CloudTopHosts is operated by WiserWeb, which also sells WiserWebCloud (listed here). Tables are ordered by advertised price. Sponsored placements are labelled and never change that order. How this works
CloudTopHosts

LLM API prices by model

701 models, each compared across every lab, inference host and router we track. Prices are USD per 1M tokens. Blended weights input and output 3:1, the usual chat workload.

Model labs 24Inference hosts 31Hyperscaler AI platforms 5LLM routers 14LLM gateways 12

ModelCreatorProvidersCheapest inputCheapest outputCheapest blendedSpreadContext
Gemini 3 Flash Preview
google/gemini-3-flash-preview
google 4$0.25$1.50$0.562 2.0×1.05M
Gemini 3.1 Flash-Lite
google/gemini-3.1-flash-lite
google 4$0.25$1.50$0.562 1.05M
Qwen3 VL 235B A22B open
qwen/qwen3-vl-235b-a22b-instruct
qwen 4$0.21$1.60$0.632 1.7×256k
GPT-5 mini
openai/gpt-5-mini
openai 4$0.25$2$0.688 1.8×400k
GPT-4.1 mini
openai/gpt-4.1-mini
openai 4$0.40$1.60$0.70 1.05M
Qwen3.6 Plus
qwen/qwen3.6-plus
qwen 4$0.325$1.95$0.731 1.5×1M
Gemini 3.6 Flash
google/gemini-3.6-flash
google 4$0.375$1.88$0.75 2.0×1.05M
Mistral Large 3 (675B) open
mistralai/mistral-large-2512
mistralai 4$0.50$1.50$0.75 1.3×256k
Gemini 3.5 Flash-Lite
google/gemini-3.5-flash-lite
google 4$0.30$2.50$0.85 1.05M
Kimi K2 0905 open
moonshotai/kimi-k2-0905
moonshotai 4$0.57$2.29$1 1.1×262k
Kimi K2 0711 open
moonshotai/kimi-k2
moonshotai 4$0.57$2.30$1 1.1×262k
Gemini 3.7 Flash
google/gemini-3.7-flash
google 4$0.75$3.75$1.50 1.05M
Gemini 3.8 Flash
google/gemini-3.8-flash
google 4$0.75$3.75$1.50 1.05M
Gemini 3.5 Flash
google/gemini-3.5-flash
google 4$0.75$4.50$1.69 2.0×1.05M
GPT-5.4 mini
openai/gpt-5.4-mini
openai 4$0.75$4.50$1.69 400k
GPT-5.1
openai/gpt-5.1
openai 4$0.625$5$1.72 2.0×400k
o3
openai/o3
openai 4$1$4$1.75 2.0×200k
o3-mini
openai/o3-mini
openai 4$1.10$4.40$1.93 200k
o4-mini
openai/o4-mini
openai 4$1.10$4.40$1.93 200k
Qwen3.7 Max
qwen/qwen3.7-max
qwen 4$1.48$4.42$2.21 1.7×1.05M
Gemini 3.1 Pro Preview
google/gemini-3.1-pro-preview
google 4$1$6$2.25 2.0×1.05M
GPT-5
openai/gpt-5
openai 4$1.25$10$3.44 2.0×400k
GPT-4.1
openai/gpt-4.1
openai 4$2$8$3.50 1.05M
GPT-5.6 Sol
openai/gpt-5.6-sol
openai 4$2$10$4 2.0×1.05M
GPT-5.6 Terra
openai/gpt-5.6-terra
openai 4$2$12$4.50 1.05M
GPT-5.2
openai/gpt-5.2
openai 4$1.75$14$4.81 400k
GPT-5.3 Codex
openai/gpt-5.3-codex
openai 4$1.75$14$4.81 400k
Claude Opus 4.5
anthropic/claude-opus-4.5
anthropic 4$5$25$10 1.1×200k
Claude Opus 4.7
anthropic/claude-opus-4.7
anthropic 4$5$25$10 1.1×1M
