| # | Model | Provider | Tokens | Requests | Avg Cost | Avg Latency |
|---|---|---|---|---|---|---|
| 1 | deepseek/deepseek-v4.1-flash | openrouter | 14.2B | 114.9K | $0.0022 | 10896ms |
| 2 | glm-5.3 | zai | 571.3M | 12.0K | $0.0200 | 15698ms |
| 3 | gpt-5.6-luna | openai | 164.6M | 11.8K | $0.0015 | 7940ms |
| 4 | gemini-2.5-flash | 64.5M | 14.8K | $0.0013 | 6150ms | |
| 5 | gemini-3.7-flash | 62.7M | 2.8K | $0.0087 | 4609ms | |
| 6 | gpt-5.4-mini | openai | 59.5M | 14.4K | $0.0028 | 1535ms |
| 7 | openrouter/moonshotai/kimi-k3 | openrouter | 54.3M | 935 | $0.0340 | 20864ms |
| 8 | glm-5.2 | zai | 44.6M | 1.4K | $0.0141 | 13581ms |
| 9 | gpt-5.6-terra | openai | 17.7M | 867 | $0.0143 | 5010ms |
| 10 | deepseek/deepseek-v4-pro-0813 | openrouter | 17.5M | 491 | $0.0044 | 11106ms |
| 11 | google/gemini-2.5-flash-lite | 16.0M | 3.2K | $0.0004 | 1303ms | |
| 12 | glm-5.1 | zai | 15.7M | 3.1K | $0.0073 | 5703ms |
| 13 | gemini-3.1-pro-preview | 15.2M | 1.1K | $0.0091 | 9490ms | |
| 14 | jev-1.13.0 | typesafe | 12.4M | 1.5K | $0.0004 | 931ms |
| 15 | openrouter/openai/gpt-5.6-luna | openrouter | 10.8M | 2.4K | $0.0015 | 11172ms |
| 16 | qwen/qwen-2.5-7b-instruct | openrouter | 9.3M | 23.2K | $0.0001 | 4427ms |
| 17 | zai/glm-5.2 | zai | 7.1M | 224 | $0.0133 | 11931ms |
| 18 | ibm-granite/granite-4.0-h-micro | openrouter | 4.1M | 10.6K | $0.0000 | 7066ms |
| 19 | google/gemma-3-4b-it | openrouter | 3.8M | 10.5K | $0.0000 | 6640ms |
| 20 | google/gemma-3-12b-it | openrouter | 3.7M | 10.5K | $0.0000 | 5164ms |
| 21 | gpt-5-search-api | openai | 3.1M | 230 | $0.0172 | 5758ms |
| 22 | meta-llama/llama-3.2-3b-instruct | openrouter | 2.6M | 8.0K | $0.0000 | 1964ms |
| 23 | gpt-4.1-mini | openai | 2.5M | 1.1K | $0.0005 | 900ms |
| 24 | gpt-4o-mini | openai | 2.2M | 2.0K | $0.0001 | 1301ms |
| 25 | accounts/fireworks/models/deepseek-v4-flash-0731 | fireworks | 2.1M | 265 | $0.0004 | 4575ms |
| 26 | gpt-5-mini | openai | 1.9M | 797 | $0.0012 | 4290ms |
| 27 | google/gemini-2.5-flash | 1.7M | 214 | $0.0014 | 2181ms | |
| 28 | meta-llama/llama-3.2-1b-instruct | openrouter | 1.5M | 6.0K | $0.0000 | 1946ms |
| 29 | fireworks/qwen3p8-max | fireworks | 1.2M | 1.1K | $0.0046 | 7392ms |
| 30 | deepseek/deepseek-v4-flash | openrouter | 726.0K | 56 | $0.0005 | 9297ms |
| 31 | gpt-5.5 | openai | 709.9K | 735 | $0.0106 | 3205ms |
| 32 | codestral-latest | mistral | 463.9K | 1.1K | $0.0002 | 2885ms |
| 33 | gpt-5 | openai | 389.6K | 696 | $0.0006 | 1546ms |
| 34 | gpt-5.4-nano | openai | 339.8K | 571 | $0.0001 | 1305ms |
| 35 | openrouter/z-ai/glm-5.3 | openrouter | 331.8K | 81 | $0.0041 | 35139ms |
| 36 | gpt-5.4 | openai | 328.1K | 105 | $0.0323 | 20267ms |
| 37 | meta-llama/llama-3.1-8b-instruct | openrouter | 290.3K | 1.9K | $0.0000 | 1676ms |
| 38 | qwen/qwen3-max | openrouter | 277.9K | 90 | $0.0100 | 42121ms |
| 39 | gemini-2.5-flash-lite | 253.3K | 816 | $0.0000 | 613ms | |
| 40 | gpt-5.6-sol | openai | 248.5K | 201 | $0.0075 | 2879ms |
| 41 | openai/gpt-5.6-luna | openai | 239.9K | 489 | $0.0001 | 1696ms |
| 42 | openrouter/anthropic/claude-sonnet-5 | openrouter | 223.0K | 25 | $0.0269 | 7597ms |
| 43 | gemini-3.5-flash | 218.8K | 39 | $0.0076 | 10781ms | |
| 44 | gpt-4.1-nano | openai | 130.8K | 61 | $0.0001 | 1469ms |
