List prices for every language model with published per-token pricing, across every major provider, in one table — plus the two columns nobody else publishes: how much more an output token costs than an input one, and what caching actually saves you.
Every figure below is computed from the live catalogue at load, not typed in by hand.
The output premium is the single most useful number on this page. Prefill is compute-bound and parallel; decode is memory-bandwidth-bound and serial. That physical asymmetry is why output costs multiples of input — and why an architecture that generates fewer, shorter outputs beats one that merely switches to a cheaper model.
Sorted by blended cost at a 3:1 input:output ratio — the common benchmarking convention. The 10:1 column is closer to what agentic and RAG-heavy traffic actually looks like, and the two orders differ more than most people expect.
Updated Aug 4, 2026, 10:57 PM UTC · source: the public OpenRouter model catalogue.
| Model | In / 1M | Out / 1M | Output premium | Cache saves | Blended 3:1 | Blended 10:1 | Context |
|---|---|---|---|---|---|---|---|
| inclusionAI: Ling-2.6-flash inclusionai/ling-2.6-flash | $0.010 | $0.030 | 3.0× | 80% | $0.015 | $0.012 | 262K |
| Mistral: Mistral Nemo mistralai/mistral-nemo | $0.019 | $0.030 | 1.6× | — | $0.022 | $0.020 | 131K |
| IBM: Granite 4.0 Micro ibm-granite/granite-4.0-h-micro | $0.017 | $0.112 | 6.6× | — | $0.041 | $0.026 | 131K |
| Sao10K: Llama 3 8B Lunaris sao10k/l3-lunaris-8b | $0.040 | $0.050 | 1.2× | — | $0.042 | $0.041 | 8K |
| Nex AGI: Nex-N2-Mini nex-agi/nex-n2-mini | $0.025 | $0.100 | 4.0× | 90% | $0.044 | $0.032 | 262K |
| Qwen: Qwen3.7 Flash qwen/qwen3.7-flash | $0.030 | $0.130 | 4.3× | 80% | $0.055 | $0.039 | 1M |
| OpenAI: gpt-oss-20b openai/gpt-oss-20b | $0.030 | $0.130 | 4.3× | — | $0.055 | $0.039 | 131K |
| Mistral: Mistral Small 3 mistralai/mistral-small-24b-instruct-2501 | $0.050 | $0.080 | 1.6× | — | $0.057 | $0.053 | 33K |
| Meta: Llama 3.1 8B Instruct meta-llama/llama-3.1-8b-instruct | $0.050 | $0.080 | 1.6× | 50% | $0.057 | $0.053 | 131K |
| Amazon: Nova Micro 1.0 amazon/nova-micro-v1 | $0.035 | $0.140 | 4.0× | — | $0.061 | $0.045 | 128K |
| IBM: Granite 4.1 8B ibm-granite/granite-4.1-8b | $0.050 | $0.100 | 2.0× | — | $0.063 | $0.055 | 131K |
| Google: Gemma 3 4B google/gemma-3-4b-it | $0.050 | $0.100 | 2.0× | — | $0.063 | $0.055 | 131K |
| Cohere: Command R7B (12-2024) cohere/command-r7b-12-2024 | $0.037 | $0.150 | 4.0× | — | $0.066 | $0.048 | 128K |
| OpenAI: gpt-oss-120b openai/gpt-oss-120b | $0.037 | $0.170 | 4.6× | — | $0.070 | $0.049 | 131K |
| Meta: Llama 3.2 1B Instruct meta-llama/llama-3.2-1b-instruct | $0.027 | $0.201 | 7.4× | — | $0.071 | $0.043 | 60K |
| Poolside: Laguna XS 2.1 poolside/laguna-xs-2.1 | $0.060 | $0.120 | 2.0× | 50% | $0.075 | $0.065 | 262K |
| Google: Gemma 3n 4B google/gemma-3n-e4b-it | $0.060 | $0.120 | 2.0× | — | $0.075 | $0.065 | 33K |
| Google: Gemma 3 12B google/gemma-3-12b-it | $0.050 | $0.150 | 3.0× | — | $0.075 | $0.059 | 131K |
| Qwen: Qwen3 30B A3B Instruct 2507 qwen/qwen3-30b-a3b-instruct-2507 | $0.048 | $0.193 | 4.0× | — | $0.084 | $0.061 | 262K |
| NVIDIA: Nemotron 3 Nano 30B A3B nvidia/nemotron-3-nano-30b-a3b | $0.050 | $0.200 | 4.0× | 40% | $0.087 | $0.064 | 262K |
| MythoMax 13B gryphe/mythomax-l2-13b | $0.080 | $0.110 | 1.4× | — | $0.087 | $0.083 | 8K |
| Microsoft: Phi 4 microsoft/phi-4 | $0.070 | $0.140 | 2.0× | — | $0.088 | $0.076 | 16K |
| Tencent: Hy3 preview tencent/hy3-preview | $0.063 | $0.210 | 3.3× | 67% | $0.100 | $0.076 | 262K |
| Reka Edge rekaai/reka-edge | $0.100 | $0.100 | 1.0× | — | $0.100 | $0.100 | 16K |
| Mistral: Ministral 3 3B 2512 mistralai/ministral-3b-2512 | $0.100 | $0.100 | 1.0× | 90% | $0.100 | $0.100 | 131K |
| Amazon: Nova Lite 1.0 amazon/nova-lite-v1 | $0.060 | $0.240 | 4.0× | — | $0.105 | $0.076 | 300K |
| Qwen: Qwen3.5-9B qwen/qwen3.5-9b | $0.100 | $0.150 | 1.5× | — | $0.112 | $0.105 | 262K |
| DeepSeek V4 Flash Latest ~deepseek/deepseek-v4-flash-latest | $0.090 | $0.180 | 2.0× | 80% | $0.113 | $0.098 | 1.0M |
| DeepSeek: DeepSeek V4 Flash 0731 deepseek/deepseek-v4-flash-0731 | $0.090 | $0.180 | 2.0× | 80% | $0.113 | $0.098 | 1.0M |
| Poolside: Laguna S 2.1 poolside/laguna-s-2.1 | $0.090 | $0.180 | 2.0× | 90% | $0.113 | $0.098 | 1.0M |
| Qwen: Qwen3.5-Flash qwen/qwen3.5-flash-02-23 | $0.065 | $0.260 | 4.0× | — | $0.114 | $0.083 | 1M |
