Leaderboard

Best models, ranked.

Intelligence Index vs. price

Each point is a model priced under $10/1M input tokens, colored by creator — hover a point for details. Source: Artificial Analysis. Pricier outlier models (e.g. o1 pro) are excluded here to keep the axis readable; the table below has every model.

015304560$0.00$2.88$5.75$8.62$11.50Claude 4.5 Haiku (Non-reasoning) — 23.7 — $2.00/MClaude Opus 4.5 (Non-reasoning) — 34.7 — $10.00/MClaude Opus 4.6 (Non-reasoning, High Effort) — 37.8 — $10.00/MClaude Opus 4.7 (Adaptive Reasoning, Max Effort) — 53.5 — $10.00/MClaude Opus 4.8 (Adaptive Reasoning, Max Effort) — 55.7 — $10.00/MClaude 4.5 Sonnet (Non-reasoning) — 29.3 — $6.00/MClaude Sonnet 4.6 (Non-reasoning, High Effort) — 35.9 — $6.00/MClaude Sonnet 5 (Adaptive Reasoning, Max Effort) — 53.4 — $4.00/MMiniMax-M2.7 — 38.1 — $0.52/MMiniMax-M3 — 44.4 — $0.52/MHermes 3 - Llama-3.1 70B — 5.1 — $0.70/MQwen2.5 Instruct 72B — 9.6 — $0.47/MQwen3 14B (Non-reasoning) — 7.0 — $0.61/MQwen3 235B A22B 2507 Instruct — 18.2 — $1.22/MQwen3 235B A22B 2507 (Reasoning) — 19.6 — $2.62/MQwen3 30B A3B (Non-reasoning) — 6.8 — $0.35/MQwen3 32B (Non-reasoning) — 8.6 — $1.22/MQwen3 Coder 480B A35B Instruct — 18.0 — $3.00/MQwen3 Max — 24.0 — $2.40/MQwen3 Next 80B A3B Instruct — 13.7 — $0.88/MQwen3 VL 235B A22B Instruct — 14.3 — $1.22/MQwen3 VL 30B A3B Instruct — 10.0 — $0.35/MQwen3.5 122B A10B (Reasoning) — 32.3 — $1.10/MQwen3.5 27B (Reasoning) — 33.8 — $0.82/MQwen3.5 35B A3B (Reasoning) — 29.3 — $0.69/MQwen3.5 397B A17B (Reasoning) — 33.7 — $1.35/MQwen3.5 9B (Reasoning) — 21.4 — $0.11/MQwen3.6 27B (Reasoning) — 37.1 — $1.35/MQwen3.6 35B A3B (Reasoning) — 31.6 — $0.56/MQwen3.7 Max — 46.0 — $3.75/MMiMo-V2.5 — 37.2 — $0.18/MMiMo-V2.5-Pro — 42.2 — $0.54/MDeepSeek R1 0528 (May '25) — 20.1 — $2.06/MDeepSeek V3 (Dec '24) — 14.2 — $0.52/MDeepSeek V3 0324 — 15.4 — $1.21/MDeepSeek V3.1 (Non-reasoning) — 21.0 — $0.84/MDeepSeek V3.1 Terminus (Non-reasoning) — 21.4 — $0.45/MDeepSeek V3.2 (Non-reasoning) — 24.7 — $0.32/MDeepSeek V4 Flash (Reasoning, Max Effort) — 40.3 — $0.18/MDeepSeek V4 Pro (Reasoning, Max Effort) — 44.3 — $0.54/MGemini 2.5 Flash (Non-reasoning) — 14.1 — $0.85/MGemini 2.5 Pro — 25.8 — $3.44/MGemini 3.1 Flash-Lite — 25.0 — $0.56/MGemini 3.1 Pro Preview — 46.5 — $4.50/MGemini 3.5 Flash (high) — 50.2 — $3.38/MGemma 3 12B Instruct — 5.5 — $0.00/MGemma 3 27B Instruct — 7.4 — $0.00/MGemma 