Skip to content

Cheaper Inference

A discount marketplace for frontier and open models.

Cheaper Inference resells frontier models (Claude, GPT, Gemini, Grok) and open ones (GLM, Kimi, DeepSeek, Qwen) from marketplace sellers, at a listed discount against each maker’s price. Requests can set a minimum discount, require zero data retention or rank sellers by speed or discount. It lists bare model ids (claude-opus-4.6), which the site aligns to canonical ids using the maker each listing names.

Discounted frontier models Zero-data-retention routing Bare model ids
Status
Live
Models in catalog
97
Text / multimodal
91
Publishes pricing for
97 models
Largest context window
1.1M tokens
Model id style
Bare ids (`claude-opus-4.6`, `glm-5.3`), aligned to canonical ids.
Billing
Prepaid wallet; pay per token at the discounted rate.
Catalog last checked
Website
www.cheaperinference.com
Documentation
Developer docs
Catalog

97 models on Cheaper Inference

The 60 most widely available are shown; the rest are searchable in the full model list. "Id on this gateway" is what Cheaper Inference calls the model — where it differs from the canonical id, that difference is what a router has to translate.

Search all 97 models on Cheaper Inference
ModelVendorTypeId on this gatewayAvailable onContextInput / Mtok
Claude Fable 5 anthropic/claude-fable-5 Anthropic Multimodal claude-fable-5 Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $6.96–$10.00
Claude Fable 5.1 anthropic/claude-fable-5.1 Anthropic Multimodal claude-fable-5.1 Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $6.50–$10.00
Claude Haiku 4.5 anthropic/claude-haiku-4.5 Anthropic Multimodal claude-haiku-4.5 Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 200K $0.650–$1.00
Claude Opus 4.6 anthropic/claude-opus-4.6 Anthropic Multimodal claude-opus-4.6 Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $3.34–$5.00
Claude Opus 4.7 anthropic/claude-opus-4.7 Anthropic Multimodal claude-opus-4.7 Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $3.25–$5.50
Claude Opus 4.8 anthropic/claude-opus-4.8 Anthropic Multimodal claude-opus-4.8 Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $3.48–$5.50
Claude Opus 5 anthropic/claude-opus-5 Anthropic Multimodal claude-opus-5 Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $3.25–$5.50
Claude Opus 5.5 anthropic/claude-opus-5.5 Anthropic Multimodal claude-opus-5.5 Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $2.60–$4.00
Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 Anthropic Multimodal claude-sonnet-4.6 Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $2.02–$3.00
Claude Sonnet 5 anthropic/claude-sonnet-5 Anthropic Multimodal claude-sonnet-5 Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $1.30–$2.20
Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 Anthropic Multimodal claude-sonnet-5.5 Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $1.30–$2.00
Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 Anthropic Multimodal claude-sonnet-4.5 Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterRampRequestyVercel 1M $1.95–$3.00
Qwen3.5 35B A3B qwen/qwen3.5-35b-a3b Qwen Multimodal qwen3.5-35b-a3b Cheaper InferenceCloudflareConcentrateDarkbloomLLM GatewayOpenRouterOrcaRouterRequesty 262.1K $0.057–$0.250
Qwen3.8 27B qwen/qwen3.8-27b Qwen Multimodal qwen3.8-27b Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRequestyVercel 1M $0.040–$0.500
Qwen3.8 Max qwen/qwen3.8-max Qwen Multimodal qwen3.8-max Cheaper InferenceCloudflareConcentrateFireworksLLM GatewayOrcaRouterRampRequesty 1M $1.30–$2.00
Claude Opus 4.5 anthropic/claude-opus-4.5 Anthropic Multimodal claude-opus-4.5 Cheaper InferenceCloudflareConcentrateOpenRouterOrcaRouterRequestyVercel 200K $3.25–$5.00
Muse Spark 1.2 meta-llama/muse-spark-1.2 Meta Multimodal muse-spark-1.2 Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterVercel 1M $1.06–$1.25
Qwen3 32B qwen/qwen3-32b Qwen Text qwen3-32b Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterRequestyVercel 131.1K $0.080–$0.360
Qwen3.6 35B A3B qwen/qwen3.6-35b-a3b Qwen Multimodal qwen3.6-35b-a3b Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterSail 262.1K $0.100–$0.248
Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b Qwen Text qwen3.8-2.4t-a95b Cheaper InferenceCloudflareFireworksLLM GatewayOpenRouterRequestyTogether 1M $1.30–$2.50
Qwen Flash qwen/qwen3.8-flash Qwen Text qwen3.8-flash Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterTogether 1M $0.050–$0.150
MiMo V2.6 Flash xiaomi/mimo-v2.6-flash Xiaomi Multimodal mimo-v2.6-flash Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterRequestyVercel 1.1M $0.119–$0.140