| Meta: Llama 3.2 3B Instruct meta-llama/llama-3.2-3b-instruct | $0.050 | $0.330 | 6.6× | — | $0.120 | $0.075 | 131K |
| Qwen: Qwen3 Coder 30B A3B Instruct qwen/qwen3-coder-30b-a3b-instruct | $0.070 | $0.270 | 3.9× | — | $0.120 | $0.088 | 262K |
| ByteDance: UI-TARS 7B bytedance/ui-tars-1.5-7b | $0.100 | $0.200 | 2.0× | — | $0.125 | $0.109 | 128K |
| Reka Flash 3 rekaai/reka-flash-3 | $0.100 | $0.200 | 2.0× | — | $0.125 | $0.109 | 66K |
| Qwen: Qwen2.5 7B Instruct qwen/qwen-2.5-7b-instruct | $0.100 | $0.200 | 2.0× | — | $0.125 | $0.109 | 33K |
| Qwen: Qwen3 32B qwen/qwen3-32b | $0.080 | $0.280 | 3.5× | — | $0.130 | $0.098 | 131K |
| ByteDance Seed: Seed 1.6 Flash bytedance-seed/seed-1.6-flash | $0.075 | $0.300 | 4.0× | — | $0.131 | $0.095 | 262K |
| OpenAI: gpt-oss-safeguard-20b openai/gpt-oss-safeguard-20b | $0.075 | $0.300 | 4.0× | 50% | $0.131 | $0.095 | 131K |
| Mistral: Mistral Small 3.2 24B mistralai/mistral-small-3.2-24b-instruct | $0.094 | $0.250 | 2.7× | — | $0.133 | $0.108 | 256K |
| OpenAI: GPT-5 Nano openai/gpt-5-nano | $0.050 | $0.400 | 8.0× | 90% | $0.137 | $0.082 | 400K |
| Google: Gemma 4 26B A4B google/gemma-4-26b-a4b-it | $0.070 | $0.340 | 4.9× | — | $0.138 | $0.095 | 262K |
| Z.ai: GLM 4.7 Flash z-ai/glm-4.7-flash | $0.060 | $0.400 | 6.7× | 83% | $0.145 | $0.091 | 203K |
| StepFun: Step 3.5 Flash stepfun/step-3.5-flash | $0.100 | $0.300 | 3.0× | — | $0.150 | $0.118 | 262K |
| Mistral: Ministral 3 8B 2512 mistralai/ministral-8b-2512 | $0.150 | $0.150 | 1.0× | 90% | $0.150 | $0.150 | 262K |
| Mistral: Voxtral Small 24B 2507 mistralai/voxtral-small-24b-2507 | $0.100 | $0.300 | 3.0× | 90% | $0.150 | $0.118 | 32K |
| Meta: Llama 4 Scout meta-llama/llama-4-scout | $0.100 | $0.300 | 3.0× | — | $0.150 | $0.118 | 1.3M |
| Meta: Llama 3.3 70B Instruct meta-llama/llama-3.3-70b-instruct | $0.100 | $0.320 | 3.2× | — | $0.155 | $0.120 | 131K |
| Google: Gemma 4 31B google/gemma-4-31b-it | $0.100 | $0.340 | 3.4× | — | $0.160 | $0.122 | 262K |
| NVIDIA: Nemotron 3 Super nvidia/nemotron-3-super-120b-a12b | $0.085 | $0.400 | 4.7× | — | $0.164 | $0.114 | 1M |
| Google: Gemma 3 27B google/gemma-3-27b-it | $0.080 | $0.450 | 5.6× | 50% | $0.172 | $0.114 | 262K |
| ByteDance Seed: Seed-2.0-Mini bytedance-seed/seed-2.0-mini | $0.100 | $0.400 | 4.0× | — | $0.175 | $0.127 | 262K |
| Google: Gemini 2.5 Flash Lite google/gemini-2.5-flash-lite | $0.100 | $0.400 | 4.0× | 90% | $0.175 | $0.127 | 1.0M |
| OpenAI: GPT-4.1 Nano openai/gpt-4.1-nano | $0.100 | $0.400 | 4.0× | 75% | $0.175 | $0.127 | 1.0M |
| DeepSeek: DeepSeek V4 Flash 0423 deepseek/deepseek-v4-flash | $0.140 | $0.280 | 2.0× | 80% | $0.175 | $0.153 | 1.0M |
| Xiaomi: MiMo-V2.5 xiaomi/mimo-v2.5 | $0.140 | $0.280 | 2.0× | 98% | $0.175 | $0.153 | 1.1M |
| Meta: Llama Guard 4 12B meta-llama/llama-guard-4-12b | $0.180 | $0.180 | 1.0× | — | $0.180 | $0.180 | 1.0M |
| Qwen: Qwen3 VL 32B Instruct qwen/qwen3-vl-32b-instruct | $0.104 | $0.416 | 4.0× | — | $0.182 | $0.132 | 131K |
| Nous: Hermes 4 70B nousresearch/hermes-4-70b | $0.130 | $0.400 | 3.1× | — | $0.198 | $0.155 | 131K |
| Mistral: Ministral 3 14B 2512 mistralai/ministral-14b-2512 | $0.200 | $0.200 | 1.0× | 90% | $0.200 | $0.200 | 262K |
| Qwen: Qwen3 VL 8B Instruct qwen/qwen3-vl-8b-instruct | $0.117 | $0.455 | 3.9× | — | $0.202 | $0.148 | 262K |
| Qwen: Qwen3 8B qwen/qwen3-8b | $0.117 | $0.455 | 3.9× | — | $0.202 | $0.148 | 131K |
| inclusionAI: Ring-2.6-1T inclusionai/ring-2.6-1t | $0.075 | $0.625 | 8.3× | 80% | $0.212 | $0.125 | 262K |
| inclusionAI: Ling-2.6-1T inclusionai/ling-2.6-1t | $0.075 | $0.625 | 8.3× | 80% | $0.212 | $0.125 | 262K |
| Qwen: Qwen3 30B A3B qwen/qwen3-30b-a3b | $0.120 | $0.500 | 4.2× | — | $0.215 | $0.155 | 131K |
| OpenAI: GPT-5.6 Luna Pro openai/gpt-5.6-luna-pro | $0.100 | $0.600 | 6.0× | 90% | $0.225 | $0.145 | 1.1M |
| OpenAI: GPT-5.6 Luna openai/gpt-5.6-luna | $0.100 | $0.600 | 6.0× | 90% | $0.225 | $0.145 | 1.1M |
| Tencent: Hy3 tencent/hy3 | $0.132 | $0.528 | 4.0× | 75% | $0.231 | $0.168 | 262K |
| AllenAI: Olmo 3 32B Think allenai/olmo-3-32b-think | $0.150 | $0.500 | 3.3× | — | $0.237 | $0.182 | 66K |
| Tencent: Hunyuan A13B Instruct tencent/hunyuan-a13b-instruct | $0.140 | $0.570 | 4.1× | — | $0.248 | $0.179 | 131K |
| Qwen: Qwen3 235B A22B Instruct 2507 qwen/qwen3-235b-a22b-2507 | $0.150 | $0.598 | 4.0× | — | $0.262 | $0.190 | 262K |
