InferIndex
Language, English, EN
Account

ProvidersNanoGPT

NanoGPT

The 277 models NanoGPT serves, direct and through aggregators, with the price and conditions of each offer.

Provider page We read NanoGPT's own price page.

No training on promptsNumber of this provider's offers whose published policy says prompts are not used for training, out of all its offers.
284 / 284 offers
Cheapest on InferIndexModels for which this provider has the lowest price on InferIndex.
77 / 277 models

Offers

AllAt the lowestAbove the lowest 284 of 284 offers
NanoGPT: LLM API prices
Model BlendedA single price that mixes input and output: 3 input tokens for 1 output token, per million tokens. It makes offers easy to rank; your real cost depends on your own mix.$/1M In$/1M Out$/1M ObservationGap to the lowest price we track for this model. CtxThe maximum amount of text, counted in tokens, the model can take in and write in a single request. Past this limit, the request is refused or cut. Offer
Aion-2.0 (aion-labs/aion-2.0) $1.00  $0.80  $1.60  Cheapest. The lowest price on InferIndex for this model. 131k Go to offer at NanoGPT (opens in a new tab)
Aion-3.0 (aion-labs/aion-3.0) $3.75  $3.00  $6.00  Cheapest. The lowest price on InferIndex for this model. 131k Go to offer at NanoGPT (opens in a new tab)
Aion-3.0-Mini (aion-labs/aion-3.0-mini) $0.875 $0.70  $1.40  Cheapest. The lowest price on InferIndex for this model. 131k Go to offer at NanoGPT (opens in a new tab)
Aion 3.5 (aion-labs/aion-3.5) $3.75  $3.00  $6.00  Cheapest. The lowest price on InferIndex for this model. 262k Go to offer at NanoGPT (opens in a new tab)
Aion 3.5 Mini (aion-labs/aion-3.5-mini) $0.875 $0.70  $1.40  Cheapest. The lowest price on InferIndex for this model. 262k Go to offer at NanoGPT (opens in a new tab)
Aion-RP 1.0 (8B) (aion-labs/aion-rp-llama-3.1-8b) $1.00  $0.80  $1.60  4.3× Lowest on InferIndex: $0.23. 33k Go to offer at NanoGPT (opens in a new tab)
Gemma-SEA-LION-v4-27B-IT (aisingapore/gemma-sea-lion-v4-27b-it) $0.30  $0.24  $0.48  +20% Lowest on InferIndex: $0.25. 131k Go to offer at NanoGPT (opens in a new tab)
Qwen-SEA-LION-v4-32B-IT (aisingapore/qwen-sea-lion-v4-32b-it) $0.375 $0.30  $0.60  +20% Lowest on InferIndex: $0.313. 131k Go to offer at NanoGPT (opens in a new tab)
Nova 2 Lite (amazon/nova-2-lite-v1) $1.45  $0.51  $4.25  +61% Lowest on InferIndex: $0.85. 1M Go to offer at NanoGPT (opens in a new tab)
Nova Lite 1.0 (amazon/nova-lite-v1) $0.104 $0.06  $0.238 Cheapest. The lowest price on InferIndex for this model. 300k Go to offer at NanoGPT (opens in a new tab)
Nova Pro 1.0 (amazon/nova-pro-v1) $1.40  $0.799 $3.20  Cheapest. The lowest price on InferIndex for this model. 300k Go to offer at NanoGPT (opens in a new tab)
Magnum v4 72B (anthracite-org/magnum-v4-72b) $2.25  $2.01  $2.99  Cheapest. The lowest price on InferIndex for this model. 16k Go to offer at NanoGPT (opens in a new tab)
Claude Fable 5 (anthropic/claude-fable-5) $20.00  $10.00  $50.00  At the lowest Lowest on InferIndex: $20.00. 1M Go to offer at NanoGPT (opens in a new tab)
Claude Fable 5.1 (anthropic/claude-fable-5.1) $20.00  $10.00  $50.00  At the lowest Lowest on InferIndex: $20.00. 1M Go to offer at NanoGPT (opens in a new tab)
Claude Haiku 4.5 (anthropic/claude-haiku-4.5)Thinking: Thinking: a mode of the model $2.00  $1.00  $5.00  At the lowest Lowest on InferIndex: $2.00. 200k Go to offer at NanoGPT (opens in a new tab)
Claude Haiku 5.5 (anthropic/claude-haiku-5.5) $0.20  $0.10  $0.50  At the lowest Lowest on InferIndex: $0.20. 1M Go to offer at NanoGPT (opens in a new tab)
Claude Opus 4.1 (anthropic/claude-opus-4.1)Unverified. Withdrawn by its lab; this seller has not shown it for sale for 72 hours: listed, not designated cheapest+1Thinking: Thinking: a mode of the model $30.00  $15.00  $75.00  – 200k Go to offer at NanoGPT (opens in a new tab)
Claude Opus 4.5 (anthropic/claude-opus-4.5)Thinking: Thinking: a mode of the model $10.00  $5.00  $25.00  At the lowest Lowest on InferIndex: $10.00. 200k Go to offer at NanoGPT (opens in a new tab)
Claude Opus 4.6 (anthropic/claude-opus-4.6)Thinking: Thinking: a mode of the model $10.00  $5.00  $25.00  At the lowest Lowest on InferIndex: $10.00. 1M Go to offer at NanoGPT (opens in a new tab)
Claude Opus 4.7 (anthropic/claude-opus-4.7)Thinking: Thinking: a mode of the model $10.00  $5.00  $25.00  At the lowest Lowest on InferIndex: $10.00. 1M Go to offer at NanoGPT (opens in a new tab)
Claude Opus 4.8 (anthropic/claude-opus-4.8)Thinking: Thinking: a mode of the model $10.00  $5.00  $25.00  At the lowest Lowest on InferIndex: $10.00. 1M Go to offer at NanoGPT (opens in a new tab)
Claude Opus 5 (anthropic/claude-opus-5) $10.00  $5.00  $25.00  At the lowest Lowest on InferIndex: $10.00. 1M Go to offer at NanoGPT (opens in a new tab)
Claude Opus 5.5 (anthropic/claude-opus-5.5) $8.00  $4.00  $20.00  At the lowest Lowest on InferIndex: $8.00. 1M Go to offer at NanoGPT (opens in a new tab)
Claude Sonnet 4.5 (anthropic/claude-sonnet-4.5)Thinking: Thinking: a mode of the model $6.00  $3.00  $15.00  At the lowest Lowest on InferIndex: $6.00. 200k Go to offer at NanoGPT (opens in a new tab)
Claude Sonnet 4.6 (anthropic/claude-sonnet-4.6)Thinking: Thinking: a mode of the model $6.00  $3.00  $15.00  At the lowest Lowest on InferIndex: $6.00. 1M Go to offer at NanoGPT (opens in a new tab)
Claude Sonnet 5 (anthropic/claude-sonnet-5)Thinking: Thinking: a mode of the model $4.00  $2.00  $10.00  At the lowest Lowest on InferIndex: $4.00. 1M Go to offer at NanoGPT (opens in a new tab)
Claude Sonnet 5.5 (anthropic/claude-sonnet-5.5)Thinking: Thinking: a mode of the model $4.00  $2.00  $10.00  At the lowest Lowest on InferIndex: $4.00. 1M Go to offer at NanoGPT (opens in a new tab)
Trinity Large Thinking (arcee-ai/trinity-large-thinking) $0.413 $0.25  $0.90  +6% Lowest on InferIndex: $0.388. 262k Go to offer at NanoGPT (opens in a new tab)
Doubao Seed 2.1 Pro (bytedance-seed/doubao-seed-2.1-pro) $2.00  $1.00  $5.00  +13% Lowest on InferIndex: $1.77. 256k Go to offer at NanoGPT (opens in a new tab)
Doubao Seed 2.1 Turbo (bytedance-seed/doubao-seed-2.1-turbo) $1.00  $0.50  $2.50  +13% Lowest on InferIndex: $0.885. 256k Go to offer at NanoGPT (opens in a new tab)
Seed 2.1 Turbo (bytedance-seed/seed-2-1-turbo) $1.00  $0.50  $2.50  Cheapest. The lowest price on InferIndex for this model. 262k Go to offer at NanoGPT (opens in a new tab)
Seed-2.0-Code (bytedance-seed/seed-2.0-code) $1.13  $0.50  $3.00  +17% Lowest on InferIndex: $0.962. 262k Go to offer at NanoGPT (opens in a new tab)