3 4B Instruct — 1.1 — $0.00/MGemma 4 26B A4B (Reasoning) — 25.7 — $0.20/MGemma 4 31B (Reasoning) — 29.4 — $0.00/MLlama 3.3 Instruct 70B — 9.4 — $0.61/MLlama 4 Maverick — 14.3 — $0.47/MLlama 4 Scout — 10.0 — $0.29/MLlama 3.1 Instruct 70B — 6.8 — $0.56/MLlama 3.1 Instruct 8B — 7.6 — $0.08/MPhi-4 — 4.9 — $0.22/MMistral Small 3.2 — 10.6 — $0.15/MKimi K2.5 (Reasoning) — 38.1 — $1.20/MKimi K2.6 — 44.2 — $1.71/MKimi K2.7 Code — 41.9 — $1.71/MNVIDIA Nemotron 3 Super 120B A12B (Reasoning) — 25.4 — $0.38/MNemotron 3 Ultra 550B A55B (Reasoning) — 37.8 — $1.18/MNVIDIA Nemotron 3 Nano 30B A3B (Non-reasoning) — 7.4 — $0.09/Mgpt-oss-120b (high) — 23.8 — $0.26/Mgpt-oss-20b (high) — 14.9 — $0.09/MStep 3.7 Flash — 30.3 — $0.44/MHy3-preview (Reasoning) — 33.6 — $0.20/MGLM-4.6 (Non-reasoning) — 23.0 — $0.98/MGLM-4.7 (Reasoning) — 33.7 — $1.00/MGLM-4.7-Flash (Reasoning) — 22.9 — $0.15/MGLM-5 (Reasoning) — 39.5 — $1.55/MGLM-5.1 (Reasoning) — 40.2 — $2.15/MGLM-5.2 (max) — 51.1 — $2.15/MDeepSeek R1 Distill Llama 70B — 9.9 — $0.79/MMiniMax-M2.5 — 33.7 — $0.52/MMinistral 3 14B — 11.1 — $0.20/MNemotron 3 Nano Omni 30B A3B Reasoning — 14.9 — $0.13/MNVIDIA Nemotron Nano 12B v2 VL (Non-reasoning) — 4.6 — $0.30/MQwen3.7 Plus — 39.0 — $0.70/MQwen3.6 Max Preview — 40.0 — $2.92/MQwen3.6 Plus — 39.6 — $1.12/MKAT Coder Pro V2 — 35.4 — $0.52/MKimi K2 Thinking — 32.7 — $1.07/MGPT-4o (Nov '24) — 11.2 — $4.38/MGPT-4o mini — 6.9 — $0.26/MGPT-5 (high) — 34.7 — $3.44/MGPT-5.1 (high) — 36.9 — $3.44/MGPT-5.2 (xhigh) — 42.2 — $4.81/MGPT-5.2 Codex (xhigh) — 40.1 — $4.81/MGPT-5.3 Codex (xhigh) — 44.3 — $4.81/MGPT-5.4 (xhigh) — 51.4 — $5.62/MGPT-5.4 mini (xhigh) — 40.0 — $1.69/MGPT-5.4 nano (xhigh) — 38.2 — $0.46/MGPT-5.5 (xhigh) — 54.8 — $11.25/MGPT-5.6 Luna (max) — 51.2 — $2.25/MGPT-5.6 Sol (max) — 58.9 — $11.25/MGPT-5.6 Terra (max) — 55.0 — $5.62/MGrok 4.5 (high) — 53.8 — $3.00/MGemini 2.5 Flash-Lite (Non-reasoning) — 6.9 — $0.18/MGemini 3 Flash Preview (Non-reasoning) — 27.4 — $1.12/MMuse Spark 1.1 (xhigh) — 50.6 — $2.00/MLlama 3.2 Instruct 1B — 1.1 — $0.05/MMiniMax-M2 — 28.3 — $0.52/MMiniMax-M2.1 — 31.4 — $0.52/MMinistral 3 3B — 6.8 — $0.10/MMinistral 3 8B — 9.0 — $0.15/MMistral Large 3 — 15.9 — $0.75/MMistral Medium 3 — 12.5 — $0.80/MMistral Medium 3.5 — 29.9 — $3.00/MKimi K2 0905 — 23.5 — $1.07/MERNIE 4.5 300B A47B — 9.0 — $0.49/MDeepSeek V3.2 Exp (Non-reasoning) — 21.3 — $0.32/MLing-2.6-1T — 26.1 — $0.85/MLing 2.6 Flash — 14.1 — $0.15/MRing-2.6-1T — 30.6 — $0.85/MLlama 3 Instruct 70B — 3.5 — $1.18/MLlama 3 Instruct 8B — 1.2 — $0.07/MLlama 3.2 Instruct 3B — 4.2 — $0.15/MMiniMax M1 80k — 17.7 — $0.96/MKimi K2 — 19.4 — $1.03/MQwen3 235B A22B (Non-reasoning) — 10.9 — $1.22/MQwen3 8B (Non-reasoning) — 5.1 — $0.31/MQwen3 Coder 30B A3B Instruct — 13.6 — $0.90/MQwen3 Coder Next — 21.1 — $0.56/MQwen3 Next 80B A3B (Reasoning) — 16.7 — $1.88/MQwen3 Omni 30B A3B Instruct — 5.1 — $0.43/MQwen3 Omni 30B A3B (Reasoning) — 9.6 — $0.43/MQwen3 VL 235B A22B (Reasoning) — 20.6 — $2.62/MQwen3 VL 30B A3B (Reasoning) — 13.3 — $0.75/MQwen3 VL 8B Instruct — 8.4 — $0.31/MMiMo-V2-Flash (Non-reasoning) — 24.7 — $0.15/MMiMo-V2-Pro — 40.3 — $1.50/MGLM-4.5 (Reasoning) — 19.5 — $1.00/MGLM-4.5-Air — 16.5 — $0.37/MGLM-4.5V (Non-reasoning) — 7.0 — $0.90/MGLM-4.6V (Non-reasoning) — 11.0 — $0.45/MGPT-3.5 Turbo — 3.6 — $0.75/MGPT-4.1 — 19.4 — $3.50/MGPT-4.1 mini — 14.8 — $0.70/MGPT-4.1 nano — 9.6 — $0.18/MGPT-4o (May '24) — 8.6 — $7.50/MGPT-4o (Aug '24) — 9.6 — $4.38/MGPT-5 (ChatGPT) — 15.3 — $3.44/MGPT-5 Codex (high) — 36.1 — $3.44/MGPT-5 mini (high) — 25.3 — $0.69/MGPT-5 nano (high) — 19.9 — $0.14/MGPT-5.1 (Non-reasoning) — 20.4 — $3.44/MGPT-5.1 Codex (high) — 34.7 — $3.44/MGPT-5.1 Codex mini (high) — 30.6 — $0.69/MGPT-5.2 (Non-reasoning) — 26.0 — $4.81/Mo3 — 30.4 — $3.50/Mo3-mini — 19.0 — $1.93/Mo4-mini (high) — 25.6 — $1.93/MQwen3 30B A3B 2507 Instruct — 9.1 — $0.35/MQwen3 VL 32B Instruct — 11.1 — $1.22/MQwen3 VL 8B (Reasoning) — 10.6 — $0.66/MGemma 4 12B (Reasoning) — 22.0 — $0.15/MGrok 4.20 0309 v2 (Reasoning) — 37.0 — $3.00/MGrok 4.3 (high) — 37.6 — $1.56/MGrok Build 0.1 0616 — 39.8 — $1.25/MIntelligence Index$/1M tokens (blended, 3:1 input:output)
AlibabaOpenAIGoogleDeepSeekMetaZ AIAnthropicOther
Source: Artificial Analysis (artificialanalysis.ai) — every column here (Creator, Intelligence Index, Price, Speed, Latency, End-to-End Response Time) is their independently measured data, licensed via their Data API, not LLMRouter's own grade or registry. Value (Intelligence ÷ Price) is the one exception — it's our own ratio, computed from their Intelligence Index and blended price. Rows are matched to Artificial Analysis's evaluated models by name on a best-effort basis; a model missing here means we couldn't confidently match it to one of their entries. Click any column header's arrow to sort.