| Kwaipilot: KAT-Coder-Air V2.5 kwaipilot/kat-coder-air-v2.5 | $0.150 | $0.600 | 4.0× | 80% | $0.262 | $0.191 | 256K |
| Mistral: Mistral Small 4 mistralai/mistral-small-2603 | $0.150 | $0.600 | 4.0× | 90% | $0.262 | $0.191 | 262K |
| Upstage: Solar Pro 3 upstage/solar-pro-3 | $0.150 | $0.600 | 4.0× | 90% | $0.262 | $0.191 | 128K |
| Qwen: Qwen3 VL 30B A3B Instruct qwen/qwen3-vl-30b-a3b-instruct | $0.150 | $0.600 | 4.0× | — | $0.262 | $0.191 | 262K |
| Cohere: Command R (08-2024) cohere/command-r-08-2024 | $0.150 | $0.600 | 4.0× | — | $0.262 | $0.191 | 128K |
| OpenAI: GPT-4o-mini openai/gpt-4o-mini | $0.150 | $0.600 | 4.0× | 50% | $0.262 | $0.191 | 128K |
| OpenAI: GPT-4o-mini (2024-07-18) openai/gpt-4o-mini-2024-07-18 | $0.150 | $0.600 | 4.0× | 50% | $0.262 | $0.191 | 128K |
| Qwen: Qwen3 Coder Next qwen/qwen3-coder-next | $0.120 | $0.800 | 6.7× | 42% | $0.290 | $0.182 | 262K |
| Mistral: Saba mistralai/mistral-saba | $0.200 | $0.600 | 3.0× | 90% | $0.300 | $0.236 | 33K |
| DeepSeek: DeepSeek V3.2 deepseek/deepseek-v3.2 | $0.269 | $0.400 | 1.5× | 50% | $0.302 | $0.281 | 164K |
| DeepSeek: DeepSeek V3.2 Exp deepseek/deepseek-v3.2-exp | $0.270 | $0.410 | 1.5× | — | $0.305 | $0.283 | 164K |
| Z.ai: GLM 4.5 Air z-ai/glm-4.5-air | $0.130 | $0.850 | 6.5× | 81% | $0.310 | $0.195 | 131K |
| TheDrummer: Rocinante 12B thedrummer/rocinante-12b | $0.250 | $0.500 | 2.0× | — | $0.313 | $0.273 | 66K |
| MiniMax: MiniMax M2.5 minimax/minimax-m2.5 | $0.150 | $0.900 | 6.0× | 67% | $0.337 | $0.218 | 205K |
| Qwen: Qwen3 Next 80B A3B Instruct qwen/qwen3-next-80b-a3b-instruct | $0.090 | $1.10 | 12.2× | — | $0.343 | $0.182 | 262K |
| TheDrummer: Cydonia 24B V4.1 thedrummer/cydonia-24b-v4.1 | $0.300 | $0.500 | 1.7× | 50% | $0.350 | $0.318 | 131K |
| Meta: Llama 4 Maverick meta-llama/llama-4-maverick | $0.200 | $0.800 | 4.0× | — | $0.350 | $0.255 | 1.0M |
| Qwen: Qwen3.6 35B A3B qwen/qwen3.6-35b-a3b | $0.140 | $1.00 | 7.1× | — | $0.355 | $0.218 | 262K |
| Qwen: Qwen3.5-35B-A3B qwen/qwen3.5-35b-a3b | $0.140 | $1.00 | 7.1× | — | $0.355 | $0.218 | 262K |
| Qwen2.5 72B Instruct qwen/qwen-2.5-72b-instruct | $0.360 | $0.400 | 1.1× | — | $0.370 | $0.364 | 33K |
| Inception: Mercury 2 inception/mercury-2 | $0.250 | $0.750 | 3.0× | 90% | $0.375 | $0.295 | 128K |
| Venice: Uncensored cognitivecomputations/dolphin-mistral-24b-venice-edition | $0.200 | $0.900 | 4.5× | — | $0.375 | $0.264 | 128K |
| Qwen: Qwen2.5 VL 72B Instruct qwen/qwen2.5-vl-72b-instruct | $0.250 | $0.750 | 3.0× | — | $0.375 | $0.295 | 128K |
| Arcee AI: Trinity Large Thinking arcee-ai/trinity-large-thinking | $0.220 | $0.850 | 3.9× | 73% | $0.378 | $0.277 | 262K |
| Qwen: Qwen3 Coder Flash qwen/qwen3-coder-flash | $0.195 | $0.975 | 5.0× | 80% | $0.390 | $0.266 | 1M |
| Qwen: Qwen Plus 0728 qwen/qwen-plus-2025-07-28 | $0.260 | $0.780 | 3.0× | — | $0.390 | $0.307 | 1M |
| Qwen: Qwen-Plus qwen/qwen-plus | $0.260 | $0.780 | 3.0× | 80% | $0.390 | $0.307 | 1M |
| Qwen: Qwen3 14B qwen/qwen3-14b | $0.227 | $0.910 | 4.0× | — | $0.398 | $0.290 | 131K |
| TheDrummer: UnslopNemo 12B thedrummer/unslopnemo-12b | $0.400 | $0.400 | 1.0× | — | $0.400 | $0.400 | 1.0M |
| Meta: Llama 3.1 70B Instruct meta-llama/llama-3.1-70b-instruct | $0.400 | $0.400 | 1.0× | — | $0.400 | $0.400 | 131K |
| Mistral: Mistral Small 3.1 24B mistralai/mistral-small-3.1-24b-instruct | $0.351 | $0.555 | 1.6× | — | $0.402 | $0.370 | 128K |
| Qwen: Qwen3 Next 80B A3B Thinking qwen/qwen3-next-80b-a3b-thinking | $0.150 | $1.20 | 8.0× | — | $0.412 | $0.245 | 262K |
| Qwen: Qwen3.6 Flash qwen/qwen3.6-flash | $0.188 | $1.13 | 6.0× | — | $0.422 | $0.273 | 1M |
| DeepSeek: DeepSeek V3.1 deepseek/deepseek-chat-v3.1 | $0.250 | $0.950 | 3.8× | 48% | $0.425 | $0.314 | 164K |
| MiniMax: MiniMax-01 minimax/minimax-01 | $0.200 | $1.10 | 5.5× | — | $0.425 | $0.282 | 1.0M |
| Nex AGI: Nex-N2-Pro nex-agi/nex-n2-pro | $0.250 | $1.00 | 4.0× | 90% | $0.438 | $0.318 | 262K |
| StepFun: Step 3.7 Flash stepfun/step-3.7-flash | $0.200 | $1.15 | 5.8× | 80% | $0.438 | $0.286 | 262K |
| MiniMax: MiniMax M2 minimax/minimax-m2 | $0.255 | $1.02 | 4.0× | — | $0.446 | $0.325 | 205K |
| Z.ai: GLM 4.6V z-ai/glm-4.6v | $0.300 | $0.900 | 3.0× | 82% | $0.450 | $0.355 | 131K |
| Mistral: Codestral 2508 mistralai/codestral-2508 | $0.300 | $0.900 | 3.0× | 90% | $0.450 | $0.355 | 256K |
| DeepSeek: DeepSeek V3 deepseek/deepseek-chat | $0.257 | $1.03 | 4.0× | — | $0.450 | $0.328 | 164K |
