0.00018 | $0.0014 | 1049K |
| MiniMax M2.1 minimax/minimax-m2.1 | $0.00036 | $0.0014 | 198K |
| Meta: Muse Spark 1.2 Contributor meta-llama/muse-spark-1.2-contributor | $0.00069 | $0.0014 | 1049K |
| Gemma 4 26B A4B IT google/gemma-4-26b-a4b-it | $0.00045 | $0.0015 | 262K |
| Gemma 3 12B IT google/gemma-3-12b-it | $0.00049 | $0.0015 | 128K |
| DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731 | $0.00090 | $0.0018 | 1049K |
| GLM 4.7 Flash z-ai/glm-4.7-flash | $0.00031 | $0.0020 | 198K |
| Meta: Muse Spark 1.3 Contributor meta-llama/muse-spark-1.3-contributor | $0.00094 | $0.0019 | 1049K |
| Gemma 3 27B google/gemma-3-27b-it | $0.00079 | $0.0020 | 40K |
| Ministral 3 8B mistralai/ministral-3-8b-instruct | $0.0017 | $0.0017 | 128K |
| GLM-5.2 z-ai/glm-5.2 | $0.00056 | $0.0022 | 1049K |
| Qwen 3.8 27B qwen/qwen-3-8-27b | $0.00020 | $0.0025 | 262K |
| Ministral 14B 3.0 mistralai/ministral-3-14b-instruct | $0.0020 | $0.0020 | 128K |
| Qwen3 Coder 30B A3B Instruct qwen/qwen3-coder-30b-a3b-instruct | $0.00069 | $0.0028 | 256K |
| Qwen3 32B qwen/qwen3-32b | $0.00079 | $0.0028 | 32K |
| Gemma 4 31B google/gemma-4-31b | $0.00091 | $0.0027 | 256K |
| NVIDIA Nemotron 3 Nano 30B nvidia/nemotron-3-nano-30b-a3b | $0.00074 | $0.0030 | 128K |
| Qwen 3 235B A22B Instruct 2507 qwen/qwen3-235b-a22b-2507 | $0.00057 | $0.0035 | 128K |
| Gemma 4 31B IT google/gemma-4-31b-it | $0.00090 | $0.0034 | 262K |
| DeepSeek V4 Pro deepseek/deepseek-v4-pro | $0.0016 | $0.0032 | 1000K |
| Gemma 4 E2B google/gemma-4-e2b | $0.0020 | $0.0040 | 128K |
| NVIDIA Nemotron Nano 9B v2 nvidia/nemotron-nano-9b-v2 | $0.0011 | $0.0043 | 128K |
| DeepSeek V3.2 deepseek/deepseek-v3.2 | $0.0026 | $0.0039 | 160K |
| Qwen3.8 Flash qwen/qwen3.8-flash | $0.0014 | $0.0045 | 1000K |
| Kimi K2.7 Code moonshotai/kimi-k2.7-code | $0.00097 | $0.0056 | 262K |
| NVIDIA Nemotron 3 Super 120B nvidia/nemotron-3-super-120b | $0.00077 | $0.0062 | 256K |
| Qwen: Qwen3.7 Flash qwen/qwen3.7-flash | $0.0014 | $0.0060 | 1000K |
| Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b | $0.0021 | $0.0063 | 1000K |
| Kimi K2.6 moonshotai/kimi-k2.6 | $0.0013 | $0.0067 | 256K |
| Qwen: Qwen3.8 Max (0902) qwen/qwen3.8-max-0902 | $0.0022 | $0.0065 | 1000K |
| NVIDIA Nemotron Nano 12B v2 VL BF16 nvidia/nemotron-nano-12b-v2 | $0.0022 | $0.0065 | 128K |
| Qwen3 Coder Next qwen/qwen3-coder-next | $0.0012 | $0.0079 | 256K |
| MiniMax M2.5 minimax/minimax-m2.5 | $0.0024 | $0.0086 | 198K |
| Qwen3 Next 80B A3B qwen/qwen3-next-80b-a3b-instruct | $0.00086 | $0.0095 | 256K |
| MiniMax M2 minimax/minimax-m2 | $0.0023 | $0.0093 | 1000K |