| 45 | mistralai/mistral-large | openrouter | 119.0K | 225 | $0.0012 | 2087ms |
| 46 | openrouter/z-ai/glm-5.2 | openrouter | 89.8K | 14 | $0.0050 | 18557ms |
| 47 | gemini-3.5-flash-lite | 76.3K | 61 | $0.0004 | 1400ms | |
| 48 | google/gemini-3.1-flash-lite | 62.2K | 27 | $0.0006 | 1619ms | |
| 49 | glm-4.5 | cache | 53.8K | 674 | $0.0000 | 976ms |
| 50 | openrouter/google/gemini-3.1-pro-preview | openrouter | 48.5K | 1 | $0.1166 | 24976ms |
| 51 | groq/openai/gpt-oss-120b | groq | 45.1K | 34 | $0.0002 | 1066ms |
| 52 | moonshotai/kimi-k2.5 | openrouter | 43.2K | 5 | $0.0190 | 78788ms |
| 53 | gemini-3.1-flash-lite | 40.5K | 36 | $0.0003 | 1453ms | |
| 54 | anthropic/claude-haiku-4-5 | openrouter | 36.3K | 13 | $0.0033 | 2141ms |
| 55 | openrouter/anthropic/claude-opus-5 | openrouter | 31.4K | 6 | $0.0358 | 4010ms |
| 56 | fireworks/deepseek-v4-flash-0731 | fireworks | 20.1K | 336 | $0.0000 | 1044ms |
| 57 | gpt-4.1 | openai | 19.4K | 3 | $0.0148 | 3981ms |
| 58 | openai/gpt-5.4 | openai | 17.9K | 96 | $0.0027 | 2643ms |
| 59 | codestral-2508 | cache | 13.1K | 685 | $0.0000 | 495ms |
| 60 | kimi-k2.7-code | cache | 12.4K | 229 | $0.0000 | 313ms |
| 61 | openai/gpt-4o-mini | openai | 10.3K | 287 | $0.0000 | 1274ms |
| 62 | gemini-2.5-pro | cache | 9.6K | 686 | $0.0000 | 865ms |
| 63 | openrouter/google/gemini-2.5-flash-lite | openrouter | 7.7K | 2 | $0.0004 | 5543ms |
| 64 | openai/gpt-chat-latest | cache | 7.3K | 281 | $0.0001 | 630ms |
| 65 | google/gemini-3.5-flash-lite | 6.0K | 2 | $0.0010 | 1407ms | |
| 66 | openrouter/moonshotai/kimi-k2.7-code | openrouter | 3.1K | 57 | $0.0001 | 2791ms |
| 67 | glm-5-turbo | zai | 2.8K | 1 | $0.0112 | 46824ms |
| 68 | openai/gpt-6-astra-pro | openrouter | 1.5K | 1 | $0.0181 | 6991ms |
| 69 | qwen/qwen3.7-plus | openrouter | 1.0K | 3 | $0.0004 | 5040ms |
| 70 | gpt-5-nano | openai | 868 | 6 | $0.0000 | 2129ms |
| 71 | openrouter/z-ai/glm-4.5 | openrouter | 690 | 5 | $0.0003 | 8755ms |
| 72 | gemini-3.6-flash | 556 | 6 | $0.0002 | 4616ms | |
| 73 | fireworks/deepseek-v4-pro-0813 | fireworks | 480 | 7 | $0.0003 | 2556ms |
| 74 | gemini-3-flash-preview | 461 | 4 | $0.0002 | 2645ms | |
| 75 | z-ai/glm-5.3 | zai | 375 | 2 | $0.0008 | 6470ms |
| 76 | google/gemini-2.5-flash-preview-tts | 346 | 7 | $0.0005 | 3051ms | |
| 77 | openai/gpt-5 | cache | 318 | 2 | $0.0008 | 2317ms |
| 78 | tool/web_fetch | tangle | 245 | 4 | $0.0000 | 2651ms |
| 79 | openai/gpt-5-mini | openai | 230 | 4 | $0.0001 | 2155ms |
| 80 | zai/glm-5.3 | zai | 194 | 1 | $0.0008 | 6533ms |
| 81 | qwen/qwen3-8b | openrouter | 162 | 1 | $0.0001 | 2715ms |
| 82 | search/searxng | searxng | 154 | 13 | $0.0000 | 4102ms |
| 83 | openai/gpt-5-nano | openai | 146 | 1 | $0.0001 | 3798ms |
| 84 | z-ai/glm-5 | zai | 136 | 1 | $0.0003 | 4414ms |
| 85 | deepseek/deepseek-v4-flash-0731 | openrouter | 115 | 1 | $0.0000 | 2320ms |
| 86 | openai/gpt-5.5 | cache | 80 | 2 | $0.0003 | 986ms |
| 87 | openai/gpt-4.1-mini | cache | 46 | 2 | $0.0000 | 852ms |
| 88 | qwen/qwen3-30b-a3b-instruct-2507 | openrouter | 22 | 1 | $0.0000 | 2268ms |
| 89 | openai/gpt-5.6-sol | openai | 15 | 1 | $0.0002 | 1532ms |
Request Activity
Models ranked by routed activity across operators
Quality Scores
Community ratings and evaluation signals per model
Cost Efficiency
Best value models comparing price, speed, and quality