| DeepSeek: DeepSeek V3.1 Terminus deepseek/deepseek-v3.1-terminus | $0.270 | $1.00 | 3.7× | 50% | $0.453 | $0.336 | 164K |
| OpenAI: GPT-5.4 Nano openai/gpt-5.4-nano | $0.200 | $1.25 | 6.3× | 90% | $0.463 | $0.295 | 400K |
| MiniMax: MiniMax M2.7 minimax/minimax-m2.7 | $0.270 | $1.08 | 4.0× | 80% | $0.473 | $0.344 | 205K |
| Qwen: Qwen3 Coder 480B A35B qwen/qwen3-coder | $0.300 | $1.00 | 3.3× | 67% | $0.475 | $0.364 | 262K |
| DeepSeek: DeepSeek V3 0324 deepseek/deepseek-chat-v3-0324 | $0.270 | $1.12 | 4.1× | 50% | $0.483 | $0.347 | 164K |
| Perceptron: Perceptron Mk1 perceptron/perceptron-mk1 | $0.150 | $1.50 | 10.0× | — | $0.487 | $0.273 | 33K |
| Anthropic: Claude 3 Haiku anthropic/claude-3-haiku | $0.250 | $1.25 | 5.0× | 88% | $0.500 | $0.341 | 200K |
| ReMM SLERP 13B undi95/remm-slerp-l2-13b | $0.450 | $0.650 | 1.4× | — | $0.500 | $0.468 | 6K |
| Meituan: LongCat 2.0 meituan/longcat-2.0 | $0.300 | $1.20 | 4.0× | 98% | $0.525 | $0.382 | 1.0M |
| MiniMax: MiniMax M3 minimax/minimax-m3 | $0.300 | $1.20 | 4.0× | 80% | $0.525 | $0.382 | 1.0M |
| Kwaipilot: KAT-Coder-Pro V2 kwaipilot/kat-coder-pro-v2 | $0.300 | $1.20 | 4.0× | 80% | $0.525 | $0.382 | 262K |
| MiniMax: MiniMax M2-her minimax/minimax-m2-her | $0.300 | $1.20 | 4.0× | 90% | $0.525 | $0.382 | 66K |
| MiniMax: MiniMax M2.1 minimax/minimax-m2.1 | $0.300 | $1.20 | 4.0× | 90% | $0.525 | $0.382 | 205K |
| Qwen: Qwen3.5-27B qwen/qwen3.5-27b | $0.195 | $1.56 | 8.0× | — | $0.536 | $0.319 | 262K |
| DeepSeek: DeepSeek V4 Pro deepseek/deepseek-v4-pro | $0.435 | $0.870 | 2.0× | 99% | $0.544 | $0.475 | 1.0M |
| Xiaomi: MiMo-V2.5-Pro xiaomi/mimo-v2.5-pro | $0.435 | $0.870 | 2.0× | 99% | $0.544 | $0.475 | 1.1M |
| Qwen: Qwen3.7 Plus qwen/qwen3.7-plus | $0.320 | $1.28 | 4.0× | 80% | $0.560 | $0.407 | 1M |
| Google: Nano Banana 2 Lite (Gemini 3.1 Flash Lite Image) google/gemini-3.1-flash-lite-image | $0.250 | $1.50 | 6.0× | — | $0.563 | $0.364 | 66K |
| Google: Gemini 3.1 Flash Lite google/gemini-3.1-flash-lite | $0.250 | $1.50 | 6.0× | 90% | $0.563 | $0.364 | 1.0M |
| Google: Gemini 3.1 Flash Lite Preview google/gemini-3.1-flash-lite-preview | $0.250 | $1.50 | 6.0× | 90% | $0.563 | $0.364 | 1.0M |
| Mancer: Weaver (alpha) mancer/weaver | $0.500 | $0.750 | 1.5× | — | $0.563 | $0.523 | 8K |
| Qwen: Qwen3.5 Plus 2026-02-15 qwen/qwen3.5-plus-02-15 | $0.260 | $1.56 | 6.0× | — | $0.585 | $0.378 | 1M |
| Qwen: Qwen Plus 0728 (thinking) qwen/qwen-plus-2025-07-28:thinking | $0.400 | $1.20 | 3.0× | — | $0.600 | $0.473 | 1M |
| TheDrummer: Skyfall 36B V2 thedrummer/skyfall-36b-v2 | $0.550 | $0.800 | 1.5× | 55% | $0.613 | $0.573 | 33K |
| WizardLM-2 8x22B microsoft/wizardlm-2-8x22b | $0.620 | $0.620 | 1.0× | — | $0.620 | $0.620 | 66K |
| Baidu: ERNIE 4.5 VL 424B A47B baidu/ernie-4.5-vl-424b-a47b | $0.420 | $1.25 | 3.0× | — | $0.627 | $0.495 | 123K |
| Qwen: Qwen3 VL 235B A22B Instruct qwen/qwen3-vl-235b-a22b-instruct | $0.210 | $1.90 | 9.0× | 52% | $0.632 | $0.364 | 262K |
| Google: Gemma 2 27B google/gemma-2-27b-it | $0.650 | $0.650 | 1.0× | — | $0.650 | $0.650 | 8K |
| Qwen: Qwen3 VL 8B Thinking qwen/qwen3-vl-8b-thinking | $0.180 | $2.10 | 11.7× | — | $0.660 | $0.355 | 131K |
| Qwen: Qwen3.5 Plus 2026-04-20 qwen/qwen3.5-plus-20260420 | $0.300 | $1.80 | 6.0× | — | $0.675 | $0.436 | 1M |
| Thinking Machines: Inkling Small thinkingmachines/inkling-small | $0.500 | $1.20 | 2.4× | 80% | $0.675 | $0.564 | 524K |
| Sao10K: Llama 3.3 Euryale 70B sao10k/l3.3-euryale-70b | $0.650 | $0.750 | 1.2× | — | $0.675 | $0.659 | 131K |
| ByteDance Seed: Seed-2.0-Lite bytedance-seed/seed-2.0-lite | $0.250 | $2.00 | 8.0× | — | $0.688 | $0.409 | 262K |
| ByteDance Seed: Seed 1.6 bytedance-seed/seed-1.6 | $0.250 | $2.00 | 8.0× | — | $0.688 | $0.409 | 262K |
| OpenAI: GPT-5.1-Codex-Mini openai/gpt-5.1-codex-mini | $0.250 | $2.00 | 8.0× | 88% | $0.688 | $0.409 | 400K |
| OpenAI: GPT-5 Mini openai/gpt-5-mini | $0.250 | $2.00 | 8.0× | 90% | $0.688 | $0.409 | 400K |
| OpenAI: GPT-4.1 Mini openai/gpt-4.1-mini | $0.400 | $1.60 | 4.0× | 75% | $0.700 | $0.509 | 1.0M |
| Nous: Hermes 3 70B Instruct nousresearch/hermes-3-llama-3.1-70b | $0.700 | $0.700 | 1.0× | — | $0.700 | $0.700 | 131K |
| Qwen: Qwen3.5-122B-A10B qwen/qwen3.5-122b-a10b | $0.260 | $2.08 | 8.0× | — | $0.715 | $0.425 | 262K |
| Qwen: Qwen3.6 Plus qwen/qwen3.6-plus | $0.325 | $1.95 | 6.0× | — | $0.731 | $0.473 | 1M |