| DeepSeek V3.1 deepseek/deepseek-v3.1 | $0.0025 | $0.0094 | 128K |
| GPT OSS Safeguard 120B openai/gpt-oss-safeguard-120b | $0.0024 | $0.0096 | 128K |
| Qwen 3 Coder 480b qwen/qwen3-coder | $0.0030 | $0.0099 | 256K |
| GLM-4.7 z-ai/glm-4.7 | $0.0028 | $0.0102 | 128K |
| GPT-5.6 Luna openai/gpt-5.6-luna | $0.0020 | $0.0121 | 1050K |
| GLM 5.3 z-ai/glm-5.3 | $0.00070 | $0.0141 | 1000K |
| Palmyra Vision 7B writer/palmyra-vision-7b | $0.0034 | $0.0134 | 4K |
| GPT-4o Mini openai/gpt-4o-mini | $0.0035 | $0.0138 | 128K |
| Gemini 3.1 Flash Lite google/gemini-3.1-flash-lite | $0.0025 | $0.0149 | 1049K |
| GPT-6 Luna openai/gpt-6-luna | $0.0030 | $0.0149 | 1050K |
| GLM-4.6 z-ai/glm-4.6 | $0.0042 | $0.0170 | 198K |
| GLM-5 z-ai/glm-5 | $0.0054 | $0.0174 | 198K |
| DeepSeek V4.1 Flash 1017 deepseek/deepseek-v4.1-flash-1017 | $0.0045 | $0.0180 | 1049K |
| Qwen3 VL 235B A22B qwen/qwen3-vl-235b-a22b-instruct | $0.0021 | $0.0188 | 256K |
| Qwen3.5 Flash qwen/qwen3.5-flash | $0.0050 | $0.0200 | 1000K |
| Kimi K2.5 moonshotai/kimi-k2.5 | $0.0041 | $0.0205 | 256K |
| Gemini 3 Flash Preview google/gemini-3-flash-preview | $0.0036 | $0.0216 | 256K |
| Magistral Small 2509 mistralai/magistral-small-2509 | $0.0069 | $0.0208 | 128K |
| GLM 4.5 z-ai/glm-4.5 | $0.0059 | $0.0216 | 128K |
| Gemini 2.5 Flash google/gemini-2.5-flash | $0.0030 | $0.0248 | 1049K |
| NVIDIA Nemotron 3 Ultra 550B nvidia/nemotron-3-ultra-550b-a55b | $0.0050 | $0.0250 | 1000K |
| Kimi K2 Thinking moonshotai/kimi-k2-thinking | $0.0059 | $0.0248 | 256K |
| Grok 4.3 x-ai/grok-4.3 | $0.0124 | $0.0248 | 1000K |
| Meta: Muse Spark 1.2 meta-llama/muse-spark-1.2 | $0.0078 | $0.0267 | 1049K |
| Meta: Muse Spark 1.1 meta-llama/muse-spark-1.1 | $0.0079 | $0.0268 | 1049K |
| Meta: Muse Spark 1.3 meta-llama/muse-spark-1.3 | $0.0091 | $0.0311 | 1049K |
| Claude Haiku 5.5 anthropic/claude-haiku-5.5 | $0.0071 | $0.0355 | 1000K |
| Gemini 3.8 Flash google/gemini-3.8-flash | $0.0074 | $0.0372 | 1049K |
| Gemini 3.7 Flash google/gemini-3.7-flash | $0.0075 | $0.0375 | 1049K |
| Devstral 2 123B mistralai/devstral-2-123b | $0.0077 | $0.0384 | 256K |
| Tencent HY3 tencent/hy3 | $0.0095 | $0.0380 | 262K |
| DeepSeek V4 Flash deepseek/deepseek-v4-flash | $0.0182 | $0.0364 | 1000K |
| Thinking Machines: Inkling thinking-machines/inkling | $0.0094 | $0.0401 | 1049K |
| GLM-5 Turbo z-ai/glm-5-turbo | $0.0119 | $0.0396 | 200K |
| MiMo-V2.6-Flash xiaomi/mimo-v2.6-flash | $0.0208 | $0.0416 | 1049K |
| GPT 5 Nano openai/gpt-5-nano | $0.0059 | $0.0471 | 400K |
| Qwen 3.6 35B A3B qwen/qwen3-6-35b-a3b | $0.0049 | $0.0485 | 262K |
| Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct | $0.0145 | $0.0465 | 128K |
| GPT OSS 20B openai/e2ee-gpt-oss-20b-p | $0.0125 | $0.0475 | 128K |
| GLM 5.1 z-ai/glm-5.1 | $0.0152 | $0.0479 | 200K |
| Grok 4.5 x-ai/grok-4.5 | $0.0168 | $0.0505 | 500K |
| MiniMax M3 minimax/minimax-m3 | $0.0180 | $0.0719 | 200K |
| Kimi K3 moonshotai/kimi-k3 | $0.0010 | $0.0788 | 1000K |
| Qwen3.5 Plus qwen/qwen3.5-plus | $0.0130 | $0.0780 | 1000K |
| Mistral Large 3 mistralai/mistral-large-3 | $0.0248 | $0.0742 | 256K |
| MiniMax M2.7 minimax/minimax-m2.7 | $0.0192 | $0.0769 | 198K |
| Mistral Small 3.2 24B Instruct mistralai/mistral-small-3.2-24b-instruct | $0.0299 | $0.0798 | 256K |
| Gemini 3.5 Flash google/gemini-3.5-flash | $0.0150 | $0.0900 | 1000K |
| Qwen 2.5 7B qwen/e2ee-qwen-2-5-7b-p | $0.0325 | $0.0845 | 32K |
| MiniMax M3.1 Flash minimax/minimax-m3-1-flash | $0.0225 | $0.0900 | 1000K |
| Qwen 3.5 9B qwen/qwen3.5-9b | $0.0300 | $0.0900 | 256K |
| OpenAI: GPT-6.1 Terra openai/gpt-6.1-terra | $0.0196 | $0.0982 | 1050K |
| inclusionAI: Ling 3.1 Flash inclusionai/ling-3.1-flash | $0.0338 | $0.1013 | 262K |
| Z.ai: GLM 5.3 Prime z-ai/glm-5.3-prime | $0.0338 | $0.1063 | 1000K |
| Qwen 3 235B A22B Thinking 2507 qwen/qwen3-235b-a22b-thinking-2507 | $0.0910 | $0.0910 | 128K |
| DeepSeek V4 Pro 0813 deepseek/deepseek-v4-pro-0813 | $0.0035 | $0.1206 | 1049K |
| Qwen 3.5 397B qwen/qwen3.5-397b-a17b | $0.0179 | $0.1289 | 128K |
| Qwen 3.6 27B qwen/qwen3.6-27b | $0.0159 | $0.1323 | 256K |
| Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 | $0.0285 | $0.1425 | 1000K |
| Inception: Mercury 2.5 inception/mercury-2.5 | $0.0380 | $0.1425 | 260K |
| GLM 4.7 Flash Heretic z-ai/glm-4.7-flash-heretic | $0.0279 | $0.1597 | 200K |
| NVIDIA Nemotron 3.5 Lightning 30B nvidia/nemotron-3-5-lightning-30b-a3b | $0.0640 | $0.1600 | 1000K |
| MiMo-V2.6-Pro xiaomi/mimo-v2.6-pro | $0.0851 | $0.1701 | 1049K |
| Mistral Small 4 mistralai/mistral-small-4 | $0.0469 | $0.1875 | 256K |
| Claude Opus 4.7 anthropic/claude-opus-4.7 | $0.0400 | $0.2000 | 1000K |
| GPT-6 Luna Pro openai/gpt-6-luna-pro | $0.0400 | $0.2000 | 1050K |
| Meta: Muse Wonder meta-llama/muse-wonder | $0.0400 | $0.2000 | 1049K |
| GPT-6 Sol openai/gpt-6-sol | $0.0403 | $0.2013 | 1050K |
| Gemma 3 27B E2EE google/e2ee-gemma-3-27b | $0.0560 | $0.2000 | 40K |
| GPT OSS 120B openai/e2ee-gpt-oss-120b-p | $0.0427 | $0.2136 | 128K |
| GPT-5.6 Terra openai/gpt-5.6-terra | $0.0378 | $0.2267 | 1050K |
| OpenAI GPT OSS 120B (Morpheus Web) openai/gpt-oss-120b:web | $0.0525 | $0.2250 | 128K |
| Llama 3.2 3B meta-llama/llama-3.2-3b-instruct | $0.0350 | $0.2310 | 128K |