Seed-2.0-Lite (bytedance-seed/seed-2.0-lite) $0.688 $0.25  $2.00  3.4× Lowest on InferIndex: $0.203. 262k Go to offer at NanoGPT (opens in a new tab)
Seed-2.0-Mini (bytedance-seed/seed-2.0-mini) $0.196 $0.10  $0.485 2× Lowest on InferIndex: $0.098. 256k Go to offer at NanoGPT (opens in a new tab)
Command R+ (08-2024) (cohere/command-r-plus-08-2024) $5.70  $2.86  $14.25  +24% Lowest on InferIndex: $4.38. 128k Go to offer at NanoGPT (opens in a new tab)
DeepSeek V3 (deepseek/deepseek-chat) $0.181 $0.10  $0.425 Cheapest. The lowest price on InferIndex for this model. 128k Go to offer at NanoGPT (opens in a new tab)
DeepSeek V3 0324 (deepseek/deepseek-chat-v3-0324) $0.343 $0.20  $0.77  Cheapest. The lowest price on InferIndex for this model. 128k Go to offer at NanoGPT (opens in a new tab)
DeepSeek V3.1 (deepseek/deepseek-chat-v3.1)Thinking: Thinking: a mode of the model $0.325 $0.20  $0.70  – 128k Go to offer at NanoGPT (opens in a new tab)
R1 0528 (deepseek/deepseek-r1-0528) $0.913 $0.50  $2.15  +31% Lowest on InferIndex: $0.695. 164k Go to offer at NanoGPT (opens in a new tab)
DeepSeek V3.1 Terminus (deepseek/deepseek-v3.1-terminus)Thinking: Thinking: a mode of the model $0.363 $0.25  $0.70  – 128k Go to offer at NanoGPT (opens in a new tab)
DeepSeek V3.2 (deepseek/deepseek-v3.2)Thinking: Thinking: a mode of the model+1Price drop observed: The blended price is 26% lower than before this drop; possibly temporary. · Price drop observed since Oct 15, 2026 $0.234 $0.209 $0.31  – 163k Go to offer at NanoGPT (opens in a new tab)
DeepSeek V3.2 Exp (deepseek/deepseek-v3.2-exp) $0.315 $0.28  $0.42  +9% Lowest on InferIndex: $0.29. 164k Go to offer at NanoGPT (opens in a new tab)
DeepSeek V3.2 Exp Thinking (deepseek/deepseek-v3.2-exp-thinking) $0.315 $0.28  $0.42  Cheapest. The lowest price on InferIndex for this model. 164k Go to offer at NanoGPT (opens in a new tab)
deepseek/deepseek-v4-flashThinking: Thinking: a mode of the model $0.175 $0.14  $0.28  – 1M Go to offer at NanoGPT (opens in a new tab)
DeepSeek V4 Flash 0731 (deepseek/deepseek-v4-flash-0731)Thinking: Thinking: a mode of the model+1Price changes often: 10 price changes in 7 days. Over that period: input $0.044 – $0.05, output $0.133 – $0.16 per million tokens. An offer whose price changes this often is not selected as the cheapest. $0.078 $0.05  $0.16  – 1M Go to offer at NanoGPT (opens in a new tab)
deepseek/deepseek-v4-flash-vision-expPrice drop observed: The blended price is 51% lower than before this drop; possibly temporary. · Price drop observed since Oct 16, 2026 $0.323 $0.216 $0.647 – 1M Go to offer at NanoGPT (opens in a new tab)
deepseek/deepseek-v4-proThinking: Thinking: a mode of the model+1Price drop observed: The blended price is 36% lower than before this drop; possibly temporary. · Price drop observed since Oct 31, 2026 $0.875 $0.70  $1.40  – 1M Go to offer at NanoGPT (opens in a new tab)
DeepSeek V4 Pro 0813 (deepseek/deepseek-v4-pro-0813)Thinking: Thinking: a mode of the model+2Price drop observed: The blended price is 32% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026Price changes often: 19 price changes in 7 days. Over that period: input $0.132 – $0.66, output $0.396 – $1.98 per million tokens. An offer whose price changes this often is not selected as the cheapest. $0.988 $0.659 $1.98  +17% Lowest on InferIndex: $0.842. 1M Go to offer at NanoGPT (opens in a new tab)
DeepSeek V4.1 Flash (deepseek/deepseek-v4.1-flash)Thinking: Thinking: a mode of the model+2Price drop observed: The blended price is 69% lower than before this drop; possibly temporary. · Price drop observed since Oct 21, 2026Price changes often: 10 price changes in 7 days. Over that period: input $0.022 – $0.09, output $0.13 – $0.27 per million tokens. An offer whose price changes this often is not selected as the cheapest. $0.065 $0.022 $0.192 – 1M Go to offer at NanoGPT (opens in a new tab)
DeepSeek V4.1 Flash 1017 (deepseek/deepseek-v4.1-flash-1017)Thinking: Thinking: a mode of the model+1Price changes often: 8 price changes in 7 days. Over that period: input $0.017 – $0.12, output $0.60 – $0.72 per million tokens. An offer whose price changes this often is not selected as the cheapest. $0.27  $0.12  $0.72  2.3× Lowest on InferIndex: $0.113. 1M Go to offer at NanoGPT (opens in a new tab)
Glimpse (elorian/glimpse) $1.26  $0.63  $3.15  +5% Lowest on InferIndex: $1.20. 262k Go to offer at NanoGPT (opens in a new tab)
Ember-1 (fireworks/ember-1) $6.00  $3.00  $15.00  Cheapest. The lowest price on InferIndex for this model. 1M Go to offer at NanoGPT (opens in a new tab)
Gemini 2.5 Flash (google/gemini-2.5-flash) $0.85  $0.30  $2.50  At the lowest Lowest on InferIndex: $0.85. 1M Go to offer at NanoGPT (opens in a new tab)
Gemini 2.5 Flash Lite (google/gemini-2.5-flash-lite) $0.175 $0.10  $0.40  At the lowest Lowest on InferIndex: $0.175. 1M Go to offer at NanoGPT (opens in a new tab)
Gemini 2.5 Pro (google/gemini-2.5-pro) $3.44  $1.25  $10.00  At the lowest Lowest on InferIndex: $3.44. 1M Go to offer at NanoGPT (opens in a new tab)
Gemini 2.5 Pro Preview 06-05 (google/gemini-2.5-pro-preview) $4.38  $2.50  $10.00  +21% Lowest on InferIndex: $3.44. 1M Go to offer at NanoGPT (opens in a new tab)
Gemini 3 Flash Preview (google/gemini-3-flash-preview) $1.13  $0.50  $3.00  At the lowest Lowest on InferIndex: $1.13. 1M Go to offer at NanoGPT (opens in a new tab)
Gemini 3.1 Flash Lite (google/gemini-3.1-flash-lite) $0.563 $0.25  $1.50  At the lowest Lowest on InferIndex: $0.563. 1M Go to offer at NanoGPT (opens in a new tab)
Gemini 3.1 Pro Preview (google/gemini-3.1-pro-preview) $4.50  $2.00  $12.00  At the lowest Lowest on InferIndex: $4.50. 1M Go to offer at NanoGPT (opens in a new tab)
Gemini 3.1 Pro Preview Custom Tools (google/gemini-3.1-pro-preview-customtools) $4.50  $2.00  $12.00  Cheapest. The lowest price on InferIndex for this model. 1M Go to offer at NanoGPT (opens in a new tab)
Gemini 3.5 Flash Lite (google/gemini-3.5-flash-lite) $0.85  $0.30  $2.50  At the lowest Lowest on InferIndex: $0.85. 1M Go to offer at NanoGPT (opens in a new tab)
Gemini 3.6 Flash (google/gemini-3.6-flash)
2 routes
 $1.50  $0.75  $3.75  At the lowest Lowest on InferIndex: $1.50. 1M Go to offer at NanoGPT (opens in a new tab)
NanoGPT $3.38  $1.50  $9.00  2.3× Lowest on InferIndex: $1.50. 1M Go to offer at NanoGPT (opens in a new tab)
Gemini 3.8 Flash (google/gemini-3.8-flash)
2 routes
 $1.50  $0.75  $3.75  At the lowest Lowest on InferIndex: $1.50. 1M Go to offer at NanoGPT (opens in a new tab)
NanoGPT $1.50  $0.75  $3.75  At the lowest Lowest on InferIndex: $1.50. 1M Go to offer at NanoGPT (opens in a new tab)