| Z.ai: GLM 4.7 z-ai/glm-4.7 | $0.400 | $1.75 | 4.4× | 80% | $0.738 | $0.523 | 205K |
| Qwen2.5 Coder 32B Instruct qwen/qwen-2.5-coder-32b-instruct | $0.660 | $1.00 | 1.5× | — | $0.745 | $0.691 | 33K |
| Qwen: Qwen3 235B A22B Thinking 2507 qwen/qwen3-235b-a22b-thinking-2507 | $0.230 | $2.30 | 10.0× | — | $0.747 | $0.418 | 262K |
| Mistral: Mistral Large 3 2512 mistralai/mistral-large-2512 | $0.500 | $1.50 | 3.0× | 90% | $0.750 | $0.591 | 262K |
| Qwen: Qwen3 VL 30B A3B Thinking qwen/qwen3-vl-30b-a3b-thinking | $0.200 | $2.40 | 12.0× | — | $0.750 | $0.400 | 262K |
| Qwen: Qwen3 30B A3B Thinking 2507 qwen/qwen3-30b-a3b-thinking-2507 | $0.200 | $2.40 | 12.0× | — | $0.750 | $0.400 | 82K |
| OpenAI: GPT-3.5 Turbo openai/gpt-3.5-turbo | $0.500 | $1.50 | 3.0× | — | $0.750 | $0.591 | 16K |
| Qwen: Qwen3 235B A22B qwen/qwen3-235b-a22b | $0.455 | $1.82 | 4.0× | — | $0.796 | $0.579 | 131K |
| DeepSeek: R1 Distill Llama 70B deepseek/deepseek-r1-distill-llama-70b | $0.800 | $0.800 | 1.0× | — | $0.800 | $0.800 | 8K |
| Mistral: Mistral Medium 3.1 mistralai/mistral-medium-3.1 | $0.400 | $2.00 | 5.0× | 90% | $0.800 | $0.545 | 131K |
| Mistral: Mistral Medium 3 mistralai/mistral-medium-3 | $0.400 | $2.00 | 5.0× | 90% | $0.800 | $0.545 | 131K |
| Qwen: Qwen3.6 27B qwen/qwen3.6-27b | $0.289 | $2.40 | 8.3× | — | $0.817 | $0.481 | 262K |
| Google: Gemini 3.5 Flash Lite google/gemini-3.5-flash-lite | $0.300 | $2.50 | 8.3× | 90% | $0.850 | $0.500 | 1.0M |
| Amazon: Nova 2 Lite amazon/nova-2-lite-v1 | $0.300 | $2.50 | 8.3× | — | $0.850 | $0.500 | 1M |
| Google: Nano Banana (Gemini 2.5 Flash Image) google/gemini-2.5-flash-image | $0.300 | $2.50 | 8.3× | 90% | $0.850 | $0.500 | 33K |
| Google: Gemini 2.5 Flash google/gemini-2.5-flash | $0.300 | $2.50 | 8.3× | 90% | $0.850 | $0.500 | 1.0M |
| Sao10K: Llama 3.1 Euryale 70B v2.2 sao10k/l3.1-euryale-70b | $0.850 | $0.850 | 1.0× | — | $0.850 | $0.850 | 131K |
| Arcee AI: Virtuoso Large arcee-ai/virtuoso-large | $0.750 | $1.20 | 1.6× | — | $0.863 | $0.791 | 131K |
| AionLabs: Aion-3.0-Mini aion-labs/aion-3.0-mini | $0.700 | $1.40 | 2.0× | 74% | $0.875 | $0.764 | 131K |
| Z.ai: GLM 4.6 z-ai/glm-4.6 | $0.500 | $2.00 | 4.0× | 80% | $0.875 | $0.636 | 205K |
| Qwen: Qwen3.5 397B A17B qwen/qwen3.5-397b-a17b | $0.390 | $2.34 | 6.0× | — | $0.877 | $0.567 | 262K |
| Z.ai: GLM 4.5V z-ai/glm-4.5v | $0.600 | $1.80 | 3.0× | 82% | $0.900 | $0.709 | 66K |
| Morph: Morph V3 Fast morph/morph-v3-fast | $0.800 | $1.20 | 1.5× | — | $0.900 | $0.836 | 82K |
| DeepSeek: R1 0528 deepseek/deepseek-r1-0528 | $0.500 | $2.15 | 4.3× | 30% | $0.913 | $0.650 | 164K |
| Relace: Relace Apply 3 relace/relace-apply-3 | $0.850 | $1.25 | 1.5× | — | $0.950 | $0.886 | 256K |
| MiniMax: MiniMax M1 minimax/minimax-m1 | $0.550 | $2.20 | 4.0× | — | $0.963 | $0.700 | 1M |
| AionLabs: Aion-2.0 aion-labs/aion-2.0 | $0.800 | $1.60 | 2.0× | 75% | $1.00 | $0.873 | 131K |
| Z.ai: GLM 4.5 z-ai/glm-4.5 | $0.600 | $2.20 | 3.7× | 82% | $1.00 | $0.745 | 131K |
| AionLabs: Aion-RP 1.0 (8B) aion-labs/aion-rp-llama-3.1-8b | $0.800 | $1.60 | 2.0× | — | $1.00 | $0.873 | 33K |
| Perplexity: Sonar perplexity/sonar | $1.00 | $1.00 | 1.0× | — | $1.00 | $1.00 | 127K |
| Nous: Hermes 3 405B Instruct nousresearch/hermes-3-llama-3.1-405b | $1.00 | $1.00 | 1.0× | — | $1.00 | $1.00 | 131K |
| MoonshotAI: Kimi K2 0711 moonshotai/kimi-k2 | $0.570 | $2.30 | 4.0× | — | $1.00 | $0.727 | 131K |
| OpenAI: GPT Audio Mini openai/gpt-audio-mini | $0.600 | $2.40 | 4.0× | — | $1.05 | $0.764 | 128K |
| MoonshotAI: Kimi K2.6 moonshotai/kimi-k2.6 | $0.589 | $2.48 | 4.2× | 83% | $1.06 | $0.761 | 262K |
| MoonshotAI: Kimi K2 Thinking moonshotai/kimi-k2-thinking | $0.600 | $2.50 | 4.2× | 75% | $1.07 | $0.773 | 262K |
| MoonshotAI: Kimi K2 0905 moonshotai/kimi-k2-0905 | $0.600 | $2.50 | 4.2× | — | $1.07 | $0.773 | 262K |
| Google: Nano Banana 2 (Gemini 3.1 Flash Image) google/gemini-3.1-flash-image | $0.500 | $3.00 | 6.0× | — | $1.13 | $0.727 | 131K |
| Google: Nano Banana 2 (Gemini 3.1 Flash Image Preview) google/gemini-3.1-flash-image-preview | $0.500 | $3.00 | 6.0× | — | $1.13 | $0.727 | 66K |
| Google: Gemini 3 Flash Preview google/gemini-3-flash-preview | $0.500 | $3.00 | 6.0× | 90% | $1.13 | $0.727 | 1.0M |
| MoonshotAI: Kimi K2.5 moonshotai/kimi-k2.5 | $0.570 | $2.85 | 5.0× | 83% | $1.14 | $0.777 | 262K |
| Morph: Morph V3 Large morph/morph-v3-large | $0.900 | $1.90 | 2.1× | — | $1.15 | $0.991 | 262K |