| GPT-4o openai/gpt-4o | $0.0589 | $0.2355 | 128K |
| GPT 5.4 Nano openai/gpt-5.4-nano | $0.0396 | $0.2475 | 400K |
| Gemma 4 Uncensored google/gemma-4-uncensored | $0.0780 | $0.2399 | 256K |
| Claude Haiku 5.5 (batch) anthropic/claude-haiku-5.5:batch | $0.0500 | $0.2500 | 1000K |
| DeepSeek V4 Flash E2EE deepseek/e2ee-deepseek-v4-flash | $0.1147 | $0.2350 | 1000K |
| Gemma 4 26B A4B Uncensored (E2EE) google/e2ee-gemma-4-26b-a4b-uncensored-p | $0.0565 | $0.2618 | 262K |
| Mercury 3 inception/mercury-3 | $0.0800 | $0.2800 | 1000K |
| Mistral Large mistralai/mistral-large | $0.0928 | $0.2784 | 128K |
| Claude Haiku 4.5 anthropic/claude-haiku-4.5 | $0.0581 | $0.2907 | 200K |
| Venice Uncensored 1.2 venice/uncensored-1.2 | $0.0659 | $0.2967 | 128K |
| Qwen 3.5 35B A3B qwen/qwen3.5-35b-a3b | $0.0473 | $0.3151 | 256K |
| Gemma 4 31B (E2EE) google/e2ee-gemma-4-31b | $0.1000 | $0.3000 | 262K |
| GPT-5.6 Sol openai/gpt-5.6-sol | $0.0641 | $0.3205 | 1050K |
| Qwen 3.6 35B A3B (E2EE) qwen/e2ee-qwen3-6-35b-a3b | $0.0553 | $0.3587 | 128K |
| Qwen3 30B A3B qwen/qwen3-30b-a3b | $0.0840 | $0.3500 | 256K |
| GPT-5.6 Luna Pro openai/gpt-5.6-luna-pro | $0.0599 | $0.3593 | 1050K |
| GPT-5.4 openai/gpt-5.4 | $0.0608 | $0.3648 | 1000K |
| Grok 4.7 x-ai/grok-4.7 | $0.1200 | $0.3600 | 500K |
| Qwen 3.8 Max qwen/qwen-3-8-max | $0.1212 | $0.3638 | 1000K |
| Grok 4.20 Multi-Agent Beta x-ai/grok-4.20-multi-agent-beta | $0.1750 | $0.3500 | 2000K |
| Grok 4.20 Beta x-ai/grok-4.20-beta | $0.1750 | $0.3500 | 2000K |
| Gemma 4 26B A4B IT (Morpheus Web) google/gemma-4-26b-a4b-it:web | $0.1219 | $0.3750 | 262K |
| Gemma 4 31B IT (Morpheus Web) google/gemma-4-31b-it:web | $0.1313 | $0.3750 | 262K |
| GPT-6 Astra openai/gpt-6-astra | $0.0799 | $0.3993 | 1050K |
| GPT-6.1 Sol openai/gpt-6.1-sol | $0.0819 | $0.4094 | 1050K |
| GPT-5.4 Mini openai/gpt-5.4-mini | $0.0733 | $0.4401 | 400K |
| Claude Opus 4.6 anthropic/claude-opus-4.6 | $0.0889 | $0.4444 | 1000K |
| Claude Opus 5 anthropic/claude-opus-5 | $0.0900 | $0.4500 | 1000K |
| Claude Sonnet 5 anthropic/claude-sonnet-5 | $0.0904 | $0.4520 | 1000K |
| Mercury 2 inception/mercury-2 | $0.1525 | $0.4575 | 128K |
| GPT 5 Mini openai/gpt-5-mini | $0.0612 | $0.4900 | 400K |
| Particle AI: Particle-1 particle-ai/particle-1 | $0.0495 | $0.4950 | 1049K |
| DeepSeek V4 Flash 0731 Fast deepseek/deepseek-v4-flash-0731-fast | $0.2205 | $0.4410 | 1000K |
| Claude Opus 4.5 anthropic/claude-opus-4.5 | $0.0985 | $0.4925 | 198K |
| MoonshotAI: Kimi K3.1 Pro moonshotai/kimi-k3.1-pro | $0.0999 | $0.4995 | 1049K |
