Skip to content
这个页面有中文版。
切换到中文
API Pricing

11,195 prices on 4,854 listings · last collected 6 h ago · 442 flagged changes in 30 days

Every price, as each platform publishes it

A collector reads every public price on ten platforms, daily by default, and keeps the page it read. Nothing is typed in by hand. Search a model to see who charges least, per unit, right now.

Showing 1–67 of 67

“Cheapest” is the lowest exact price in this unit for your search. Rows can differ in resolution, length or quality — read the label, or add it to the search (e.g. “1080”).

Per million input tokens27

PlatformModel · what it coversUSDPlatform’s own wordingSince
OpenRouterThird-partyQwen: Qwen3.6 35B A3Bvia PrimeIntellect · fp8$0.023/M inCheapestprompt: 0.000000023 / token (endpoint primeintellect/fp8)
OpenRouterThird-partyQwen: Qwen3.8 27Bvia PrimeIntellect · fp8$0.062/M inprompt: 0.000000062 / token (endpoint primeintellect/fp8)
OpenRouterThird-partyQwen: Qwen3.5-35B-A3Bvia Darkbloom · fp4$0.065/M inprompt: 0.000000065 / token (endpoint darkbloom/fp4)
OpenRouterThird-partyQwen: Qwen3 Coder 30B A3B Instructvia SiliconFlow · fp8$0.07/M inprompt: 0.00000007 / token (endpoint siliconflow/fp8)
OpenRouterThird-partyQwen: Qwen3 32Bvia DeepInfra · fp8$0.08/M inprompt: 0.00000008 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen: Qwen3.5-9Bvia Darkbloom · fp4$0.08/M inprompt: 0.00000008 / token (endpoint darkbloom/fp4)
OpenRouterThird-partyQwen: Qwen3 235B A22B Instruct 2507via DeepInfra · fp8$0.09/M inprompt: 0.00000009 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen: Qwen3 30B A3B Instruct 2507via DekaLLM$0.09/M inprompt: 0.00000009 / token (endpoint dekallm)
OpenRouterThird-partyQwen: Qwen3 Next 80B A3B Instructvia DeepInfra · fp8$0.09/M inprompt: 0.00000009 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen: Qwen3 14Bvia NextBit · int4$0.1/M inprompt: 0.0000001 / token (endpoint nextbit/int4)
OpenRouterThird-partyQwen: Qwen3 30B A3B$0.12/M inprompt: 0.00000012 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen: Qwen3 Coder Next$0.12/M inprompt: 0.00000012 / token (endpoint parasail/bf16)
OpenRouterThird-partyQwen: Qwen3 VL 30B A3B Instructvia DeepInfra · fp8$0.15/M inprompt: 0.00000015 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen: Qwen3.8 27B (batch)$0.16/M inprompt: 0.00000016 / token (endpoint deepinfra/bf16)
OpenRouterThird-partyQwen: Qwen3 VL 235B A22B Instructvia DeepInfra · fp8$0.2/M inprompt: 0.0000002 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen: Qwen3 VL 8B Instruct$0.25/M inprompt: 0.00000025 / token (endpoint parasail/bf16)
OpenRouterThird-partyQwen: Qwen3.6 27Bvia Chutes · fp8$0.25/M inprompt: 0.00000025 / token (endpoint chutes/fp8)
OpenRouterThird-partyQwen: Qwen3.5-122B-A10Bvia SiliconFlow · fp8$0.26/M inprompt: 0.00000026 / token (endpoint siliconflow/fp8)
OpenRouterThird-partyQwen: Qwen3.5-27Bvia AtlasCloud · fp8$0.27/M inprompt: 0.00000027 / token (endpoint atlas-cloud/fp8)
OpenRouterThird-partyQwen: Qwen3 VL 30B A3B Thinking$0.29/M inprompt: 0.00000029 / token (endpoint siliconflow/fp8)
OpenRouterThird-partyQwen: Qwen3 Coder 480B A35BTurbovia DeepInfra$0.3/M inprompt: 0.0000003 / token (endpoint deepinfra/turbo)
OpenRouterThird-partyQwen2.5 72B Instruct$0.36/M inprompt: 0.00000036 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen: Qwen3.5 397B A17Bvia Alibaba$0.39/M inprompt: 0.00000039 / token (endpoint alibaba)
OpenRouterThird-partyQwen: Qwen3 235B A22B Thinking 2507$0.45/M inprompt: 0.00000045 / token (endpoint venice/fp8)
OpenRouterThird-partyQwen2.5 Coder 32B Instruct$0.66/M inprompt: 0.00000066 / token (endpoint cloudflare)
OpenRouterThird-partyQwen: Qwen2.5 VL 72B Instruct$0.8/M inprompt: 0.0000008 / token (endpoint parasail/fp8)
OpenRouterThird-partyQwen: Qwen3.8 2.4T A95Bvia Novita$2/M inprompt: 0.000002 / token (endpoint novita)