Gemini 4 Argon (google/gemini-4-argon) $4.00  $2.00  $10.00  +25% Lowest on InferIndex: $3.20. 1M Go to offer at NanoGPT (opens in a new tab)
Gemma 4 26B A4B (google/gemma-4-26b-a4b-it)Thinking: Thinking: a mode of the model+2Price drop observed: The blended price is 92% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026Price changes often: 20 price changes in 7 days. Over that period: input $0.01 – $0.09, output $0.03 – $0.30 per million tokens. An offer whose price changes this often is not selected as the cheapest. $0.015 $0.01  $0.03  – 262k Go to offer at NanoGPT (opens in a new tab)
Gemma 4 31B (google/gemma-4-31b-it)Thinking: Thinking: a mode of the model $0.16  $0.10  $0.34  +11% Lowest on InferIndex: $0.138. 262k Go to offer at NanoGPT (opens in a new tab)
Gemma 4 31B (google/gemma-4-31b-it) $0.205 $0.14  $0.40  +42% Lowest on InferIndex: $0.138. 262k Go to offer at NanoGPT (opens in a new tab)
MythoMax 13B (gryphe/mythomax-l2-13b) $0.10  $0.10  $0.10  +9% Lowest on InferIndex: $0.088. 4k Go to offer at NanoGPT (opens in a new tab)
Granite 4.2 8B (ibm-granite/granite-4.2-8b)Price drop observed: The blended price is 27% lower than before this drop; possibly temporary. · Price drop observed since Oct 26, 2026 $0.083 $0.06  $0.15  Cheapest. The lowest price on InferIndex for this model. 131k Go to offer at NanoGPT (opens in a new tab)
Mercury 2 (inception/mercury-2) $0.375 $0.25  $0.75  Cheapest. The lowest price on InferIndex for this model. 128k Go to offer at NanoGPT (opens in a new tab)
Mercury 3 (inception/mercury-3) $0.163 $0.10  $0.35  At the lowest Lowest on InferIndex: $0.163. 1M Go to offer at NanoGPT (opens in a new tab)
Ling 3.0 Flash (inclusionai/ling-3.0-flash)Thinking: Thinking: a mode of the model $0.111 $0.075 $0.22  3.5× Lowest on InferIndex: $0.032. 262k Go to offer at NanoGPT (opens in a new tab)
Ling 3.0 Flash VL (inclusionai/ling-3.0-flash-vl) $0.09  $0.06  $0.18  At the lowest Lowest on InferIndex: $0.09. 262k Go to offer at NanoGPT (opens in a new tab)
Ling 3.1 Flash (inclusionai/ling-3.1-flash) $0.111 $0.075 $0.22  Cheapest. The lowest price on InferIndex for this model. 262k Go to offer at NanoGPT (opens in a new tab)
Schematron V2 Small (inference-net/schematron-v2-small) $0.095 $0.05  $0.23  At the lowest Lowest on InferIndex: $0.095. 128k See pricing at NanoGPT (opens in a new tab)
Schematron V2 Turbo (inference-net/schematron-v2-turbo) $0.06  $0.03  $0.15  At the lowest Lowest on InferIndex: $0.06. 128k See pricing at NanoGPT (opens in a new tab)
LFM2.5-24B-A2B (liquid/lfm-2.5-24b-a2b) $0.213 $0.05  $0.70  Cheapest. The lowest price on InferIndex for this model. 128k Go to offer at NanoGPT (opens in a new tab)
LongCat 2.0 (meituan/longcat-2.0)Thinking: Thinking: a mode of the model $1.31  $0.75  $3.00  2.4× Lowest on InferIndex: $0.525. 1M Go to offer at NanoGPT (opens in a new tab)
LongCat 2.5 Preview (meituan/longcat-2.5-preview) $1.30  $0.75  $2.95  2.5× Lowest on InferIndex: $0.52. 1M Go to offer at NanoGPT (opens in a new tab)
Llama 3.1 8B Instruct (meta-llama/llama-3.1-8b-instruct)Price drop observed: The blended price is 60% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026 $0.025 $0.02  $0.04  At the lowest Lowest on InferIndex: $0.025. 131k Go to offer at NanoGPT (opens in a new tab)
Llama 3.2 3B Instruct (meta-llama/llama-3.2-3b-instruct) $0.035 $0.031 $0.049 Cheapest. The lowest price on InferIndex for this model. 131k Go to offer at NanoGPT (opens in a new tab)
Llama 3.3 70B Instruct (meta-llama/llama-3.3-70b-instruct) $0.095 $0.05  $0.23  Cheapest. The lowest price on InferIndex for this model. 131k Go to offer at NanoGPT (opens in a new tab)
Llama 4 Maverick (meta-llama/llama-4-maverick) $0.304 $0.188 $0.653 Cheapest. The lowest price on InferIndex for this model. 1M Go to offer at NanoGPT (opens in a new tab)
Llama 4 Scout (meta-llama/llama-4-scout) $0.179 $0.085 $0.46  +28% Lowest on InferIndex: $0.14. 328k Go to offer at NanoGPT (opens in a new tab)
Muse Glimmer 30B (meta/muse-glimmer-30b) $0.638 $0.35  $1.50  +82% Lowest on InferIndex: $0.35. 131k Go to offer at NanoGPT (opens in a new tab)
Muse Spark 1.1 (meta/muse-spark-1.1) $2.00  $1.25  $4.25  At the lowest Lowest on InferIndex: $2.00. 1M Go to offer at NanoGPT (opens in a new tab)
Muse Spark 1.2 (meta/muse-spark-1.2) $2.00  $1.25  $4.25  At the lowest Lowest on InferIndex: $2.00. 1M Go to offer at NanoGPT (opens in a new tab)
Muse Spark 1.2 Contributor (meta/muse-spark-1.2-contributor) $0.125 $0.10  $0.20  Cheapest. The lowest price on InferIndex for this model. 1M Go to offer at NanoGPT (opens in a new tab)
Muse Spark 1.3 (meta/muse-spark-1.3) $2.00  $1.25  $4.25  At the lowest Lowest on InferIndex: $2.00. 1M Go to offer at NanoGPT (opens in a new tab)
Muse Spark 1.3 Contributor (meta/muse-spark-1.3-contributor) $0.125 $0.10  $0.20  Cheapest. The lowest price on InferIndex for this model. 1M Go to offer at NanoGPT (opens in a new tab)
Muse Spark Open (meta/muse-spark-open) $2.00  $1.25  $4.25  At the lowest Lowest on InferIndex: $2.00. 1M Go to offer at NanoGPT (opens in a new tab)
Muse Wonder (meta/muse-wonder) $8.00  $4.00  $20.00  Cheapest. The lowest price on InferIndex for this model. 1M Go to offer at NanoGPT (opens in a new tab)
WizardLM-2 8x22B (microsoft/wizardlm-2-8x22b) $0.493 $0.493 $0.493 Cheapest. The lowest price on InferIndex for this model. 66k Go to offer at NanoGPT (opens in a new tab)
MiniMax-01 (minimax/minimax-01) $0.385 $0.139 $1.12  Cheapest. The lowest price on InferIndex for this model. 1M Go to offer at NanoGPT (opens in a new tab)
MiniMax M1 (minimax/minimax-m1) $0.438 $0.139 $1.33  Cheapest. The lowest price on InferIndex for this model. 1M Go to offer at NanoGPT (opens in a new tab)
MiniMax M2 (minimax/minimax-m2) $0.51  $0.17  $1.53  +21% Lowest on InferIndex: $0.40. 200k Go to offer at NanoGPT (opens in a new tab)
MiniMax M2-her (minimax/minimax-m2-her) $0.528 $0.302 $1.21  +0.6% Lowest on InferIndex: $0.525. 66k Go to offer at NanoGPT (opens in a new tab)
MiniMax M2.1 (minimax/minimax-m2.1)Price drop observed: The blended price is 36% lower than before this drop; possibly temporary. · Price drop observed since Oct 7, 2026 $0.525 $0.30  $1.20  +5% Lowest on InferIndex: $0.478. 200k Go to offer at NanoGPT (opens in a new tab)
MiniMax M2.5 (minimax/minimax-m2.5) $0.473 $0.27  $1.08  +2% Lowest on InferIndex: $0.44. 205k Go to offer at NanoGPT (opens in a new tab)
MiniMax M2.7 (minimax/minimax-m2.7)Price drop observed: The blended price is 33% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026 $0.368 $0.21  $0.84  +40% Lowest on InferIndex: $0.263. 205k Go to offer at NanoGPT (opens in a new tab)