| NVIDIA: Nemotron 3.5 Super VL nvidia/nemotron-3.5-super-vl | $0.1485 | $0.4950 | 262K |
| Z.ai: GLM 5.3 FlashX z-ai/glm-5.3-flashx | $0.1480 | $0.5000 | 1049K |
| GLM-5.3 Flash Uncensored z-ai/glm-5.3-flash-uncensored | $0.1500 | $0.5000 | 1049K |
| Aion 3.0 Mini aion-labs/aion-3-0-mini | $0.2450 | $0.4900 | 128K |
| DeepSeek: DeepSeek V4 Flash Vision Exp deepseek/deepseek-v4-flash-vision-exp | $0.1725 | $0.5174 | 1049K |
| Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 | $0.1099 | $0.5495 | 1000K |
| Qwen3 VL 235B qwen/qwen3-vl-235b-a22b-thinking | $0.0638 | $0.5775 | 256K |
| Hermes 3 Llama 3.1 405b nousresearch/hermes-3-llama-3.1-405b | $0.4496 | $0.4496 | 128K |
| Qwen3 VL 30B A3B qwen/qwen3-vl-30b-a3b-thinking | $0.1525 | $0.5490 | 128K |
| Venice Uncensored 1.1 venice/uncensored | $0.1344 | $0.6048 | 32K |
| Aion 2.0 aion-labs/aion-2.0 | $0.2800 | $0.5600 | 128K |
| Qwen 3.6 35B A3B Uncensored (E2EE) qwen/e2ee-qwen3-6-35b-a3b-uncensored-p | $0.2000 | $0.6000 | 128K |
| GPT-5.3 Codex openai/gpt-5.3-codex | $0.0839 | $0.6711 | 400K |
| LiquidAI: LFM2.5-24B-A2B liquid/lfm-2.5-24b-a2b | $0.0495 | $0.6930 | 128K |
| Venice Role Play Uncensored venice/uncensored-role-play | $0.1648 | $0.6593 | 128K |
| Qwen 3.7 Plus qwen/qwen3.7-plus | $0.1648 | $0.6593 | 256K |
| Aion 3.5 Mini aion-labs/aion-3-5-mini | $0.3063 | $0.6125 | 262K |
| Gemini 3.1 Pro google/gemini-3.1-pro | $0.1200 | $0.7200 | 1049K |
| GPT-5.2 openai/gpt-5.2 | $0.0927 | $0.7420 | 256K |
| Gemini 3.5 Flash Lite google/gemini-3-5-flash-lite | $0.0900 | $0.7500 | 1000K |
| GPT-5.5 openai/gpt-5.5 | $0.1250 | $0.7500 | 1000K |
| Claude Opus 5.5 anthropic/claude-opus-5.5 | $0.1579 | $0.7897 | 1000K |
| Google: Gemini 4 Argon google/gemini-4-argon | $0.1593 | $0.7963 | 1049K |
| MiMo-V2.5-Pro xiaomi/mimo-v2.5-pro | $0.2160 | $0.8100 | 1050K |
| MiniMax M3 Preview minimax/minimax-m3-preview | $0.2100 | $0.8400 | 524K |
| Trinity Large Thinking arcee-ai/trinity-large-thinking | $0.2344 | $0.8438 | 256K |
| Qwen 3 Coder 480B Turbo qwen/qwen3-coder-turbo | $0.2100 | $0.9000 | 256K |
| DeepSeek V4.1 Flash Uncensored deepseek/deepseek-v4.1-flash-uncensored | $0.0900 | $1.00 | 1049K |
| MiniMax M2.7 Highspeed minimax/minimax-m2.7-highspeed | $0.2400 | $0.9600 | 205K |
| Seed 2.1 Turbo bytedance/seed-2-1-turbo | $0.1976 | $0.9881 | 256K |
| DeepSeek R1 deepseek/deepseek-r1 | $0.2475 | $0.9855 | 160K |
| Reflection: Beam 1.0 501B A23B reflection/beam-1.0-501b-a23b | $0.2475 | $0.9900 | 1049K |
| Grok 4.6 x-ai/grok-4.6 | $0.3564 | $1.07 | 500K |
| Gemini 3.6 Flash google/gemini-3-6-flash | $0.2249 | $1.12 | 1000K |