Model Creator Intelligence Price($/1M) Intelligence per Dollar Speed(Tokens/s) Latency(s) Response(s)
Claude Fable 5anthropic, deepinfra, gmicloudAnthropic59.9$203.0059.4392.66101.07
GPT 5.6 Solgmicloud, openaiOpenAI58.9$11.255.2469.19193.39200.61
Claude Opus 4.8anthropic, deepinfra, gmicloudAnthropic55.7$105.5756.2642.9751.86
GPT 5.6 Terragmicloud, openaiOpenAI55$5.6259.78142.62158.93162.44
GPT 5.5gmicloud, openaiOpenAI54.8$11.254.8767.9596.07103.43
Grok 4.5gmicloud, x-aiSpaceXAI53.8$317.93113.8112.7517.15
Claude Opus 4.7anthropic, deepinfra, gmicloudAnthropic53.5$105.3549.1422.4832.65
Claude Sonnet 5anthropic, deepinfra, gmicloudAnthropic53.4$413.3579.55225.33231.62
GPT 5.4gmicloud, openaiOpenAI51.4$5.6259.14156.67128.15131.34
GPT 5.6 Lunagmicloud, openaiOpenAI51.2$2.2522.76215.06103.52105.85
GLM 5.2deepinfra, digitalocean, fireworks, inceptron, novita, qwen, qwen-eu, siliconflow, streamlake, z-aiZ AI51.1$2.1523.77196.051.4514.2
Muse Spark 1.1metaMeta50.6$225.30118.691.1422.2
Gemini 3.5 Flashdeepinfra, gmicloud, googleGoogle50.2$3.37514.87156.8725.2228.41
Gemini 3.1 Pro Previewdeepinfra, gmicloud, googleGoogle46.5$4.510.33135.6825.9829.67
qwen3.7 Maxdeepinfra, gmicloud, novita, qwenAlibaba46$3.7512.27197.432.5517.28
m3deepinfra, fireworks, gmicloud, minimax, novita, siliconflowMiniMax44.4$0.52584.57110.751.4123.99
v4 Prodeepinfra, deepseek, digitalocean, fireworks, gmicloud, novita, qwen, qwen-eu, siliconflow, streamlakeDeepSeek44.3$0.5482.0463.51.778.48
GPT 5.3 Codexgmicloud, openaiOpenAI44.3$4.81259.2192.6591.2296.62
Kimi k2.6deepinfra, digitalocean, fireworks, gmicloud, inceptron, moonshotai, novita, siliconflowKimi44.2$1.712525.8146.592.19108.46
Mimo v2.5 Prodeepinfra, digitalocean, gmicloud, novita, xiaomiXiaomi42.2$0.5478.1550.833.8353.01
GPT 5.2gmicloud, openaiOpenAI42.2$4.81258.7774.19161.63168.37
Kimi k2.7 Codedeepinfra, fireworks, gmicloud, inceptron, moonshotai, novita, qwen, qwen-eu, siliconflowKimi41.9$1.712524.4747.963.0659.96
v4 Flashdeepinfra, deepseek, digitalocean, fireworks, gmicloud, novita, qwen, qwen-eu, siliconflow, streamlakeDeepSeek40.3$0.175230.29101.511.3461.56
Mimo v2 PronovitaXiaomi40.3$1.526.87
GLM 5.1deepinfra, digitalocean, novita, qwen, qwen-eu, siliconflow, z-aiZ AI40.2$2.1518.70711.3761.81
GPT 5.2 Codexgmicloud, openaiOpenAI40.1$4.81258.33160.9579.8882.99
Qwen3.6 Max PreviewgmicloudAlibaba40$2.92513.6854.333.349.31