MiniMax M2.7 (minimax/minimax-m2.7) $1.05  $0.60  $2.40  4× Lowest on InferIndex: $0.263. 205k Go to offer at NanoGPT (opens in a new tab)
MiniMax M3 (minimax/minimax-m3)Thinking: Thinking: a mode of the model+1Price drop observed: The blended price is 21% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026 $0.413 $0.23  $0.96  At the lowest Lowest on InferIndex: $0.413. 512k Go to offer at NanoGPT (opens in a new tab)
MiniMax M3.1 Flash (minimax/minimax-m3.1-flash) $0.263 $0.15  $0.60  2.8× Lowest on InferIndex: $0.088. 1M Go to offer at NanoGPT (opens in a new tab)
MiniMax-M1-80k (minimaxai/minimax-m1-80k) $1.06  $0.605 $2.42  +10% Lowest on InferIndex: $0.963. 1M Go to offer at NanoGPT (opens in a new tab)
Codestral 2508 (mistralai/codestral-2508) $0.45  $0.30  $0.90  Cheapest. The lowest price on InferIndex for this model. 256k Go to offer at NanoGPT (opens in a new tab)
Devstral 2 2512 (mistralai/devstral-2512) $0.65  $0.40  $1.40  Cheapest. The lowest price on InferIndex for this model. 262k Go to offer at NanoGPT (opens in a new tab)
Ministral 3 14B 2512 (mistralai/ministral-14b-2512) $0.20  $0.20  $0.20  Cheapest. The lowest price on InferIndex for this model. 262k Go to offer at NanoGPT (opens in a new tab)
Ministral 3 3B 2512 (mistralai/ministral-3b-2512) $0.10  $0.10  $0.10  Cheapest. The lowest price on InferIndex for this model. 131k Go to offer at NanoGPT (opens in a new tab)
Ministral 3 8B 2512 (mistralai/ministral-8b-2512) $0.15  $0.15  $0.15  Cheapest. The lowest price on InferIndex for this model. 262k Go to offer at NanoGPT (opens in a new tab)
Mistral Large (mistralai/mistral-large) $3.00  $2.01  $6.00  Cheapest. The lowest price on InferIndex for this model. 128k Go to offer at NanoGPT (opens in a new tab)
Mistral Large 4 (mistralai/mistral-large-4-0) $1.03  $0.68  $2.09  Cheapest. The lowest price on InferIndex for this model. 524k Go to offer at NanoGPT (opens in a new tab)
Mistral Medium 3 (mistralai/mistral-medium-3) $0.80  $0.40  $2.00  Cheapest. The lowest price on InferIndex for this model. 131k Go to offer at NanoGPT (opens in a new tab)
Mistral Medium 3.1 (mistralai/mistral-medium-3.1) $0.80  $0.40  $2.00  Cheapest. The lowest price on InferIndex for this model. 131k Go to offer at NanoGPT (opens in a new tab)
Mistral Nemo (mistralai/mistral-nemo) $0.105 $0.10  $0.121 5.6× Lowest on InferIndex: $0.018. 16k Go to offer at NanoGPT (opens in a new tab)
Saba (mistralai/mistral-saba) $0.298 $0.199 $0.595 Cheapest. The lowest price on InferIndex for this model. 33k Go to offer at NanoGPT (opens in a new tab)
Mistral Small 3 (mistralai/mistral-small-24b-instruct-2501) $0.173 $0.116 $0.347 3× Lowest on InferIndex: $0.058. 33k Go to offer at NanoGPT (opens in a new tab)
Mistral Small 4 (mistralai/mistral-small-2603)Thinking: Thinking: a mode of the model $0.65  $0.40  $1.40  2.4× Lowest on InferIndex: $0.263. 262k Go to offer at NanoGPT (opens in a new tab)
Mistral Small 3.1 24B (mistralai/mistral-small-3.1-24b-instruct) $0.15  $0.10  $0.30  Cheapest. The lowest price on InferIndex for this model. 128k Go to offer at NanoGPT (opens in a new tab)
Mistral Small 3.2 24B (mistralai/mistral-small-3.2-24b-instruct) $0.25  $0.20  $0.40  2.4× Lowest on InferIndex: $0.106. 128k Go to offer at NanoGPT (opens in a new tab)
Mixtral 8x22B Instruct (mistralai/mixtral-8x22b-instruct) $3.00  $2.00  $6.00  Cheapest. The lowest price on InferIndex for this model. 66k Go to offer at NanoGPT (opens in a new tab)
Kimi K2 0711 (moonshotai/kimi-k2)Price drop observed: The blended price is 29% lower than before this drop; possibly temporary. · Price drop observed since Oct 7, 2026 $0.75  $0.40  $1.80  Cheapest. The lowest price on InferIndex for this model. 256k Go to offer at NanoGPT (opens in a new tab)
Kimi K2 0711 (moonshotai/kimi-k2)Price drop observed: The blended price is 25% lower than before this drop; possibly temporary. · Price drop observed since Oct 7, 2026+1Priority tier: A different service tier, with its own speed and availability conditions. $0.75  $0.40  $1.80  Not compared: not the standard tier. Lowest blended: $0.75, standard tier. 131k Go to offer at NanoGPT (opens in a new tab)
Kimi K2 0905 (moonshotai/kimi-k2-0905)Price drop observed: The blended price is 29% lower than before this drop; possibly temporary. · Price drop observed since Oct 7, 2026 $0.75  $0.40  $1.80  Cheapest. The lowest price on InferIndex for this model. 262k Go to offer at NanoGPT (opens in a new tab)
Kimi K2 Thinking (moonshotai/kimi-k2-thinking) $1.08  $0.60  $2.50  +2% Lowest on InferIndex: $1.05. 262k Go to offer at NanoGPT (opens in a new tab)
Kimi K2.5 (moonshotai/kimi-k2.5)Thinking: Thinking: a mode of the model $0.781 $0.375 $2.00  – 262k Go to offer at NanoGPT (opens in a new tab)
Kimi K2.6 (moonshotai/kimi-k2.6)Thinking: Thinking: a mode of the model+2Price drop observed: The blended price is 32% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026Price changes often: 12 price changes in 7 days. Over that period: input $0.39 – $0.45, output $1.64 – $1.95 per million tokens. An offer whose price changes this often is not selected as the cheapest. $0.702 $0.39  $1.64  – 262k Go to offer at NanoGPT (opens in a new tab)
Kimi K2.7 Code (moonshotai/kimi-k2.7-code)Price drop observed: The blended price is 30% lower than before this drop; possibly temporary. · Price drop observed since Oct 12, 2026 $1.20  $0.60  $3.00  Cheapest. The lowest price on InferIndex for this model. 262k Go to offer at NanoGPT (opens in a new tab)
Kimi K2.7 Code (moonshotai/kimi-k2.7-code)Priority tier: A different service tier, with its own speed and availability conditions. $3.43  $1.90  $8.00  Not compared: not the standard tier. Lowest blended: $1.20, standard tier. 262k Go to offer at NanoGPT (opens in a new tab)
Kimi K3 (moonshotai/kimi-k3)Price drop observed: The blended price is 53% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026 $1.90  $0.15  $7.15  Cheapest. The lowest price on InferIndex for this model. 1M Go to offer at NanoGPT (opens in a new tab)
Kimi K3.1 Pro (moonshotai/kimi-k3.1-pro) $4.00  $2.00  $10.00  +11% Lowest on InferIndex: $3.60. 1M Go to offer at NanoGPT (opens in a new tab)
Kimi K3.1 Pro (moonshotai/kimi-k3.1-pro)Priority tier: A different service tier, with its own speed and availability conditions. $8.00  $4.00  $20.00  Not compared: not the standard tier. Lowest blended: $3.60, standard tier. 1M Go to offer at NanoGPT (opens in a new tab)
Nex-N2.5-Mini (nex-agi/nex-n2.5-mini) $0.044 $0.025 $0.10  Cheapest. The lowest price on InferIndex for this model. 262k Go to offer at NanoGPT (opens in a new tab)