Per million output tokens27

PlatformModel · what it coversUSDPlatform’s own wordingSince
OpenRouterThird-partyQwen: Qwen3.5-9Bvia Darkbloom · fp4$0.13/M outCheapestcompletion: 0.00000013 / token (endpoint darkbloom/fp4)
OpenRouterThird-partyQwen: Qwen3.6 35B A3Bvia PrimeIntellect · fp8$0.213/M outcompletion: 0.000000213 / token (endpoint primeintellect/fp8)
OpenRouterThird-partyQwen: Qwen3 14Bvia NextBit · int4$0.22/M outcompletion: 0.00000022 / token (endpoint nextbit/int4)
OpenRouterThird-partyQwen: Qwen3 32Bvia DeepInfra · fp8$0.28/M outcompletion: 0.00000028 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen: Qwen3 Coder 30B A3B Instructvia SiliconFlow · fp8$0.28/M outcompletion: 0.00000028 / token (endpoint siliconflow/fp8)
OpenRouterThird-partyQwen: Qwen3 30B A3B Instruct 2507via DekaLLM$0.3/M outcompletion: 0.0000003 / token (endpoint dekallm)
OpenRouterThird-partyQwen2.5 72B Instruct$0.4/M outcompletion: 0.0000004 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen: Qwen3.8 27Bvia PrimeIntellect · fp8$0.44/M outcompletion: 0.00000044 / token (endpoint primeintellect/fp8)
OpenRouterThird-partyQwen: Qwen3 30B A3B$0.5/M outcompletion: 0.0000005 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen: Qwen3 235B A22B Instruct 2507via DeepInfra · fp8$0.55/M outcompletion: 0.00000055 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen: Qwen3 VL 30B A3B Instructvia DeepInfra · fp8$0.6/M outcompletion: 0.0000006 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen: Qwen3 VL 8B Instruct$0.75/M outcompletion: 0.00000075 / token (endpoint parasail/bf16)
OpenRouterThird-partyQwen: Qwen3.5-35B-A3Bvia Darkbloom · fp4$0.75/M outcompletion: 0.00000075 / token (endpoint darkbloom/fp4)
OpenRouterThird-partyQwen: Qwen3 Coder Next$0.8/M outcompletion: 0.0000008 / token (endpoint parasail/bf16)
OpenRouterThird-partyQwen: Qwen3 VL 235B A22B Instructvia DeepInfra · fp8$0.88/M outcompletion: 0.00000088 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen2.5 Coder 32B Instruct$1/M outcompletion: 0.000001 / token (endpoint cloudflare)
OpenRouterThird-partyQwen: Qwen2.5 VL 72B Instruct$1/M outcompletion: 0.000001 / token (endpoint parasail/fp8)
OpenRouterThird-partyQwen: Qwen3 Coder 480B A35BTurbovia DeepInfra$1/M outcompletion: 0.000001 / token (endpoint deepinfra/turbo)
OpenRouterThird-partyQwen: Qwen3 VL 30B A3B Thinking$1/M outcompletion: 0.000001 / token (endpoint siliconflow/fp8)
OpenRouterThird-partyQwen: Qwen3 Next 80B A3B Instructvia DeepInfra · fp8$1.1/M outcompletion: 0.0000011 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen: Qwen3.6 27Bvia Chutes · fp8$2/M outcompletion: 0.000002 / token (endpoint chutes/fp8)
OpenRouterThird-partyQwen: Qwen3.8 27B (batch)$2/M outcompletion: 0.000002 / token (endpoint deepinfra/bf16)
OpenRouterThird-partyQwen: Qwen3.5-122B-A10Bvia SiliconFlow · fp8$2.08/M outcompletion: 0.00000208 / token (endpoint siliconflow/fp8)
OpenRouterThird-partyQwen: Qwen3.5-27Bvia AtlasCloud · fp8$2.16/M outcompletion: 0.00000216 / token (endpoint atlas-cloud/fp8)
OpenRouterThird-partyQwen: Qwen3.5 397B A17Bvia Alibaba$2.34/M outcompletion: 0.00000234 / token (endpoint alibaba)
OpenRouterThird-partyQwen: Qwen3 235B A22B Thinking 2507$3.5/M outcompletion: 0.0000035 / token (endpoint venice/fp8)
OpenRouterThird-partyQwen: Qwen3.8 2.4T A95Bvia Novita$6/M outcompletion: 0.000006 / token (endpoint novita)