GPT 5.4 Minigmicloud, openaiOpenAI40$1.687523.70163.829.0112.06
Grok Build 0.1x-aiSpaceXAI39.8$1.2531.8459.940.5342.23
qwen3.6 Plusgmicloud, qwen, qwen-euAlibaba39.6$1.12535.2051.912.74119.3
GLM 5deepinfra, digitalocean, novita, siliconflow, z-aiZ AI39.5$1.5525.4850.11.7673.72
qwen3.7 Plusfireworks, qwenAlibaba39$0.755.7150.853.0252.18
GPT 5.4 Nanogmicloud, openaiOpenAI38.2$0.462582.59172.677.4110.3
m2.7deepinfra, fireworks, gmicloud, minimax, novitaMiniMax38.1$0.52572.5744.731.9268.14
Kimi k2.5deepinfra, digitalocean, gmicloud, moonshotai, novita, qwen, qwen-eu, siliconflowKimi38.1$1.231.7555.712.9165.16
GLM 5 Turbonovita, z-aiZ AI38.1
Claude Opus 4.6anthropic, gmicloudAnthropic37.8$103.7837.852.3415.55
Nemotron 3 Ultra 550bdeepinfra, digitalocean, fireworks, gmicloudNVIDIA37.8$1.177532.10183.841.1216.21
Grok 4.3x-aiSpaceXAI37.6$1.562524.06108.7224.1828.78
Mimo v2.5deepinfra, gmicloud, novita, xiaomiXiaomi37.2$0.175212.5778.892.5334.22
qwen3.6 27bdeepinfra, novita, siliconflowAlibaba37.1$1.3527.4859.763.83107.18
Grok 4.20x-aiSpaceXAI37$312.33153.2215.3718.63
GPT 5.1gmicloud, openaiOpenAI36.9$3.437510.73101.550.2355.16
GPT 5 CodexopenaiOpenAI36.1$3.437510.50174.978.5511.41
Claude Sonnet 4.6anthropic, deepinfra, gmicloudAnthropic35.9$65.9843.081.2612.87
Kat Coder Pro v2gmicloudKwaiKAT35.4$0.52567.43
Claude Opus 4.5anthropic, gmicloudAnthropic34.7$103.4746.921.6912.35
GPT 5gmicloud, openaiOpenAI34.7$3.437510.0986.0880.686.41
GPT 5.1 CodexopenaiOpenAI34.7$3.437510.09166.17.8610.87
GLM 5v Turbonovita, siliconflow, z-aiZ AI34.5
qwen3.5 27bdeepinfra, gmicloud, novita, qwen, qwen-eu, siliconflowAlibaba33.8$0.82540.9780.415.636.69
GLM 4.7deepinfra, novita, z-aiZ AI33.7$133.70140.660.8118.58
qwen3.5 397b a17bdeepinfra, digitalocean, gmicloud, novita, qwen, qwen-euAlibaba33.7$1.3524.9658.852.6265.25
m2.5digitalocean, gmicloud, inceptron, minimax, novita, siliconflowMiniMax33.7$0.52564.1975.161.7835.04
hy3deepinfra, gmicloud, novitaTencent33.6$0.1975170.13172.443.1117.61
Kimi k2 Thinkinggmicloud, moonshotai, novitaKimi32.7$1.07530.42161.181.2216.73
o3 ProopenaiOpenAI32.5$350.9337.8869.8883.08
qwen3.5 122b a10bdeepinfra, gmicloud, novita, qwen, qwen-eu, siliconflowAlibaba32.3$1.129.36142.122.4620.05
Qwen3 Max ThinkingdeepinfraAlibaba31.7
qwen3.6 Flashdeepinfra, gmicloud, novita, qwen, qwen-eu, siliconflowAlibaba31.6$0.5656.43166.632.3937.77
m2.1minimax, novitaMiniMax31.4$0.52559.8183.211.8331.88