Hermes 3 70B Instruct (nousresearch/hermes-3-llama-3.1-70b) $0.408 $0.408 $0.408 Cheapest. The lowest price on InferIndex for this model. 66k Go to offer at NanoGPT (opens in a new tab)
Hermes 4 405B (nousresearch/hermes-4-405b)Thinking: Thinking: a mode of the model $0.525 $0.30  $1.20  – 128k Go to offer at NanoGPT (opens in a new tab)
Nemotron 3 Nano 30B A3B (nvidia/nemotron-3-nano-30b-a3b) $0.298 $0.17  $0.68  3.4× Lowest on InferIndex: $0.088. 262k Go to offer at NanoGPT (opens in a new tab)
Nemotron 3 Super (nvidia/nemotron-3-super-120b-a12b)Thinking: Thinking: a mode of the model $0.10  $0.05  $0.25  – 262k Go to offer at NanoGPT (opens in a new tab)
Nemotron 3 Ultra (nvidia/nemotron-3-ultra-550b-a55b)Thinking: Thinking: a mode of the model $1.00  $0.50  $2.50  +8% Lowest on InferIndex: $0.925. 1M Go to offer at NanoGPT (opens in a new tab)
Nemotron 3.5 Content Safety (nvidia/nemotron-3.5-content-safety) $0.075 $0.05  $0.15  +20% Lowest on InferIndex: $0.063. 131k Go to offer at NanoGPT (opens in a new tab)
Nemotron 3.5 Lightning (nvidia/nemotron-3.5-lightning)Thinking: Thinking: a mode of the model $0.088 $0.05  $0.20  +70% Lowest on InferIndex: $0.049. 1M Go to offer at NanoGPT (opens in a new tab)
Nemotron 3.5 Super VL (nvidia/nemotron-3.5-super-vl) $0.238 $0.15  $0.50  +70% Lowest on InferIndex: $0.133. 262k Go to offer at NanoGPT (opens in a new tab)
GPT-4 Turbo (openai/gpt-4-turbo)Unverified. Withdrawn by its lab; this seller has not shown it for sale for 72 hours: listed, not designated cheapest · last confirmed 31 October 2026 $15.00  $10.00  $30.00  – 128k Go to offer at NanoGPT (opens in a new tab)
GPT-4.1 (openai/gpt-4.1) $3.50  $2.00  $8.00  At the lowest Lowest on InferIndex: $3.50. 1M Go to offer at NanoGPT (opens in a new tab)
GPT-4.1 Mini (openai/gpt-4.1-mini) $0.70  $0.40  $1.60  At the lowest Lowest on InferIndex: $0.70. 1M Go to offer at NanoGPT (opens in a new tab)
GPT-4.1 Nano (openai/gpt-4.1-nano)Unverified. Withdrawn by its lab; this seller has not shown it for sale for 72 hours: listed, not designated cheapest · last confirmed 30 October 2026 $0.175 $0.10  $0.40  – 1M Go to offer at NanoGPT (opens in a new tab)
GPT-4o (openai/gpt-4o) $4.38  $2.50  $10.00  At the lowest Lowest on InferIndex: $4.38. 128k Go to offer at NanoGPT (opens in a new tab)
GPT-4o (2024-08-06) (openai/gpt-4o-2024-08-06) $4.38  $2.50  $10.00  Cheapest. The lowest price on InferIndex for this model. 128k Go to offer at NanoGPT (opens in a new tab)
GPT-4o (2024-11-20) (openai/gpt-4o-2024-11-20) $4.38  $2.50  $10.00  At the lowest Lowest on InferIndex: $4.38. 128k Go to offer at NanoGPT (opens in a new tab)
GPT-4o-mini (openai/gpt-4o-mini) $0.263 $0.15  $0.60  At the lowest Lowest on InferIndex: $0.263. 128k Go to offer at NanoGPT (opens in a new tab)
GPT-5 (openai/gpt-5) $3.44  $1.25  $10.00  At the lowest Lowest on InferIndex: $3.44. 400k Go to offer at NanoGPT (opens in a new tab)
GPT-5 Mini (openai/gpt-5-mini) $0.688 $0.25  $2.00  At the lowest Lowest on InferIndex: $0.688. 400k Go to offer at NanoGPT (opens in a new tab)
GPT-5 Nano (openai/gpt-5-nano) $0.138 $0.05  $0.40  At the lowest Lowest on InferIndex: $0.138. 400k Go to offer at NanoGPT (opens in a new tab)
GPT-5 Pro (openai/gpt-5-pro) $41.25  $15.00  $120.00  At the lowest Lowest on InferIndex: $41.25. 400k Go to offer at NanoGPT (opens in a new tab)
GPT-5.1 (openai/gpt-5.1) $3.44  $1.25  $10.00  At the lowest Lowest on InferIndex: $3.44. 400k Go to offer at NanoGPT (opens in a new tab)
GPT-5.1-Codex (openai/gpt-5.1-codex)Unverified. Withdrawn by its lab; this seller has not shown it for sale for 72 hours: listed, not designated cheapest · last confirmed 31 October 2026 $3.44  $1.25  $10.00  – 400k Go to offer at NanoGPT (opens in a new tab)
GPT-5.1-Codex-Max (openai/gpt-5.1-codex-max)Unverified. Withdrawn by its lab; this seller has not shown it for sale for 72 hours: listed, not designated cheapest · last confirmed 31 October 2026 $6.88  $2.50  $20.00  – 400k Go to offer at NanoGPT (opens in a new tab)
GPT-5.1-Codex-Mini (openai/gpt-5.1-codex-mini)Unverified. Withdrawn by its lab; this seller has not shown it for sale for 72 hours: listed, not designated cheapest · last confirmed 31 October 2026 $0.688 $0.25  $2.00  – 400k Go to offer at NanoGPT (opens in a new tab)
GPT-5.2 (openai/gpt-5.2) $4.81  $1.75  $14.00  At the lowest Lowest on InferIndex: $4.81. 400k Go to offer at NanoGPT (opens in a new tab)
GPT-5.2-Codex (openai/gpt-5.2-codex)Unverified. Withdrawn by its lab; this seller has not shown it for sale for 72 hours: listed, not designated cheapest · last confirmed 31 October 2026 $4.81  $1.75  $14.00  – 400k Go to offer at NanoGPT (opens in a new tab)
GPT-5.3-Codex (openai/gpt-5.3-codex) $4.81  $1.75  $14.00  Cheapest. The lowest price on InferIndex for this model. 400k Go to offer at NanoGPT (opens in a new tab)
GPT-5.4 (openai/gpt-5.4) $5.63  $2.50  $15.00  At the lowest Lowest on InferIndex: $5.63. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-5.4 Mini (openai/gpt-5.4-mini) $1.69  $0.75  $4.50  At the lowest Lowest on InferIndex: $1.69. 400k Go to offer at NanoGPT (opens in a new tab)
GPT-5.4 Nano (openai/gpt-5.4-nano) $0.463 $0.20  $1.25  At the lowest Lowest on InferIndex: $0.463. 400k Go to offer at NanoGPT (opens in a new tab)
GPT-5.5 (openai/gpt-5.5) $11.25  $5.00  $30.00  At the lowest Lowest on InferIndex: $11.25. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-5.6 Luna (openai/gpt-5.6-luna) $0.45  $0.20  $1.20  At the lowest Lowest on InferIndex: $0.45. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-5.6 Luna Pro (openai/gpt-5.6-luna-pro) $0.45  $0.20  $1.20  Cheapest. The lowest price on InferIndex for this model. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-5.6 Sol (openai/gpt-5.6-sol)Below the lab's list price: Resold below the lab's list price (−50% vs lab list price), without a declared discount. $4.00  $2.00  $10.00  Cheapest. The lowest price on InferIndex for this model. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-5.6 Sol Pro (openai/gpt-5.6-sol-pro) $4.00  $2.00  $10.00  Cheapest. The lowest price on InferIndex for this model. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-5.6 Terra (openai/gpt-5.6-terra) $4.50  $2.00  $12.00  At the lowest Lowest on InferIndex: $4.50. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-5.6 Terra Pro (openai/gpt-5.6-terra-pro) $4.50  $2.00  $12.00  Cheapest. The lowest price on InferIndex for this model. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-6 Astra (openai/gpt-6-astra) $20.00  $10.00  $50.00  At the lowest Lowest on InferIndex: $20.00. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-6 Astra Pro (openai/gpt-6-astra-pro) $20.00  $10.00  $50.00  At the lowest Lowest on InferIndex: $20.00. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-6 Luna (openai/gpt-6-luna) $0.20  $0.10  $0.50  At the lowest Lowest on InferIndex: $0.20. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-6 Luna Pro (openai/gpt-6-luna-pro) $0.20  $0.10  $0.50  Cheapest. The lowest price on InferIndex for this model. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-6 Sol (openai/gpt-6-sol) $4.00  $2.00  $10.00  At the lowest Lowest on InferIndex: $4.00. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-6 Sol Pro (openai/gpt-6-sol-pro) $4.00  $2.00  $10.00  Cheapest. The lowest price on InferIndex for this model. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-6.1 Sol (openai/gpt-6.1-sol) $4.00  $2.00  $10.00  At the lowest Lowest on InferIndex: $4.00. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-6.1 Sol Pro (openai/gpt-6.1-sol-pro) $4.00  $2.00  $10.00  Cheapest. The lowest price on InferIndex for this model. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-6.1 Terra (openai/gpt-6.1-terra) $2.00  $1.00  $5.00  At the lowest Lowest on InferIndex: $2.00. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT-6.1 Terra Pro (openai/gpt-6.1-terra-pro) $2.00  $1.00  $5.00  Cheapest. The lowest price on InferIndex for this model. 1.1M Go to offer at NanoGPT (opens in a new tab)
GPT Chat Latest (openai/gpt-chat-latest) $4.00  $2.00  $10.00  Cheapest. The lowest price on InferIndex for this model. 1.1M See pricing at NanoGPT (opens in a new tab)
gpt-oss-120b (openai/gpt-oss-120b)Price drop observed: The blended price is 87% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026 $0.06  $0.03  $0.15  Cheapest. The lowest price on InferIndex for this model. 128k Go to offer at NanoGPT (opens in a new tab)
gpt-oss-20b (openai/gpt-oss-20b)Price drop observed: The blended price is 82% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026 $0.04  $0.02  $0.10  +5% Lowest on InferIndex: $0.036. 131k Go to offer at NanoGPT (opens in a new tab)
gpt-oss-safeguard-20b (openai/gpt-oss-safeguard-20b) $0.131 $0.075 $0.30  +28% Lowest on InferIndex: $0.103. 128k Go to offer at NanoGPT (opens in a new tab)
o1 (openai/o1)Unverified. Withdrawn by its lab; this seller has not shown it for sale for 72 hours: listed, not designated cheapest · last confirmed 31 October 2026 $26.25  $15.00  $60.00  – 200k Go to offer at NanoGPT (opens in a new tab)
o1-pro (openai/o1-pro)Unverified. Withdrawn by its lab; this seller has not shown it for sale for 72 hours: listed, not designated cheapest · last confirmed 31 October 2026 $262.50  $150.00  $600.00  – 200k Go to offer at NanoGPT (opens in a new tab)
o3 (openai/o3) $3.50  $2.00  $8.00  At the lowest Lowest on InferIndex: $3.50. 200k Go to offer at NanoGPT (opens in a new tab)
o3 Mini (openai/o3-mini)Unverified. Withdrawn by its lab; this seller has not shown it for sale for 72 hours: listed, not designated cheapest · last confirmed 31 October 2026 $1.93  $1.10  $4.40  – 200k Go to offer at NanoGPT (opens in a new tab)
o3 Mini High (openai/o3-mini-high) $1.93  $1.10  $4.40  Cheapest. The lowest price on InferIndex for this model. 200k Go to offer at NanoGPT (opens in a new tab)
o3 Pro (openai/o3-pro) $38.50  $22.00  $88.00  +10% Lowest on InferIndex: $35.00. 200k Go to offer at NanoGPT (opens in a new tab)
o4 Mini (openai/o4-mini)Unverified. Withdrawn by its lab; this seller has not shown it for sale for 72 hours: listed, not designated cheapest · last confirmed 31 October 2026 $1.93  $1.10  $4.40  – 200k Go to offer at NanoGPT (opens in a new tab)
o4 Mini High (openai/o4-mini-high) $1.93  $1.10  $4.40  Cheapest. The lowest price on InferIndex for this model. 200k Go to offer at NanoGPT (opens in a new tab)
Particle-1 (particle-ai/particle-1) $0.438 $0.25  $1.00  2.6× Lowest on InferIndex: $0.163. 1M Go to offer at NanoGPT (opens in a new tab)
Perceptron Mk1 (perceptron/perceptron-mk1) $0.488 $0.15  $1.50  Cheapest. The lowest price on InferIndex for this model. 33k Go to offer at NanoGPT (opens in a new tab)
Perceptron Mk1.5 (perceptron/perceptron-mk1.5) $0.488 $0.15  $1.50  Cheapest. The lowest price on InferIndex for this model. 37k Go to offer at NanoGPT (opens in a new tab)
Laguna S 2.1 (poolside/laguna-s-2.1)Thinking: Thinking: a mode of the model $0.125 $0.10  $0.20  +11% Lowest on InferIndex: $0.113. 1M Go to offer at NanoGPT (opens in a new tab)
Qwen2.5 72B Instruct (qwen/qwen-2.5-72b-instruct) $0.37  $0.36  $0.40  +29% Lowest on InferIndex: $0.273. 131k Go to offer at NanoGPT (opens in a new tab)
Qwen2.5 Coder 32B Instruct (qwen/qwen-2.5-coder-32b-instruct) $0.201 $0.201 $0.201 2.1× Lowest on InferIndex: $0.095. 32k Go to offer at NanoGPT (opens in a new tab)
Qwen-Plus (qwen/qwen-plus) $0.60  $0.40  $1.20  3.8× Lowest on InferIndex: $0.158. 996k Go to offer at NanoGPT (opens in a new tab)
Qwen2.5 VL 72B Instruct (qwen/qwen2.5-vl-72b-instruct) $0.70  $0.70  $0.70  Cheapest. The lowest price on InferIndex for this model. 32k Go to offer at NanoGPT (opens in a new tab)
Qwen3 14B (qwen/qwen3-14b) $0.12  $0.08  $0.24  +25% Lowest on InferIndex: $0.091. 41k Go to offer at NanoGPT (opens in a new tab)
Qwen3 235B A22B (qwen/qwen3-235b-a22b)Price drop observed: The blended price is 56% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026 $0.153 $0.088 $0.35  Cheapest. The lowest price on InferIndex for this model. 262k Go to offer at NanoGPT (opens in a new tab)
Qwen3 235B A22B Instruct 2507 (qwen/qwen3-235b-a22b-2507)Price drop observed: The blended price is 31% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026 $0.153 $0.088 $0.35  +86% Lowest on InferIndex: $0.078. 262k Go to offer at NanoGPT (opens in a new tab)
Qwen3 235B A22B Thinking 2507 (qwen/qwen3-235b-a22b-thinking-2507) $0.35  $0.30  $0.50  Cheapest. The lowest price on InferIndex for this model. 131k Go to offer at NanoGPT (opens in a new tab)
Qwen3 30B A3B (qwen/qwen3-30b-a3b) $0.15  $0.10  $0.30  +25% Lowest on InferIndex: $0.114. 41k Go to offer at NanoGPT (opens in a new tab)
Qwen3 30B A3B Instruct 2507 (qwen/qwen3-30b-a3b-instruct-2507) $0.275 $0.20  $0.50  +93% Lowest on InferIndex: $0.143. 256k Go to offer at NanoGPT (opens in a new tab)
Qwen3 32B (qwen/qwen3-32b)Price drop observed: The blended price is 20% lower than before this drop; possibly temporary. · Price drop observed since Oct 26, 2026 $0.12  $0.08  $0.24  Cheapest. The lowest price on InferIndex for this model. 41k Go to offer at NanoGPT (opens in a new tab)