| Meta: Muse Glimmer 30B meta-llama/muse-glimmer-30b | $0.2970 | $1.19 | 131K |
| MiMo-V2.5 xiaomi/mimo-v2-5 | $0.2440 | $1.22 | 1000K |
| Claude Opus 4.8 anthropic/claude-opus-4.8 | $0.2592 | $1.30 | 1000K |
| Cohere: Command A+ cohere/command-a-plus | $0.2970 | $1.49 | 192K |
| GLM 4.7 Thinking (Morpheus Web) z-ai/glm-4.7-thinking:web | $0.3375 | $1.50 | 128K |
| Grok Build 0.1 x-ai/grok-build-0.1 | $0.6965 | $1.39 | 256K |
| Kimi K2 moonshotai/kimi-k2 | $0.3990 | $1.61 | 256K |
| GLM 5V Turbo z-ai/glm-5v-turbo | $0.4896 | $1.63 | 200K |
| GLM 5.1 E2EE z-ai/e2ee-glm-5.1 | $0.4400 | $1.66 | 200K |
| Abliterated Large Flash abliteration-ai/abliteration-abliterated-model-large-flash | $0.7875 | $1.57 | 1000K |
| GLM 4.7 Thinking z-ai/glm-4.7-thinking | $0.4500 | $2.00 | 128K |
| Mistral: Mistral Large 4 mistralai/mistral-large-4-0 | $0.6930 | $2.08 | 524K |
| Aion 3.0 aion-labs/aion-3-0 | $1.05 | $2.10 | 128K |
| Gemini 2.5 Pro google/gemini-2.5-pro | $0.3000 | $2.40 | 1049K |
| Hermes 3 Llama 3.1 405b (Morpheus Web) meta-llama/hermes-3-llama-3.1-405b:web | $0.8250 | $2.25 | 128K |
| Claude Fable 5 anthropic/claude-fable-5 | $0.4800 | $2.40 | 1000K |
| Moondream: Moondream 3.1 moondream/moondream3.1-9b-a2b | $0.2970 | $2.48 | 32K |
| Moondream: Moondream 3 Preview moondream/moondream3-preview | $0.2970 | $2.48 | 32K |
| OpenAI: GPT-6.1 Terra Pro (batch) openai/gpt-6.1-terra-pro:batch | $0.5000 | $2.50 | 1050K |
| OpenAI: GPT-6.1 Terra (batch) openai/gpt-6.1-terra:batch | $0.5000 | $2.50 | 1050K |
| GLM 5.2 E2EE z-ai/e2ee-glm-5-2-p | $0.7851 | $2.58 | 524K |
| Qwen 3.6 Plus Uncensored qwen/qwen3.6-plus-uncensored | $0.4625 | $2.77 | 1000K |
| Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 | $0.5505 | $2.75 | 198K |
| Meta: Muse Spark Open meta-llama/muse-spark-open | $0.8000 | $2.72 | 1049K |
| Aion 3.5 aion-labs/aion-3-5 | $1.31 | $2.63 | 262K |
| Sakana: Fugu Max sakana/fugu-max | $0.9200 | $2.76 | 1000K |
| ByteDance Seed: Seed-2.0-Code bytedance/seed-2.0-code | $0.4950 | $2.97 | 262K |
| Elorian: Glimpse elorian/glimpse | $0.5940 | $2.97 | 262K |
| GPT-5.2 Codex openai/gpt-5.2-codex | $0.4375 | $3.50 | 256K |
| Kimi K2.6 (Morpheus Web) moonshotai/kimi-k2.6:web | $0.6375 | $3.49 | 256K |
| Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview | $0.6000 | $3.60 | 1000K |
| GLM 5.1 Non-thinking (Morpheus Web) z-ai/glm-5.1-non-thinking:web | $1.13 | $3.75 | 200K |
| Abliterated Large V2 abliteration-ai/abliteration-abliterated-model-large-v2 | $2.07 | $3.45 | 1000K |
| Claude Fable 5.1 anthropic/claude-fable-5.1 | $0.7868 | $3.93 | 1000K |
| GPT-6 Sol Pro openai/gpt-6-sol-pro | $0.8000 | $4.00 | 1050K |