Ring 2.6 1tnovitaInclusionAI30.6$0.8536.00126.483.3123.07
GPT 5.1 Codex MiniopenaiOpenAI30.6$0.687544.51206.989.6612.07
o3openaiOpenAI30.4$3.58.69114.466.6611.03
Step 3.7 Flashdeepinfra, novitaStepFun30.3$0.437569.26386.960.897.35
Medium 3 5mistralaiMistral29.9$39.97122.562.1722.57
Gemma 4 31b Itdeepinfra, digitalocean, google, novita, siliconflowGoogle29.4$035.221.164.59
qwen3.5 35b a3bdeepinfra, gmicloud, novita, qwen, qwen-euAlibaba29.3$0.687542.62158.212.3918.19
Claude Sonnet 4.5anthropicAnthropic29.3$64.8840.051.7414.22
m2minimax, novitaMiniMax28.3$0.52553.90811.8732.73
Claude Opus 4.1anthropicAnthropic28.2$300.9429.862.2619.01
Gemini 3 Flash PreviewgoogleGoogle27.4$1.12524.36166.810.853.84
Ling 2.6 1tnovitaInclusionAI26.1$0.8530.71
GPT 5.2 Chat LatestopenaiOpenAI26$4.81255.4064.820.988.69
Gemini 2.5 Prodeepinfra, googleGoogle25.8$3.43757.51134.2519.0222.74
Gemma 4 26b a4b Itdeepinfra, google, novita, siliconflowGoogle25.7$0.1975130.13
o4 MiniopenaiOpenAI25.6$1.92513.30156.5124.1827.37
Nemotron 3 Super 120bdeepinfra, digitaloceanNVIDIA25.4$0.382566.41144.281.0818.41
GPT 5 MiniopenaiOpenAI25.3$0.687536.8097.72104.26109.38
Gemini 3.1 Flash Litedeepinfra, gmicloud, googleGoogle25$0.562544.44271.915.697.53
Chatdeepinfra, deepseek, digitalocean, gmicloud, novita, siliconflowDeepSeek24.7$0.31578.41
Mimo v2 FlashnovitaXiaomi24.7$0.15164.67
qwen3 Maxdeepinfra, novita, qwen, qwen-euAlibaba24$2.410.0053.712.4611.77
GPT Oss 120bdeepinfra, digitalocean, fireworks, gmicloud, novita, siliconflowOpenAI23.8$0.262590.67321.450.88.58
Claude Haiku 4.5anthropic, deepinfraAnthropic23.7$211.8591.1216.49
Kimi k2 0905moonshotai, novitaKimi23.5$1.07521.8637.062.0415.53
o1openaiOpenAI23.4$26.250.89102.5226.7331.61
GLM 4.6deepinfra, novita, z-aiZ AI23$0.977523.5339.723.5916.18
GLM 4.7 Flashdeepinfra, novita, z-aiZ AI22.9$0.1525150.1690.411.1928.84
Gemma 4 12B ItsiliconflowGoogle22$0.15146.6756.382.5146.85
Qwen3.5 9Bdeepinfra, siliconflowAlibaba21.4$0.1125190.2256.421.7246.03
v3.1 Terminusdeepinfra, novita, siliconflowDeepSeek21.4$0.452547.29
v3.2 Expnovita, siliconflowDeepSeek21.3$0.31567.62
qwen3 Coder NextnovitaAlibaba21.1$0.562537.51103.431.586.41
v3.1deepinfra, novitaDeepSeek21$0.8425.00
qwen3 VL 235b a22b Thinkingnovita, qwen, qwen-euAlibaba20.6$2.6257.8556.543.0147.23
GPT 5.1 Chat LatestopenaiOpenAI20.4$3.43755.93104.160.995.79
r1deepinfra, novitaDeepSeek20.1$2.06259.75