GPT-5.5
openai/gpt-5.5
openai 4$5$30$11.25 1.05M
GPT-6 Astra
openai/gpt-6-astra
openai 4$10$50$20 1.05M
o1
openai/o1
openai 4$15$60$26.25 200k
o3-pro
openai/o3-pro
openai 4$20$80$35 200k
GPT-5 pro
openai/gpt-5-pro
openai 4$15$120$41.25 400k
GPT-5.4 pro
openai/gpt-5.4-pro
openai 4$30$180$67.50 1.05M
Nemotron-3-Nano-Omni-30B open
nvidia/nemotron-3-nano-omni-30b-a3b-reasoning
nvidia 3$0$0$0 131k
Phi-4 open
microsoft/phi-4
microsoft 3$0.056$0.112$0.07 3.1×16k
Gemma 3 12B IT open
google/gemma-3-12b-it
google 3$0.05$0.15$0.075 5.3×131k
qwen2.5-coder-32b-instruct open
qwen/qwen-2.5-coder-32b-instruct
qwen 3$0.06$0.20$0.095 7.8×131k
gpt-oss-safeguard-20b open
openai/gpt-oss-safeguard-20b
openai 3$0.07$0.20$0.102 1.3×131k
Ministral 3 8B open
mistralai/ministral-8b-2512
mistralai 3$0.15$0.15$0.15 262k
MiMo v2.5 open
xiaomi/mimo-v2.5
xiaomi 3$0.14$0.28$0.175 1.05M
Qwen3-VL 8B open
qwen/qwen3-vl-8b-instruct
qwen 3$0.117$0.455$0.202 1.9×131k
Hy3 open
tencent/hy3
tencent 3$0.132$0.528$0.231 1.1×262k
Mistral Small 4 open
mistralai/mistral-small-2603
mistral 3$0.15$0.60$0.263 1.1×262k
Qwen-Plus
qwen/qwen-plus
qwen 3$0.26$0.78$0.39 1.5×1M
Qwen3-Coder-Flash
qwen/qwen3-coder-flash
qwen 3$0.195$0.975$0.39 1.5×1.05M
Step 3.7 Flash open
stepfun/step-3.7-flash
stepfun 3$0.20$1.15$0.438 262k
Codestral
mistralai/codestral-2508
mistral 3$0.30$0.90$0.45 256k
Muse Glimmer 30B open
meta/muse-glimmer-30b
meta 3$0.30$1.10$0.50 1.3×131k
Mistral Medium 3
mistralai/mistral-medium-3
mistral 3$0.40$2$0.80 5.9×131k
Gemini 2.5 Flash Image (Nano Banana)
google/gemini-2.5-flash-image
google 3$0.30$2.50$0.85 1.05M
Qwen2.5-VL 72B open
qwen/qwen2.5-vl-72b-instruct
qwen 3$0.80$1$0.85 1.2×128k
Gemini 3.1 Flash Image (Nano Banana 2)
google/gemini-3.1-flash-image
google 3$0.50$2$0.875 1.3×131k
Sonar
perplexity/sonar
perplexity 3$1$1$1 131k
GLM-4.5 open
z-ai/glm-4.5
z-ai 3$0.60$2.20$1 131k
Grok Build 0.1
x-ai/grok-build-0.1
xai 3$1$2$1.25 256k
Qwen3-Coder-Plus
qwen/qwen3-coder-plus
qwen 3$0.65$3.25$1.30 1.5×1.05M
Hermes-4-405B open
nousresearch/hermes-4-405b
nousresearch 3$1$3$1.50 131k
Qwen3-Max
qwen/qwen3-max
qwen 3$0.78$3.44$1.51 1.6×262k
Inkling open
thinkingmachines/inkling
thinkingmachines 3$1$4.05$1.76 1.5×524k
Palmyra X5
writer/palmyra-x5
writer 3$0.60$6$1.95 1.04M
Qwen 3.8 Max
qwen/qwen3.8-max-0902
qwen 3$2$6$3 1M
Grok 4.5
x-ai/grok-4.5
xai 3$2$6$3 500k
Sonar Reasoning Pro
perplexity/sonar-reasoning-pro
perplexity 3$2$8$3.50 131k
Command A
cohere/command-a
cohere 3$2.50$10$4.38 256k
GPT-4o (2024-05-13)