| OpenAI: GPT-6.1 Sol Pro openai/gpt-6.1-sol-pro | $0.8000 | $4.00 | 1050K |
| OpenAI: GPT-6.1 Terra Pro openai/gpt-6.1-terra-pro | $0.9900 | $4.95 | 1050K |
| Qwen3.7 Max qwen/qwen3.7-max | $1.89 | $5.63 | 256K |
| Pareto 26.9 unbiased/pareto-26.9 | $2.48 | $7.42 | 262K |
| GPT-5.6 Terra Pro openai/gpt-5.6-terra-pro | $1.58 | $9.49 | 1050K |
| MiMo-V2.6-Pro-UltraSpeed xiaomi/mimo-v2.6-pro-ultraspeed | $4.31 | $8.61 | 1049K |
| Qwen: Qwen3.8 Max Prime qwen/qwen3.8-max-prime | $3.96 | $11.88 | 1000K |
| GPT-5.6 Sol Pro openai/gpt-5.6-sol-pro | $2.68 | $13.40 | 1050K |
| Sakana: Fugu Ultra v2 sakana/fugu-ultra-v2 | $2.30 | $13.80 | 1000K |
| Fireworks: Ember-1 fireworks/ember-1 | $2.97 | $14.85 | 1049K |
| Kimi K3 Fast moonshotai/kimi-k3-fast-api | $3.15 | $15.75 | 1000K |
| Claude Opus 5 (Fast) anthropic/claude-opus-5-fast | $3.98 | $19.90 | 1000K |
| Claude Opus 4.8 Fast anthropic/claude-opus-4.8-fast | $4.67 | $23.34 | 1000K |
| GPT-5.4 Pro openai/gpt-5.4-pro | $4.11 | $24.64 | 1000K |
| GPT-5.5 Pro openai/gpt-5.5-pro | $9.00 | $54.00 | 1000K |
| Claude Opus 4.6 Fast anthropic/claude-opus-4.6-fast | $27.00 | $135.00 | 1000K |
| Claude Opus 4.7 Fast anthropic/claude-opus-4.7-fast | $27.00 | $135.00 | 1000K |
FAQ sur les prix des API LLM
Comment les requêtes sont-elles acheminées et facturées ?
Chaque requête est envoyée à un fournisseur tiers disponible pour le modèle demandé. Si le fournisseur échoue avant de commencer à répondre, la requête est relancée. Les requêtes qui échouent malgré tout ne sont pas facturées. Une requête coûte ce que son fournisseur a facturé, UberLLM n’ajoute aucuns frais, et chaque requête apparaît avec son coût dans Activité.
Comment les prix des API LLM sont-ils mesurés ?
Les prix sont donnés pour 1 million de tokens, séparés entre tokens d’entrée (prompt) et de sortie (réponse). Chaque prix UberLLM est le meilleur prix en direct sur le marché UberLLM, et la colonne OpenRouter est relevée le même jour dans la liste publique des modèles d’OpenRouter. Les tableaux sont triés selon un prix combiné qui pondère l’entrée et la sortie à 1:3. UberLLM n’ajoute aucuns frais aux prix des fournisseurs. Des frais de carte de 5,5 % + 0,50 $ s’ajoutent quand vous ajoutez du crédit ; votre crédit correspond exactement au montant choisi.
Quels SDK et endpoints sont pris en charge ?
Chaque modèle listé ici est disponible avec une seule clé API sur https://api.uberllm.dev/v1. L’API accepte les requêtes OpenAI Chat Completions et Anthropic Messages : les SDK officiels d’OpenAI et d’Anthropic fonctionnent dès que vous définissez la base URL.