GPT 5 NanoopenaiOpenAI19.9$0.1375144.73146.46124.35127.76
qwen3 235b a22b Thinking 2507deepinfra, novita, qwen, qwen-euAlibaba19.6$2.6257.4757.162.8746.62
GLM 4.5novita, z-aiZ AI19.5$119.50
Kimi k2 InstructnovitaKimi19.4$1.03518.7436.432.316.02
GPT 4.1openaiOpenAI19.4$3.55.54101.470.975.9
o3 MiniopenaiOpenAI19$1.9259.87231.895.978.13
o1 ProopenaiOpenAI18.9$262.50.07
qwen3 235b a22b Instruct 2507deepinfra, novita, qwen, qwen-euAlibaba18.2$1.22514.8656.782.1710.97
qwen3 Coder 480b a35b Instructdeepinfra, novitaAlibaba18$36.0057.673.0911.76
m1 80knovitaMiniMax17.7$0.962518.39
qwen3 Next 80b a3b Thinkingnovita, qwen, qwen-euAlibaba16.7$1.8758.91173.382.3116.73
GLM 4.5 Airnovita, siliconflow, z-aiZ AI16.5$0.372544.3072.382.6937.22
Large 2512mistralaiMistral15.9$0.7521.2045.791.1712.09
v3 0324deepinfra, gmicloud, novitaDeepSeek15.4$1.20512.78
GPT 5 Chat LatestopenaiOpenAI15.3$3.43754.45161.570.793.89
GPT Oss 20bdeepinfra, digitalocean, fireworks, novita, siliconflowOpenAI14.9$0.0875170.29218.790.7812.21
Nemotron 3 Nano OmnidigitaloceanNVIDIA14.9$0.1275116.86308.2119.11
GPT 4.1 MiniopenaiOpenAI14.8$0.721.1480.040.877.12
Llama 4 Maverickdeepinfra, digitalocean, novitaMeta14.3$0.47530.111190.975.18
qwen3 VL 235b a22b Instructdeepinfra, novita, qwen, qwen-euAlibaba14.3$1.22511.6751.162.8212.59
Deepseek v3deepinfra, novitaDeepSeek14.2$0.522527.18
Gemini 2.5 Flashdeepinfra, googleGoogle14.1$0.8516.59202.330.472.95
Ling 2.6 FlashnovitaInclusionAI14.1$0.1594.00171.751.174.09
qwen3 Next 80b a3b Instructdeepinfra, gmicloud, novita, qwen, qwen-euAlibaba13.7$0.87515.66185.722.365.05
qwen3 Coder 30b a3b Instructnovita, qwen, qwen-euAlibaba13.6$0.915.1198.182.67.7
qwen3 VL 30b a3b Thinkingnovita, qwen, qwen-euAlibaba13.3$0.7517.73111.212.3324.81
Gemma 4 E4B ItdeepinfraGoogle12.5
Medium 3mistralaiMistral12.5$0.815.6246.61.4712.2
GPT 4ogmicloud, openaiOpenAI11.2$4.3752.56207.070.763.18
3 14Bdigitalocean, mistralaiMistral11.1$0.255.5074.340.857.58
qwen3 VL 32b Instructqwen, qwen-euAlibaba11.1$1.2259.0670.732.759.82
r1 Distill Qwen 32bnovitaDeepSeek11
GLM 4.6vnovita, z-aiZ AI11$0.4524.4466.065.0212.59
qwen3 235b a22bnovita, qwen, qwen-euAlibaba10.9$1.2258.9060.122.8411.16
Small 3.2 24B Instruct 2506deepinfraMistral10.6$0.1570.67151.410.633.94
qwen3 VL 8b Thinkingqwen, qwen-euAlibaba10.6$0.6616.06111.372.3624.81
r1 0528 qwen3 8bnovitaDeepSeek10.4