| DeepSeek: R1 deepseek/deepseek-r1 | $0.700 | $2.50 | 3.6× | — | $1.15 | $0.864 | 164K |
| Z.ai: GLM 5.2 z-ai/glm-5.2 | $0.760 | $2.42 | 3.2× | 82% | $1.18 | $0.911 | 1.0M |
| SpaceXAI: Grok Build 0.1 x-ai/grok-build-0.1 | $1.00 | $2.00 | 2.0× | 80% | $1.25 | $1.09 | 256K |
| Deep Cogito: Cogito v2.1 671B deepcogito/cogito-v2.1-671b | $1.25 | $1.25 | 1.0× | — | $1.25 | $1.25 | 128K |
| OpenAI: GPT-3.5 Turbo (older v0613) openai/gpt-3.5-turbo-0613 | $1.00 | $2.00 | 2.0× | — | $1.25 | $1.09 | 4K |
| Kwaipilot: KAT-Coder-Pro V2.5 kwaipilot/kat-coder-pro-v2.5 | $0.740 | $2.96 | 4.0× | 80% | $1.29 | $0.942 | 256K |
| Qwen: Qwen3 Coder Plus qwen/qwen3-coder-plus | $0.650 | $3.25 | 5.0× | 80% | $1.30 | $0.886 | 1M |
| NVIDIA: Nemotron 3 Ultra nvidia/nemotron-3-ultra-550b-a55b | $0.600 | $3.60 | 6.0× | 67% | $1.35 | $0.873 | 512K |
| Z.ai: GLM 5 z-ai/glm-5 | $0.950 | $2.55 | 2.7× | 79% | $1.35 | $1.10 | 205K |
| Amazon: Nova Pro 1.0 amazon/nova-pro-v1 | $0.800 | $3.20 | 4.0× | — | $1.40 | $1.02 | 300K |
| MoonshotAI: Kimi K2.7 Code moonshotai/kimi-k2.7-code | $0.730 | $3.50 | 4.8× | 79% | $1.42 | $0.982 | 262K |
| Z.ai: GLM 5.1 z-ai/glm-5.1 | $0.966 | $3.04 | 3.1× | 81% | $1.48 | $1.15 | 205K |
| Relace: Relace Search relace/relace-search | $1.00 | $3.00 | 3.0× | — | $1.50 | $1.18 | 256K |
| Nous: Hermes 4 405B nousresearch/hermes-4-405b | $1.00 | $3.00 | 3.0× | — | $1.50 | $1.18 | 131K |
| Qwen: Qwen3 Max Thinking qwen/qwen3-max-thinking | $0.780 | $3.90 | 5.0× | — | $1.56 | $1.06 | 262K |
| Qwen: Qwen3 Max qwen/qwen3-max | $0.780 | $3.90 | 5.0× | 80% | $1.56 | $1.06 | 262K |
| SpaceXAI: Grok 4.3 x-ai/grok-4.3 | $1.25 | $2.50 | 2.0× | 84% | $1.56 | $1.36 | 1M |
| SpaceXAI: Grok 4.20 Multi-Agent x-ai/grok-4.20-multi-agent | $1.25 | $2.50 | 2.0× | 84% | $1.56 | $1.36 | 2M |
| SpaceXAI: Grok 4.20 x-ai/grok-4.20 | $1.25 | $2.50 | 2.0× | 84% | $1.56 | $1.36 | 2M |
| OpenAI: GPT-3.5 Turbo Instruct openai/gpt-3.5-turbo-instruct | $1.50 | $2.00 | 1.3× | — | $1.63 | $1.55 | 4K |
| OpenAI GPT Mini Latest ~openai/gpt-mini-latest | $0.750 | $4.50 | 6.0× | 90% | $1.69 | $1.09 | 400K |
| OpenAI: GPT-5.4 Mini openai/gpt-5.4-mini | $0.750 | $4.50 | 6.0× | 90% | $1.69 | $1.09 | 400K |
| Qwen: Qwen3 VL 235B A22B Thinking qwen/qwen3-vl-235b-a22b-thinking | $0.980 | $3.95 | 4.0× | — | $1.72 | $1.25 | 131K |
| Thinking Machines: Inkling thinkingmachines/inkling | $1.00 | $4.05 | 4.0× | 83% | $1.76 | $1.28 | 1.0M |
| Z.ai: GLM 5V Turbo z-ai/glm-5v-turbo | $1.20 | $4.00 | 3.3× | 80% | $1.90 | $1.45 | 203K |
| Z.ai: GLM 5 Turbo z-ai/glm-5-turbo | $1.20 | $4.00 | 3.3× | 80% | $1.90 | $1.45 | 203K |
| OpenAI: o4 Mini High openai/o4-mini-high | $1.10 | $4.40 | 4.0× | 75% | $1.93 | $1.40 | 200K |
| OpenAI: o4 Mini openai/o4-mini | $1.10 | $4.40 | 4.0× | 75% | $1.93 | $1.40 | 200K |
| OpenAI: o3 Mini High openai/o3-mini-high | $1.10 | $4.40 | 4.0× | 50% | $1.93 | $1.40 | 200K |
| OpenAI: o3 Mini openai/o3-mini | $1.10 | $4.40 | 4.0× | 50% | $1.93 | $1.40 | 200K |
| Writer: Palmyra X5 writer/palmyra-x5 | $0.600 | $6.00 | 10.0× | — | $1.95 | $1.09 | 1.0M |
| Meta: Muse Spark 1.1 meta/muse-spark-1.1 | $1.25 | $4.25 | 3.4× | 88% | $2.00 | $1.52 | 1.0M |
| Anthropic Claude Haiku Latest ~anthropic/claude-haiku-latest | $1.00 | $5.00 | 5.0× | 90% | $2.00 | $1.36 | 200K |
| Anthropic: Claude Haiku 4.5 anthropic/claude-haiku-4.5 | $1.00 | $5.00 | 5.0× | 90% | $2.00 | $1.36 | 200K |
| Qwen: Qwen3.7 Max qwen/qwen3.7-max | $1.48 | $4.42 | 3.0× | 80% | $2.21 | $1.74 | 1M |
| OpenAI: GPT-5.6 Terra Pro openai/gpt-5.6-terra-pro | $1.00 | $6.00 | 6.0× | 90% | $2.25 | $1.45 | 1.1M |
| OpenAI: GPT-5.6 Terra openai/gpt-5.6-terra | $1.00 | $6.00 | 6.0× | 90% | $2.25 | $1.45 | 1.1M |
| Qwen: Qwen3.6 Max Preview qwen/qwen3.6-max-preview | $1.03 | $6.16 | 6.0× | — | $2.31 | $1.49 | 262K |
| OpenAI: GPT-5 Image Mini openai/gpt-5-image-mini | $2.50 | $2.00 | 0.8× | 90% | $2.38 | $2.45 | 400K |
| Qwen: Qwen3.8 Max qwen/qwen3.8-max | $2.00 | $6.00 | 3.0× | 88% | $3.00 | $2.36 | 1M |
| Google: Gemini 3.6 Flash google/gemini-3.6-flash | $1.50 | $7.50 | 5.0× | 90% | $3.00 | $2.05 | 1.0M |
| SpaceXAI: Grok 4.5 x-ai/grok-4.5 | $2.00 | $6.00 | 3.0× | 85% | $3.00 | $2.36 | 500K |
| xAI: Grok Latest ~x-ai/grok-latest | $2.00 | $6.00 | 3.0× | 85% | $3.00 | $2.36 | 500K |
| Mistral: Mistral Medium 3.5 mistralai/mistral-medium-3-5 | $1.50 | $7.50 | 5.0× | — | $3.00 | $2.05 | 262K |