Qwen3 8B (qwen/qwen3-8b) $0.47  $0.47  $0.47  4.8× Lowest on InferIndex: $0.098. 41k Go to offer at NanoGPT (opens in a new tab)
Qwen3 Coder 480B A35B (qwen/qwen3-coder) $0.223 $0.13  $0.50  Cheapest. The lowest price on InferIndex for this model. 262k Go to offer at NanoGPT (opens in a new tab)
Qwen3 Coder 30B A3B Instruct (qwen/qwen3-coder-30b-a3b-instruct) $0.175 $0.10  $0.40  +35% Lowest on InferIndex: $0.123. 128k Go to offer at NanoGPT (opens in a new tab)
Qwen3 Coder Flash (qwen/qwen3-coder-flash) $0.60  $0.30  $1.50  2.4× Lowest on InferIndex: $0.252. 128k Go to offer at NanoGPT (opens in a new tab)
Qwen3 Coder Next (qwen/qwen3-coder-next)Price drop observed: The blended price is 26% lower than before this drop; possibly temporary. · Price drop observed since Oct 9, 2026 $0.388 $0.25  $0.803 +27% Lowest on InferIndex: $0.29. 262k Go to offer at NanoGPT (opens in a new tab)
Qwen3 Next 80B A3B Instruct (qwen/qwen3-next-80b-a3b-instruct) $0.343 $0.09  $1.10  At the lowest Lowest on InferIndex: $0.343. 262k Go to offer at NanoGPT (opens in a new tab)
Qwen3 Next 80B A3B Thinking (qwen/qwen3-next-80b-a3b-thinking) $0.275 $0.15  $0.65  Cheapest. The lowest price on InferIndex for this model. 256k Go to offer at NanoGPT (opens in a new tab)
Qwen3 VL 235B A22B Instruct (qwen/qwen3-vl-235b-a22b-instruct) $0.70  $0.30  $1.90  +89% Lowest on InferIndex: $0.37. 131k Go to offer at NanoGPT (opens in a new tab)
Qwen3 VL 235B A22B Thinking (qwen/qwen3-vl-235b-a22b-thinking) $1.88  $0.50  $6.00  +9% Lowest on InferIndex: $1.72. – Go to offer at NanoGPT (opens in a new tab)
Qwen3.5-122B-A10B (qwen/qwen3.5-122b-a10b)Thinking: Thinking: a mode of the model+1Price drop observed: The blended price is 41% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026 $0.715 $0.26  $2.08  2.3× Lowest on InferIndex: $0.316. 262k Go to offer at NanoGPT (opens in a new tab)
Qwen3.5-27B (qwen/qwen3.5-27b)Thinking: Thinking: a mode of the model $0.688 $0.25  $2.00  2.9× Lowest on InferIndex: $0.237. 260k Go to offer at NanoGPT (opens in a new tab)
Qwen3.5-35B-A3B (qwen/qwen3.5-35b-a3b)Thinking: Thinking: a mode of the model+1Price drop observed: The blended price is 43% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026 $0.355 $0.14  $1.00  2.3× Lowest on InferIndex: $0.158. 260k Go to offer at NanoGPT (opens in a new tab)
Qwen3.5 397B A17B (qwen/qwen3.5-397b-a17b)Thinking: Thinking: a mode of the model+1Price drop observed: The blended price is 35% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026 $0.878 $0.39  $2.34  2.3× Lowest on InferIndex: $0.387. 262k Go to offer at NanoGPT (opens in a new tab)
Qwen3.5-9B (qwen/qwen3.5-9b) $0.075 $0.05  $0.15  Cheapest. The lowest price on InferIndex for this model. 262k Go to offer at NanoGPT (opens in a new tab)
Qwen3.5 Flash (qwen/qwen3.5-flash)Thinking: Thinking: a mode of the model $0.175 $0.10  $0.40  +87% Lowest on InferIndex: $0.094. 992k Go to offer at NanoGPT (opens in a new tab)
Qwen3.5 Plus (qwen/qwen3.5-plus)Thinking: Thinking: a mode of the model $0.90  $0.40  $2.40  3.5× Lowest on InferIndex: $0.258. 984k Go to offer at NanoGPT (opens in a new tab)
Qwen3.6 27B (qwen/qwen3.6-27b)Thinking: Thinking: a mode of the model $0.712 $0.203 $2.24  +88% Lowest on InferIndex: $0.36. 262k Go to offer at NanoGPT (opens in a new tab)
Qwen3.6 35B A3B (qwen/qwen3.6-35b-a3b)Thinking: Thinking: a mode of the model $0.284 $0.112 $0.80  +80% Lowest on InferIndex: $0.158. 1M Go to offer at NanoGPT (opens in a new tab)
Qwen3.6 Flash (qwen/qwen3.6-flash) $0.433 $0.19  $1.16  +17% Lowest on InferIndex: $0.371. 992k Go to offer at NanoGPT (opens in a new tab)
Qwen3.6 Max Preview (qwen/qwen3.6-max-preview) $2.34  $1.04  $6.24  Cheapest. The lowest price on InferIndex for this model. 246k Go to offer at NanoGPT (opens in a new tab)
Qwen3.6 Plus (qwen/qwen3.6-plus) $0.731 $0.325 $1.95  +18% Lowest on InferIndex: $0.62. 992k Go to offer at NanoGPT (opens in a new tab)
Qwen3.7 Flash (qwen/qwen3.7-flash)Thinking: Thinking: a mode of the model $0.055 $0.03  $0.13  +13% Lowest on InferIndex: $0.049. 984k Go to offer at NanoGPT (opens in a new tab)
Qwen3.7 Max (qwen/qwen3.7-max)Thinking: Thinking: a mode of the model+1Price drop observed: The blended price is 41% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026 $2.21  $1.48  $4.43  +64% Lowest on InferIndex: $1.35. 1M Go to offer at NanoGPT (opens in a new tab)
Qwen3.7 Plus (qwen/qwen3.7-plus)Thinking: Thinking: a mode of the model $0.70  $0.40  $1.60  +45% Lowest on InferIndex: $0.482. 984k Go to offer at NanoGPT (opens in a new tab)
Qwen3.8 27B (qwen/qwen3.8-27b)Thinking: Thinking: a mode of the model $0.288 $0.15  $0.70  2.1× Lowest on InferIndex: $0.14. 1M Go to offer at NanoGPT (opens in a new tab)
Qwen3.8 Flash (qwen/qwen3.8-flash) $0.21  $0.14  $0.42  +16% Lowest on InferIndex: $0.18. 1M Go to offer at NanoGPT (opens in a new tab)
Qwen3.8 Max (qwen/qwen3.8-max)Thinking: Thinking: a mode of the model $3.00  $2.00  $6.00  +24% Lowest on InferIndex: $2.31. 991k Go to offer at NanoGPT (opens in a new tab)
Qwen3.8 Max (0902) (qwen/qwen3.8-max-0902) $3.00  $2.00  $6.00  +21% Lowest on InferIndex: $2.48. 992k Go to offer at NanoGPT (opens in a new tab)
Qwen3.8 Max Prime (qwen/qwen3.8-max-prime) $6.00  $4.00  $12.00  Cheapest. The lowest price on InferIndex for this model. 1M Go to offer at NanoGPT (opens in a new tab)
Qwen3.8 Omni Flash (qwen/qwen3.8-omni-flash) $0.23  $0.15  $0.47  +28% Lowest on InferIndex: $0.18. 992k Go to offer at NanoGPT (opens in a new tab)
Fugu Max (sakana/fugu-max) $3.00  $2.00  $6.00  At the lowest Lowest on InferIndex: $3.00. 1M Go to offer at NanoGPT (opens in a new tab)
Fugu Ultra (sakana/fugu-ultra) $11.25  $5.00  $30.00  Cheapest. The lowest price on InferIndex for this model. 1M Go to offer at NanoGPT (opens in a new tab)
L3-8B-Stheno-v3.2 (sao10k/l3-8b-stheno-v3.2) $0.201 $0.201 $0.201 4× Lowest on InferIndex: $0.05. 16k Go to offer at NanoGPT (opens in a new tab)
Llama 3.1 Euryale 70B v2.2 (sao10k/l3.1-euryale-70b) $0.319 $0.306 $0.357 Cheapest. The lowest price on InferIndex for this model. 20k Go to offer at NanoGPT (opens in a new tab)
Llama 3.3 Euryale 70B (sao10k/l3.3-euryale-70b) $0.493 $0.493 $0.493 Cheapest. The lowest price on InferIndex for this model. 20k Go to offer at NanoGPT (opens in a new tab)
Bielik-11B-v3.0-Instruct (speakleash/bielik-11b-v3.0-instruct) $0.48  $0.48  $0.48  +91% Lowest on InferIndex: $0.251. 33k Go to offer at NanoGPT (opens in a new tab)
Step 3.5 Flash (stepfun/step-3.5-flash) $0.15  $0.10  $0.30  At the lowest Lowest on InferIndex: $0.15. 262k Go to offer at NanoGPT (opens in a new tab)