qwen3 VL 30b a3b Instructdeepinfra, novita, qwen, qwen-euAlibaba10$0.3528.57111.042.166.66
Llama 4 Scout 17b 16e Instructdeepinfra, novitaMeta10$0.292534.19114.630.895.25
r1 Distill Llama 70bdigitalocean, novitaDeepSeek9.9$0.787512.5729.210.6386.21
r1 Distill Qwen 14bnovitaDeepSeek9.8
2.5 72b Instructdeepinfra, novitaAlibaba9.6$0.47520.21
qwen3 Omni 30b a3b ThinkingnovitaAlibaba9.6$0.4322.3397.361.9927.67
GPT 4.1 NanoopenaiOpenAI9.6$0.17554.86153.60.673.93
GPT 4o 2024 08 06openaiOpenAI9.6$4.3752.1975.251.638.28
Llama 3.3 70b Instructdeepinfra, digitalocean, meta-llama, novitaMeta9.4$0.612515.3589.741.517.09
qwen3 30b a3b Instruct 2507qwen, qwen-euAlibaba9.1$0.3526.00141.791.985.51
Ministral 8b 2512mistralaiMistral9$0.1560.0079.170.827.14
Ernie 4.5 300b a47b PaddlenovitaBaidu9$0.48518.56
qwen3 32bdeepinfra, digitalocean, novita, qwen, qwen-euAlibaba8.6$1.2257.0294.772.67.88
GPT 4o 2024 05 13openaiOpenAI8.6$7.51.1583.961.137.08
qwen3 VL 8b Instructnovita, qwen, qwen-euAlibaba8.4$0.3127.10119.312.36.49
GPT 4 TurboopenaiOpenAI7.9$150.5331.752.6118.35
Llama 3.1 8b Instructdeepinfra, novitaMeta7.6$0.08589.41154.40.914.15
Gemma 3 27b Itdeepinfra, novitaGoogle7.4$0
Nemotron 3 Nano 30b a3bdeepinfra, novitaNVIDIA7.4$0.087584.57105.620.55.24
qwen3 14bdeepinfra, qwenAlibaba7$0.612511.4361.792.8310.92
GLM 4.5vnovita, z-aiZ AI7$0.97.7872.0814.2121.14
GPT 4openaiOpenAI7$37.50.19
GPT 4o Minigmicloud, openaiOpenAI6.9$0.262526.2971.850.897.85
Gemini 2.5 Flash LitegoogleGoogle6.9$0.17539.43214.820.352.68
qwen3 30b a3bdeepinfra, novita, qwen, qwen-euAlibaba6.8$0.3519.43102.032.327.22
3.1 70B Instruct TurbodeepinfraMeta6.8$0.5612.1433.421.7416.7
Ministral 3b 2512mistralaiMistral6.8$0.168.00161.920.613.7
qwen3 4b fp8novitaAlibaba6.8
Gemini 1.5 Flash 8bdeepinfraGoogle5.5
Gemma 3 12b Itdeepinfra, novitaGoogle5.5$0
Hermes 3 Llama 3.1 70BdeepinfraNous Research5.1$0.77.2934.321.8516.42
qwen3 8bnovita, qwen, qwen-euAlibaba5.1$0.3116.4537.983.8517.01
qwen3 Omni 30b a3b InstructnovitaAlibaba5.1$0.4311.8693.672.047.38
Phi 4deepinfraMicrosoft4.9$0.222522.0225.462.1921.82
Nemotron Nano 12b v2 VLdigitaloceanNVIDIA4.6$0.315.33220.391.143.41
Llama 3.2 3b InstructnovitaMeta4.2$0.1528.0052.31.0810.64
GPT 3.5 TurboopenaiOpenAI3.6$0.754.80
Llama 3 70b InstructnovitaMeta3.5$1.1752.98
Llama 3 8b InstructnovitaMeta1.2$0.06518.46
Gemma 3 4b ItdeepinfraGoogle1.1$0
Llama 3.2 1b Instructmeta-llama, novitaMeta1.1$0.0522.0084.720.886.79