Qwen3 Coder Next qwen/qwen3-coder-next Qwen Text qwen3-coder-next Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterVercel 262.1K $0.108–$0.500
Qwen3 VL 235B A22B Instruct qwen/qwen3-vl-235b-a22b-instruct Qwen Multimodal qwen3-vl-235b-a22b-instruct Cheaper InferenceCloudflareLLM GatewayOpenRouterOrcaRouterVercel 262.1K $0.200–$0.400
Seedance 2.0 bytedance/seedance-2.0 ByteDance Video seedance-2.0 Cheaper InferenceCloudflareLLM GatewayTogetherVercel 2K Free
GPT-5.6 Luna gpt-5.6-luna OpenAI Multimodal gpt-5.6-luna Cheaper InferenceConcentrateLLM GatewayOrcaRouterRamp 1.1M $0.080–$0.200
Qwen3 Next 80B A3B Instruct qwen/qwen3-next-80b-a3b-instruct Qwen Text qwen3-next-80b-a3b-instruct Cheaper InferenceCloudflareLLM GatewayOpenRouterVercel 262.1K $0.098–$0.150
Qwen3.6 27B qwen/qwen3.6-27b Qwen Multimodal qwen3.6-27b Cheaper InferenceCloudflareConcentrateOpenRouterVercel 262.1K $0.320–$0.600
DeepSeek V4.1 Flash deepseek-v4.1-flash DeepSeek Multimodal deepseek-v4.1-flash Cheaper InferenceConcentrateLLM GatewayRamp 1.1M $0.075–$0.300
Gemini 2.5 Flash gemini-2.5-flash Google Multimodal gemini-2.5-flash Cheaper InferenceConcentrateLLM GatewayRamp 1M $0.195–$0.300
Gemini 3.5 Flash gemini-3.5-flash Google Multimodal gemini-3.5-flash Cheaper InferenceConcentrateLLM GatewayRamp 1M $0.996–$1.50
Gemini 3.5 Flash Lite gemini-3.5-flash-lite Google Multimodal gemini-3.5-flash-lite Cheaper InferenceConcentrateLLM GatewayRamp 1M $0.195–$0.300
Gemini 3.6 Flash gemini-3.6-flash Google Multimodal gemini-3.6-flash Cheaper InferenceConcentrateLLM GatewayRamp 1M $0.487–$0.750
Gemini 3.7 Flash gemini-3.7-flash Google Multimodal gemini-3.7-flash Cheaper InferenceConcentrateLLM GatewayRamp 1M $0.487–$0.750
Gemini 3.8 Flash gemini-3.8-flash Google Multimodal gemini-3.8-flash Cheaper InferenceConcentrateLLM GatewayRamp 1M $0.487–$0.750
GPT-5 Mini gpt-5-mini OpenAI Multimodal gpt-5-mini Cheaper InferenceConcentrateLLM GatewayRamp 400K $0.163–$0.250
GPT-5 Nano gpt-5-nano OpenAI Text gpt-5-nano Cheaper InferenceConcentrateLLM GatewayRamp 400K $0.033–$0.050
GPT-5.4 gpt-5.4 OpenAI Multimodal gpt-5.4 Cheaper InferenceConcentrateLLM GatewayRamp 1.1M $1.63–$2.50
GPT-5.4 Mini gpt-5.4-mini OpenAI Multimodal gpt-5.4-mini Cheaper InferenceConcentrateLLM GatewayRamp 400K $0.487–$0.750
GPT-5.4 Nano gpt-5.4-nano OpenAI Multimodal gpt-5.4-nano Cheaper InferenceConcentrateLLM GatewayRamp 400K $0.170–$0.200
GPT-5.5 gpt-5.5 OpenAI Multimodal gpt-5.5 Cheaper InferenceConcentrateLLM GatewayRamp 1.1M $3.25–$5.00
GPT-5.6 Sol gpt-5.6-sol OpenAI Multimodal gpt-5.6-sol Cheaper InferenceConcentrateLLM GatewayRamp 1.1M $2.00–$4.00
GPT-5.6 Terra gpt-5.6-terra OpenAI Multimodal gpt-5.6-terra Cheaper InferenceConcentrateLLM GatewayRamp 1.1M $1.18–$2.00
GPT-6 Astra gpt-6-astra OpenAI Multimodal gpt-6-astra Cheaper InferenceConcentrateLLM GatewayRamp 1.1M $6.68–$10.00
GPT-6 Luna gpt-6-luna OpenAI Multimodal gpt-6-luna Cheaper InferenceConcentrateLLM GatewayRamp 1.1M $0.065–$0.100
GPT-6 Sol gpt-6-sol OpenAI Multimodal gpt-6-sol Cheaper InferenceConcentrateLLM GatewayRamp 1.1M $1.30–$2.00
GPT-6.1 Sol gpt-6.1-sol OpenAI Multimodal gpt-6.1-sol Cheaper InferenceConcentrateLLM GatewayRamp 1.1M $1.30–$2.00
GPT OSS 120B gpt-oss-120b OpenAI Text gpt-oss-120b Cheaper InferenceConcentrateLLM GatewayRamp 131.1K $0.032–$0.150
Grok 4.3 grok-4.3 xAI Multimodal grok-4.3 Cheaper InferenceConcentrateLLM GatewayRamp 1M $0.813–$1.25
Grok 4.5 grok-4.5 xAI Multimodal grok-4.5 Cheaper InferenceConcentrateLLM GatewayRamp 500K $1.30–$2.00
Grok 4.6 grok-4.6 xAI Multimodal grok-4.6 Cheaper InferenceConcentrateLLM GatewayRamp 500K $1.30–$2.00
Grok 4.7 grok-4.7 xAI Multimodal grok-4.7 Cheaper InferenceConcentrateLLM GatewayRamp 524.3K $1.30–$2.00
Kimi K3 kimi-k3 Moonshot AI Multimodal kimi-k3 Cheaper InferenceConcentrateLLM GatewayRamp 1M $2.19–$3.00
MiMo V2.6 Pro mimo-v2.6-pro Xiaomi Text mimo-v2.6-pro Cheaper InferenceConcentrateLLM GatewayRequesty 1M $0.362–$0.435
MiniMax M3 minimax-m3 MiniMax Multimodal minimax-m3 Cheaper InferenceConcentrateLLM GatewayRamp 1M $0.195–$0.300
Qwen3 Coder 30B A3B Instruct qwen/qwen3-coder-30b-a3b-instruct Qwen Text qwen3-coder-30b-a3b-instruct Cheaper InferenceCloudflareLLM GatewayOpenRouter 262.1K $0.070–$0.292
Claude Opus 4.8 (Fast) anthropic/claude-opus-4.8-fast Anthropic Text claude-opus-4.8-fast Cheaper InferenceCloudflareVercel 1M $6.50–$10.00
Claude Opus 5 (Fast) anthropic/claude-opus-5-fast Anthropic Text claude-opus-5-fast Cheaper InferenceCloudflareVercel 1M $6.50–$10.00
DeepSeek V4 Flash deepseek-v4-flash DeepSeek Text deepseek-v4-flash Cheaper InferenceLLM GatewayRamp 1.1M $0.065–$0.130
DeepSeek V4 Flash 0731 (Baseten) deepseek-v4-flash-0731 DeepSeek Text deepseek-v4-flash-0731 Cheaper InferenceConcentrateRamp 1M $0.130–$0.132
Cheapest here