| Google Gemini Flash Latest ~google/gemini-flash-latest | $1.50 | $7.50 | 5.0× | 90% | $3.00 | $2.05 | 1.0M |
| Mistral Large 2407 mistralai/mistral-large-2407 | $2.00 | $6.00 | 3.0× | 90% | $3.00 | $2.36 | 131K |
| Mistral: Mixtral 8x22B Instruct mistralai/mixtral-8x22b-instruct | $2.00 | $6.00 | 3.0× | 90% | $3.00 | $2.36 | 66K |
| Mistral Large mistralai/mistral-large | $2.00 | $6.00 | 3.0× | 90% | $3.00 | $2.36 | 128K |
| OpenAI: GPT-3.5 Turbo 16k openai/gpt-3.5-turbo-16k | $3.00 | $4.00 | 1.3× | — | $3.25 | $3.09 | 16K |
| Google: Gemini 3.5 Flash google/gemini-3.5-flash | $1.50 | $9.00 | 6.0× | 90% | $3.38 | $2.18 | 1.0M |
| OpenAI: GPT-5.1-Codex-Max openai/gpt-5.1-codex-max | $1.25 | $10.00 | 8.0× | 90% | $3.44 | $2.05 | 400K |
| OpenAI: GPT-5.1 openai/gpt-5.1 | $1.25 | $10.00 | 8.0× | 90% | $3.44 | $2.05 | 400K |
| OpenAI: GPT-5.1-Codex openai/gpt-5.1-codex | $1.25 | $10.00 | 8.0× | 90% | $3.44 | $2.05 | 400K |
| OpenAI: GPT-5 openai/gpt-5 | $1.25 | $10.00 | 8.0× | 90% | $3.44 | $2.05 | 400K |
| Google: Gemini 2.5 Pro google/gemini-2.5-pro | $1.25 | $10.00 | 8.0× | 90% | $3.44 | $2.05 | 1.0M |
| Google: Gemini 2.5 Pro Preview 06-05 google/gemini-2.5-pro-preview | $1.25 | $10.00 | 8.0× | 90% | $3.44 | $2.05 | 1.0M |
| Google: Gemini 2.5 Pro Preview 05-06 google/gemini-2.5-pro-preview-05-06 | $1.25 | $10.00 | 8.0× | 90% | $3.44 | $2.05 | 1.0M |
| AI21: Jamba Large 1.7 ai21/jamba-large-1.7 | $2.00 | $8.00 | 4.0× | — | $3.50 | $2.55 | 256K |
| OpenAI: o3 openai/o3 | $2.00 | $8.00 | 4.0× | 75% | $3.50 | $2.55 | 200K |
| OpenAI: GPT-4.1 openai/gpt-4.1 | $2.00 | $8.00 | 4.0× | 75% | $3.50 | $2.55 | 1.0M |
| Perplexity: Sonar Reasoning Pro perplexity/sonar-reasoning-pro | $2.00 | $8.00 | 4.0× | — | $3.50 | $2.55 | 128K |
| Perplexity: Sonar Deep Research perplexity/sonar-deep-research | $2.00 | $8.00 | 4.0× | — | $3.50 | $2.55 | 128K |
| Magnum v4 72B anthracite-org/magnum-v4-72b | $3.00 | $5.00 | 1.7× | — | $3.50 | $3.18 | 16K |
| AionLabs: Aion-3.0 aion-labs/aion-3.0 | $3.00 | $6.00 | 2.0× | 75% | $3.75 | $3.27 | 131K |
| Anthropic: Claude Sonnet 5 anthropic/claude-sonnet-5 | $2.00 | $10.00 | 5.0× | 90% | $4.00 | $2.73 | 1M |
| Anthropic Claude Sonnet Latest ~anthropic/claude-sonnet-latest | $2.00 | $10.00 | 5.0× | 90% | $4.00 | $2.73 | 1M |
| OpenAI: GPT Audio openai/gpt-audio | $2.50 | $10.00 | 4.0× | — | $4.38 | $3.18 | 128K |
| Cohere: Command A cohere/command-a | $2.50 | $10.00 | 4.0× | — | $4.38 | $3.18 | 256K |
| OpenAI: GPT-4o (2024-11-20) openai/gpt-4o-2024-11-20 | $2.50 | $10.00 | 4.0× | 50% | $4.38 | $3.18 | 128K |
| Cohere: Command R+ (08-2024) cohere/command-r-plus-08-2024 | $2.50 | $10.00 | 4.0× | — | $4.38 | $3.18 | 128K |
| OpenAI: GPT-4o (2024-08-06) openai/gpt-4o-2024-08-06 | $2.50 | $10.00 | 4.0× | 50% | $4.38 | $3.18 | 128K |
| OpenAI: GPT-4o openai/gpt-4o | $2.50 | $10.00 | 4.0× | 50% | $4.38 | $3.18 | 128K |
| Google: Nano Banana Pro (Gemini 3 Pro Image) google/gemini-3-pro-image | $2.00 | $12.00 | 6.0× | 90% | $4.50 | $2.91 | 131K |
| Google Gemini Pro Latest ~google/gemini-pro-latest | $2.00 | $12.00 | 6.0× | 90% | $4.50 | $2.91 | 1.0M |
| Google: Gemini 3.1 Pro Preview Custom Tools google/gemini-3.1-pro-preview-customtools | $2.00 | $12.00 | 6.0× | 90% | $4.50 | $2.91 | 1.0M |
| Google: Gemini 3.1 Pro Preview google/gemini-3.1-pro-preview | $2.00 | $12.00 | 6.0× | 90% | $4.50 | $2.91 | 1.0M |
| Google: Nano Banana Pro (Gemini 3 Pro Image Preview) google/gemini-3-pro-image-preview | $2.00 | $12.00 | 6.0× | 90% | $4.50 | $2.91 | 66K |
| OpenAI: GPT-5.3 Chat openai/gpt-5.3-chat | $1.75 | $14.00 | 8.0× | 90% | $4.81 | $2.86 | 128K |
| OpenAI: GPT-5.3-Codex openai/gpt-5.3-codex | $1.75 | $14.00 | 8.0× | 90% | $4.81 | $2.86 | 400K |
| OpenAI: GPT-5.2-Codex openai/gpt-5.2-codex | $1.75 | $14.00 | 8.0× | 90% | $4.81 | $2.86 | 400K |
| OpenAI: GPT-5.2 Chat openai/gpt-5.2-chat | $1.75 | $14.00 | 8.0× | 90% | $4.81 | $2.86 | 128K |
| OpenAI: GPT-5.2 openai/gpt-5.2 | $1.75 | $14.00 | 8.0× | 90% | $4.81 | $2.86 | 400K |
| Amazon: Nova Premier 1.0 amazon/nova-premier-v1 | $2.50 | $12.50 | 5.0× | 75% | $5.00 | $3.41 | 1M |
| OpenAI: GPT-5.4 openai/gpt-5.4 | $2.50 | $15.00 | 6.0× | 90% | $5.63 | $3.64 | 1.1M |
| MoonshotAI Kimi Latest ~moonshotai/kimi-latest | $2.90 | $14.00 | 4.8× | 90% | $5.68 | $3.91 | 1.0M |