openai/gpt-4o-2024-05-13
openai 3$2.50$10$4.38 1.7×128k
GPT-4o (2024-11-20)
openai/gpt-4o-2024-11-20
openai 3$2.50$10$4.38 128k
Gemini 3 Pro Image (Nano Banana Pro)
google/gemini-3-pro-image
google 3$2$12$4.50 1.05M
Claude Sonnet 4
anthropic/claude-sonnet-4
anthropic 3$3$15$6 1M
Sonar Pro
perplexity/sonar-pro
perplexity 3$3$15$6 205k
Claude Opus 4.1
anthropic/claude-opus-4.1
anthropic 3$15$75$30 200k
GPT-5.2 pro
openai/gpt-5.2-pro
openai 3$21$168$57.75 400k
GPT-5.5 Pro
openai/gpt-5.5-pro
openai 3$30$180$67.50 1.05M
Lyria 3 Clip Preview
google/lyria-3-clip-preview
google 2$0$0$0 1.05M
Lyria 3 Pro Preview
google/lyria-3-pro-preview
google 2$0$0$0 1.05M
NVIDIA: Nemotron 3.5 Content Safety open
nvidia/nemotron-3.5-content-safety
nvidia 2$0$0$0 131k
granite-4.0-h-micro open
ibm-granite/granite-4.0-h-micro
ibm 2$0.017$0.112$0.041 131k
Qwen3.7-Flash
qwen/qwen3.7-flash
qwen 2$0.03$0.13$0.055 1M
Amazon Nova Micro
amazon/nova-micro-v1
amazon 2$0.035$0.14$0.061 128k
Gemma 3 4B open
google/gemma-3-4b-it
google 2$0.05$0.10$0.062 131k
Command R7B open
cohere/command-r7b-12-2024
cohere 2$0.037$0.15$0.066 128k
Mercury 2.5
inception/mercury-2.5
inception 2$0.04$0.15$0.068 5.0×260k
MythoMax 13B open
gryphe/mythomax-l2-13b
gryphe 2$0.08$0.09$0.087 4k
Qwen-Turbo
qwen/qwen-turbo
qwen 2$0.05$0.20$0.087 1M
Llama 3 8B Instruct Lite open
meta-llama/llama-3-8b-instruct
meta 2$0.05$0.14$0.10 1.4×
Ministral 3 (3B) open
mistralai/ministral-3b-2512
mistral 2$0.10$0.10$0.10 256k
Reka Edge open
rekaai/reka-edge
reka 2$0.10$0.10$0.10 16k
Amazon Nova Lite
amazon/nova-lite-v1
amazon 2$0.06$0.24$0.105 300k
IBM Granite 4.2 8B open
ibm-granite/granite-4.2-8b
ibm-granite 2$0.06$0.15$0.107 131k
Qwen3.5-Flash
qwen/qwen3.5-flash-02-23
qwen 2$0.065$0.26$0.114 1.5×1M
UI-TARS 1.5 7B open
bytedance/ui-tars-1.5-7b
bytedance 2$0.10$0.20$0.125 128k
Muse Spark 1.2 (Contributor)
meta/muse-spark-1.2-contributor
meta 2$0.10$0.20$0.125 1.05M
Muse Spark 1.3 (Contributor)
meta/muse-spark-1.3-contributor
meta 2$0.10$0.20$0.125 1.05M
Qwen2.5 7B Instruct Turbo open
qwen/qwen-2.5-7b-instruct
qwen 2$0.10$0.20$0.125 2.4×33k
Seed 1.6 Flash
bytedance-seed/seed-1.6-flash
bytedance 2$0.075$0.30$0.131 262k
Voxtral Small open
mistralai/voxtral-small-24b-2507
mistral 2$0.10$0.30$0.15 1.2×33k
Step 3.5 Flash open
stepfun/step-3.5-flash
stepfun 2$0.10$0.30$0.15 262k
Seed 2.0 Mini
bytedance-seed/seed-2.0-mini
bytedance 2$0.10$0.40$0.175 262k
Qwen3-VL-32B INSTRUCT open
qwen/qwen3-vl-32b-instruct
qwen 2$0.104$0.416$0.182 1.5×131k