Per million cached input tokens (read)13

PlatformModel · what it coversUSDPlatform’s own wordingSince
OpenRouterThird-partyQwen: Qwen3.8 27Bvia PrimeIntellect · fp8$0.007/M cache readCheapestinput_cache_read: 0.000000007 / token (endpoint primeintellect/fp8)
OpenRouterThird-partyQwen: Qwen3.6 35B A3Bvia PrimeIntellect · fp8$0.021/M cache readinput_cache_read: 0.000000021 / token (endpoint primeintellect/fp8)
OpenRouterThird-partyQwen: Qwen3.6 27Bvia Chutes · fp8$0.025/M cache readinput_cache_read: 0.000000025 / token (endpoint chutes/fp8)
OpenRouterThird-partyQwen: Qwen3.5-35B-A3Bvia Darkbloom · fp4$0.033/M cache readinput_cache_read: 0.0000000325 / token (endpoint darkbloom/fp4)
OpenRouterThird-partyQwen: Qwen3.5-9Bvia Darkbloom · fp4$0.04/M cache readinput_cache_read: 0.00000004 / token (endpoint darkbloom/fp4)
OpenRouterThird-partyQwen: Qwen3.8 27B (batch)$0.04/M cache readinput_cache_read: 0.00000004 / token (endpoint deepinfra/bf16)
OpenRouterThird-partyQwen: Qwen3 Coder Next$0.07/M cache readinput_cache_read: 0.00000007 / token (endpoint parasail/bf16)
OpenRouterThird-partyQwen: Qwen3 Coder 480B A35BTurbovia DeepInfra$0.1/M cache readinput_cache_read: 0.0000001 / token (endpoint deepinfra/turbo)
OpenRouterThird-partyQwen: Qwen3 VL 235B A22B Instructvia DeepInfra · fp8$0.11/M cache readinput_cache_read: 0.00000011 / token (endpoint deepinfra/fp8)
OpenRouterThird-partyQwen: Qwen3 VL 8B Instruct$0.12/M cache readinput_cache_read: 0.00000012 / token (endpoint parasail/bf16)
OpenRouterThird-partyQwen: Qwen3.8 2.4T A95Bvia Novita$0.25/M cache readinput_cache_read: 0.00000025 / token (endpoint novita)
OpenRouterThird-partyQwen: Qwen3.5-27Bvia AtlasCloud · fp8$0.27/M cache readinput_cache_read: 0.00000027 / token (endpoint atlas-cloud/fp8)
OpenRouterThird-partyQwen: Qwen2.5 VL 72B Instruct$0.4/M cache readinput_cache_read: 0.0000004 / token (endpoint parasail/fp8)