| MoonshotAI: Kimi K3 moonshotai/kimi-k3 | $3.00 | $15.00 | 5.0× | 90% | $6.00 | $4.09 | 1.0M |
| Anthropic: Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 | $3.00 | $15.00 | 5.0× | 90% | $6.00 | $4.09 | 1M |
| Perplexity: Sonar Pro Search perplexity/sonar-pro-search | $3.00 | $15.00 | 5.0× | — | $6.00 | $4.09 | 200K |
| Anthropic: Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 | $3.00 | $15.00 | 5.0× | 90% | $6.00 | $4.09 | 1M |
| Anthropic: Claude Sonnet 4 anthropic/claude-sonnet-4 | $3.00 | $15.00 | 5.0× | 90% | $6.00 | $4.09 | 1M |
| Perplexity: Sonar Pro perplexity/sonar-pro | $3.00 | $15.00 | 5.0× | — | $6.00 | $4.09 | 200K |
| OpenAI: GPT-4o (2024-05-13) openai/gpt-4o-2024-05-13 | $5.00 | $15.00 | 3.0× | — | $7.50 | $5.91 | 128K |
| OpenAI: GPT-5.4 Image 2 openai/gpt-5.4-image-2 | $8.00 | $15.00 | 1.9× | 75% | $9.75 | $8.64 | 272K |
| Claude Opus 5 anthropic/claude-opus-5 | $5.00 | $25.00 | 5.0× | 90% | $10.00 | $6.82 | 1M |
| Anthropic: Claude Opus 4.8 anthropic/claude-opus-4.8 | $5.00 | $25.00 | 5.0× | 90% | $10.00 | $6.82 | 1M |
| Anthropic: Claude Opus Latest ~anthropic/claude-opus-latest | $5.00 | $25.00 | 5.0× | 90% | $10.00 | $6.82 | 1M |
| Anthropic: Claude Opus 4.7 anthropic/claude-opus-4.7 | $5.00 | $25.00 | 5.0× | 90% | $10.00 | $6.82 | 1M |
| Anthropic: Claude Opus 4.6 anthropic/claude-opus-4.6 | $5.00 | $25.00 | 5.0× | 90% | $10.00 | $6.82 | 1M |
| Anthropic: Claude Opus 4.5 anthropic/claude-opus-4.5 | $5.00 | $25.00 | 5.0× | 90% | $10.00 | $6.82 | 200K |
| OpenAI: GPT-5 Image openai/gpt-5-image | $10.00 | $10.00 | 1.0× | 88% | $10.00 | $10.00 | 400K |
| OpenAI: GPT-5.6 Sol Pro openai/gpt-5.6-sol-pro | $5.00 | $30.00 | 6.0× | 90% | $11.25 | $7.27 | 1.1M |
| OpenAI: GPT-5.6 Sol openai/gpt-5.6-sol | $5.00 | $30.00 | 6.0× | 90% | $11.25 | $7.27 | 1.1M |
| Sakana: Fugu Ultra sakana/fugu-ultra | $5.00 | $30.00 | 6.0× | 90% | $11.25 | $7.27 | 1M |
| OpenAI: GPT Chat Latest openai/gpt-chat-latest | $5.00 | $30.00 | 6.0× | 90% | $11.25 | $7.27 | 400K |
| OpenAI GPT Latest ~openai/gpt-latest | $5.00 | $30.00 | 6.0× | 90% | $11.25 | $7.27 | 1.1M |
| OpenAI: GPT-5.5 openai/gpt-5.5 | $5.00 | $30.00 | 6.0× | 90% | $11.25 | $7.27 | 1.1M |
| OpenAI: GPT-4 Turbo openai/gpt-4-turbo | $10.00 | $30.00 | 3.0× | — | $15.00 | $11.82 | 128K |
| OpenAI: GPT-4 Turbo Preview openai/gpt-4-turbo-preview | $10.00 | $30.00 | 3.0× | — | $15.00 | $11.82 | 128K |
| Claude Opus 5 (Fast) anthropic/claude-opus-5-fast | $10.00 | $50.00 | 5.0× | 90% | $20.00 | $13.64 | 1M |
| Anthropic: Claude Fable Latest ~anthropic/claude-fable-latest | $10.00 | $50.00 | 5.0× | 90% | $20.00 | $13.64 | 1M |
| Anthropic: Claude Fable 5 anthropic/claude-fable-5 | $10.00 | $50.00 | 5.0× | 90% | $20.00 | $13.64 | 1M |
| Anthropic: Claude Opus 4.8 (Fast) anthropic/claude-opus-4.8-fast | $10.00 | $50.00 | 5.0× | 90% | $20.00 | $13.64 | 1M |
| OpenAI: o1 openai/o1 | $15.00 | $60.00 | 4.0× | 50% | $26.25 | $19.09 | 200K |
| Anthropic: Claude Opus 4.1 anthropic/claude-opus-4.1 | $15.00 | $75.00 | 5.0× | 90% | $30.00 | $20.45 | 200K |
| Anthropic: Claude Opus 4 anthropic/claude-opus-4 | $15.00 | $75.00 | 5.0× | 90% | $30.00 | $20.45 | 200K |
| OpenAI: o3 Pro openai/o3-pro | $20.00 | $80.00 | 4.0× | — | $35.00 | $25.45 | 200K |
| OpenAI: GPT-4 openai/gpt-4 | $30.00 | $60.00 | 2.0× | — | $37.50 | $32.73 | 8K |
| OpenAI: GPT-5 Pro openai/gpt-5-pro | $15.00 | $120 | 8.0× | — | $41.25 | $24.55 | 400K |
| OpenAI: GPT-5.2 Pro openai/gpt-5.2-pro | $21.00 | $168 | 8.0× | — | $57.75 | $34.36 | 400K |
| Anthropic: Claude Opus 4.7 (Fast) anthropic/claude-opus-4.7-fast | $30.00 | $150 | 5.0× | 90% | $60.00 | $40.91 | 1M |
| OpenAI: GPT-5.5 Pro openai/gpt-5.5-pro | $30.00 | $180 | 6.0× | — | $67.50 | $43.64 | 1.1M |
| OpenAI: GPT-5.4 Pro openai/gpt-5.4-pro | $30.00 | $180 | 6.0× | — | $67.50 | $43.64 | 1.1M |
| OpenAI: o1-pro openai/o1-pro | $150 | $600 | 4.0× | — | $263 | $191 | 200K |
What this table is, and what it is not.
These are published list prices as the upstream catalogue reports them. They are not your negotiated rate, not your effective rate once caching and batch discounts land, and not a measurement of what any task costs you — token volume per task usually moves your bill more than unit price does. Use this to shortlist and to sanity-check an invoice. To find out what you are actually spending, you have to look at your own usage data. That is what the free teardown is for.