Lowest input prices on Cheaper Inference

Ranked by what this gateway charges, not by the cheapest price anywhere.

ModelVendorAvailable onContextInput / MtokSpread
GPT-5 Nano gpt-5-nano OpenAI Cheaper InferenceConcentrateLLM GatewayRamp 400K $0.033–$0.050 1.54x
gemma-3-12b-it gemma-3-12b-it Google Cheaper Inference 128K $0.033 —
gemma-3-4b-it gemma-3-4b-it Google Cheaper Inference 128K $0.033 —
GPT OSS 120B gpt-oss-120b OpenAI Cheaper InferenceConcentrateLLM GatewayRamp 131.1K $0.032–$0.150 4.69x
GLM-4.7 Flash glm-4.7-flash Z.ai Cheaper InferenceConcentrateLLM Gateway 200K $0.045–$0.060 1.32x
gemma-3-27b-it gemma-3-27b-it Google Cheaper Inference 40K $0.052 —
GPT-6 Luna gpt-6-luna OpenAI Cheaper InferenceConcentrateLLM GatewayRamp 1.1M $0.065–$0.100 1.54x
DeepSeek V4.1 Flash deepseek-v4.1-flash DeepSeek Cheaper InferenceConcentrateLLM GatewayRamp 1.1M $0.075–$0.300 4x
GPT-4.1 Nano gpt-4.1-nano OpenAI Cheaper InferenceLLM GatewayRamp 1M $0.075–$0.100 1.33x
GPT-5.6 Luna gpt-5.6-luna OpenAI Cheaper InferenceConcentrateLLM GatewayOrcaRouterRamp 1.1M $0.080–$0.200 2.50x
By model type

What Cheaper Inference carries

A gateway with 2,000 models is not necessarily a gateway with 2,000 chat models.

Multimodal 57 Text 34 Image 5 Video 1
Not exclusive

88 of these models are on other gateways too

Anything in this list can be served from somewhere other than Cheaper Inference without changing the model id your application sends.

ModelVendorAvailable onContextInput / MtokSpread
Claude Fable 5 anthropic/claude-fable-5 Anthropic Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $6.96–$10.00 1.44x
Claude Fable 5.1 anthropic/claude-fable-5.1 Anthropic Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $6.50–$10.00 1.54x
Claude Haiku 4.5 anthropic/claude-haiku-4.5 Anthropic Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 200K $0.650–$1.00 1.54x
Claude Opus 4.6 anthropic/claude-opus-4.6 Anthropic Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $3.34–$5.00 1.50x
Claude Opus 4.7 anthropic/claude-opus-4.7 Anthropic Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $3.25–$5.50 1.69x
Claude Opus 4.8 anthropic/claude-opus-4.8 Anthropic Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $3.48–$5.50 1.58x
Claude Opus 5 anthropic/claude-opus-5 Anthropic Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $3.25–$5.50 1.69x
Claude Opus 5.5 anthropic/claude-opus-5.5 Anthropic Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $2.60–$4.00 1.54x
Claude Sonnet 4.6 anthropic/claude-sonnet-4.6 Anthropic Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $2.02–$3.00 1.48x
Claude Sonnet 5 anthropic/claude-sonnet-5 Anthropic Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $1.30–$2.20 1.69x
Claude Sonnet 5.5 anthropic/claude-sonnet-5.5 Anthropic Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRampRequestyVercel 1M $1.30–$2.00 1.54x
Claude Sonnet 4.5 anthropic/claude-sonnet-4.5 Anthropic Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterRampRequestyVercel 1M $1.95–$3.00 1.54x
Qwen3.5 35B A3B qwen/qwen3.5-35b-a3b Qwen Cheaper InferenceCloudflareConcentrateDarkbloomLLM GatewayOpenRouterOrcaRouterRequesty 262.1K $0.057–$0.250 4.39x
Qwen3.8 27B qwen/qwen3.8-27b Qwen Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterRequestyVercel 1M $0.040–$0.500 12.50x
Qwen3.8 Max qwen/qwen3.8-max Qwen Cheaper InferenceCloudflareConcentrateFireworksLLM GatewayOrcaRouterRampRequesty 1M $1.30–$2.00 1.54x
Claude Opus 4.5 anthropic/claude-opus-4.5 Anthropic Cheaper InferenceCloudflareConcentrateOpenRouterOrcaRouterRequestyVercel 200K $3.25–$5.00 1.54x
Muse Spark 1.2 meta-llama/muse-spark-1.2 Meta Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterVercel 1M $1.06–$1.25 1.18x
Qwen3 32B qwen/qwen3-32b Qwen Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterRequestyVercel 131.1K $0.080–$0.360 4.50x
Qwen3.6 35B A3B qwen/qwen3.6-35b-a3b Qwen Cheaper InferenceCloudflareConcentrateLLM GatewayOpenRouterOrcaRouterSail 262.1K $0.100–$0.248 2.48x
Qwen3.8 2.4T A95B qwen/qwen3.8-2.4t-a95b Qwen Cheaper InferenceCloudflareFireworksLLM GatewayOpenRouterRequestyTogether 1M $1.30–$2.50 1.92x
Recent churn

What Cheaper Inference has changed lately

From the daily catalog crawl. Every line below concerns this gateway, so it is not named on each one.

All gateway changes
  • nano-banana-pro arrived
  • nano-banana-2 arrived
  • nano-banana arrived
  • claude-opus-5-fast arrived
  • claude-opus-4.8-fast arrived
  • Seedance 2.0 arrived on 2 gateways at once
  • Qwen3.8 2.4T A95B arrived on 2 gateways at once
  • Qwen3.6 35B A3B arrived on 2 gateways at once
  • Qwen3 VL 235B A22B Instruct arrived on 2 gateways at once
  • Qwen3 Next 80B A3B Instruct arrived on 2 gateways at once
  • Qwen3 Coder 30B A3B Instruct arrived on 2 gateways at once
  • Qwen3.8 Max arrived on 3 gateways at once
  • Qwen3.8 27B arrived on 3 gateways at once
  • Qwen3.6 27B arrived on 2 gateways at once
  • Qwen3.5 35B A3B arrived on 4 gateways at once
  • Qwen3 Coder Next arrived on 3 gateways at once
  • Qwen3 32B arrived on 3 gateways at once
  • Muse Spark 1.2 arrived on 3 gateways at once
  • Claude Opus 4.5 arrived on 2 gateways at once
  • Claude Sonnet 4.6 arrived on 4 gateways at once
  • Claude Sonnet 4.5 arrived on 4 gateways at once
  • Claude Opus 4.6 arrived on 4 gateways at once
  • Claude Haiku 4.5 arrived on 4 gateways at once
  • Claude Fable 5.1 arrived on 4 gateways at once
  • Claude Fable 5 arrived on 4 gateways at once