Step 3.7 Flash (stepfun/step-3.7-flash)Thinking: Thinking: a mode of the model $0.438 $0.20  $1.15  At the lowest Lowest on InferIndex: $0.438. 262k Go to offer at NanoGPT (opens in a new tab)
Step 5 Preview (stepfun/step-5-preview) $1.43  $1.00  $2.70  At the lowest Lowest on InferIndex: $1.43. 1M Go to offer at NanoGPT (opens in a new tab)
Hy3 (tencent/hy3) $0.115 $0.066 $0.26  Cheapest. The lowest price on InferIndex for this model. 262k Go to offer at NanoGPT (opens in a new tab)
Hy4 preview (tencent/hy4-preview)Price changes often: 19 price changes in 7 days. Over that period: input $0.751 – $0.834, output $2.25 – $2.50 per million tokens. An offer whose price changes this often is not selected as the cheapest. $1.25  $0.834 $2.50  At the lowest Lowest on InferIndex: $1.25. 1M Go to offer at NanoGPT (opens in a new tab)
Cydonia 24B V4.1 (thedrummer/cydonia-24b-v4.1)Price drop observed: The blended price is 13% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026 $0.35  $0.30  $0.50  +72% Lowest on InferIndex: $0.204. 131k Go to offer at NanoGPT (opens in a new tab)
UnslopNemo 12B (thedrummer/unslopnemo-12b) $0.493 $0.493 $0.493 2.2× Lowest on InferIndex: $0.225. 8k Go to offer at NanoGPT (opens in a new tab)
Inkling (thinkingmachines/inkling)Thinking: Thinking: a mode of the model $1.76  $1.00  $4.05  +2% Lowest on InferIndex: $1.73. 1M Go to offer at NanoGPT (opens in a new tab)
Inkling Small (thinkingmachines/inkling-small)Thinking: Thinking: a mode of the model $0.638 $0.45  $1.20  +21% Lowest on InferIndex: $0.525. 524k Go to offer at NanoGPT (opens in a new tab)
Jev 1.13 (typesafe/jev-1.13) $0.032 $0.042 $0.00  At the lowest Lowest on InferIndex: $0.032. 32k See pricing at NanoGPT (opens in a new tab)
ReMM SLERP 13B (undi95/remm-slerp-l2-13b) $0.901 $0.799 $1.21  2.2× Lowest on InferIndex: $0.413. 6k Go to offer at NanoGPT (opens in a new tab)
Solar Mini 4 (upstage/solar-mini4)Thinking: Thinking: a mode of the model $0.088 $0.05  $0.20  – 524k Go to offer at NanoGPT (opens in a new tab)
Solar Pro 3 (upstage/solar-pro-3) $0.263 $0.15  $0.60  Cheapest. The lowest price on InferIndex for this model. 131k Go to offer at NanoGPT (opens in a new tab)
Solar Pro 4 (upstage/solar-pro4)Thinking: Thinking: a mode of the model $0.053 $0.03  $0.12  – 524k Go to offer at NanoGPT (opens in a new tab)
Grok 4.20 (x-ai/grok-4.20)Price drop observed: The blended price is 48% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026 $1.56  $1.25  $2.50  Cheapest. The lowest price on InferIndex for this model. 2M Go to offer at NanoGPT (opens in a new tab)
Grok 4.20 Multi-Agent (x-ai/grok-4.20-multi-agent)Price drop observed: The blended price is 48% lower than before this drop; possibly temporary. · Price drop observed since Oct 18, 2026 $1.56  $1.25  $2.50  Cheapest. The lowest price on InferIndex for this model. 2M Go to offer at NanoGPT (opens in a new tab)
Grok 4.3 (x-ai/grok-4.3) $1.56  $1.25  $2.50  At the lowest Lowest on InferIndex: $1.56. 1M Go to offer at NanoGPT (opens in a new tab)
Grok 4.5 (x-ai/grok-4.5) $3.00  $2.00  $6.00  At the lowest Lowest on InferIndex: $3.00. 500k Go to offer at NanoGPT (opens in a new tab)
Grok 4.6 (x-ai/grok-4.6) $3.00  $2.00  $6.00  At the lowest Lowest on InferIndex: $3.00. 500k Go to offer at NanoGPT (opens in a new tab)
Grok 4.7 (x-ai/grok-4.7) $3.00  $2.00  $6.00  At the lowest Lowest on InferIndex: $3.00. 500k Go to offer at NanoGPT (opens in a new tab)
Grok Build 0.1 (x-ai/grok-build-0.1) $1.25  $1.00  $2.00  At the lowest Lowest on InferIndex: $1.25. 256k Go to offer at NanoGPT (opens in a new tab)
MiMo-V2.5 (xiaomi/mimo-v2.5)Thinking: Thinking: a mode of the model $0.175 $0.14  $0.28  +18% Lowest on InferIndex: $0.149. 1M Go to offer at NanoGPT (opens in a new tab)
MiMo-V2.5-Pro (xiaomi/mimo-v2.5-pro)Thinking: Thinking: a mode of the model $0.544 $0.435 $0.87  +43% Lowest on InferIndex: $0.381. 1M Go to offer at NanoGPT (opens in a new tab)
MiMo-V2.6-Flash (xiaomi/mimo-v2.6-flash) $0.175 $0.14  $0.28  +48% Lowest on InferIndex: $0.112. 1M Go to offer at NanoGPT (opens in a new tab)
MiMo-V2.6-Pro (xiaomi/mimo-v2.6-pro) $0.544 $0.435 $0.87  +18% Lowest on InferIndex: $0.462. 1M Go to offer at NanoGPT (opens in a new tab)
MiMo-V2.6-Pro-UltraSpeed (xiaomi/mimo-v2.6-pro-ultraspeed) $5.44  $4.35  $8.70  At the lowest Lowest on InferIndex: $5.44. 1M Go to offer at NanoGPT (opens in a new tab)
GLM 4.5 (z-ai/glm-4.5)Thinking: Thinking: a mode of the model $0.55  $0.30  $1.30  – 128k Go to offer at NanoGPT (opens in a new tab)
GLM 4.5 Air (z-ai/glm-4.5-air)Thinking: Thinking: a mode of the model $0.31  $0.13  $0.85  +88% Lowest on InferIndex: $0.165. 128k Go to offer at NanoGPT (opens in a new tab)
GLM 4.5V (z-ai/glm-4.5v)Thinking: Thinking: a mode of the model $0.90  $0.60  $1.80  2× Lowest on InferIndex: $0.451. 66k Go to offer at NanoGPT (opens in a new tab)
GLM 4.6 (z-ai/glm-4.6)Thinking: Thinking: a mode of the model $0.875 $0.50  $2.00  +15% Lowest on InferIndex: $0.76. 200k Go to offer at NanoGPT (opens in a new tab)
GLM 4.6 (z-ai/glm-4.6) $1.50  $1.00  $3.00  +97% Lowest on InferIndex: $0.76. 205k Go to offer at NanoGPT (opens in a new tab)
GLM 4.6 (z-ai/glm-4.6)Thinking: Thinking: a mode of the model $1.50  $1.00  $3.00  +97% Lowest on InferIndex: $0.76. 205k Go to offer at NanoGPT (opens in a new tab)
GLM 4.6V (z-ai/glm-4.6v) $0.45  $0.30  $0.90  2.1× Lowest on InferIndex: $0.218. 128k Go to offer at NanoGPT (opens in a new tab)
GLM 4.7 (z-ai/glm-4.7)Thinking: Thinking: a mode of the model $0.783 $0.40  $1.93  +49% Lowest on InferIndex: $0.526. 200k Go to offer at NanoGPT (opens in a new tab)
GLM 4.7 Flash (z-ai/glm-4.7-flash)Thinking: Thinking: a mode of the model $0.153 $0.07  $0.40  +5% Lowest on InferIndex: $0.145. 200k Go to offer at NanoGPT (opens in a new tab)
GLM 5 (z-ai/glm-5)Thinking: Thinking: a mode of the model $0.925 $0.60  $1.90  – 200k Go to offer at NanoGPT (opens in a new tab)
GLM 5 Turbo (z-ai/glm-5-turbo) $1.90  $1.20  $4.00  +41% Lowest on InferIndex: $1.35. 203k Go to offer at NanoGPT (opens in a new tab)
GLM 5.1 (z-ai/glm-5.1)Thinking: Thinking: a mode of the model $1.15  $0.70  $2.50  – 200k Go to offer at NanoGPT (opens in a new tab)
GLM 5.2 (z-ai/glm-5.2)Thinking: Thinking: a mode of the model+2Price drop observed: The blended price is 43% lower than before this drop; possibly temporary. · Price drop observed since Oct 29, 2026Price changes often: 13 price changes in 7 days. Over that period: input $0.086 – $0.42, output $0.594 – $2.21 per million tokens. An offer whose price changes this often is not selected as the cheapest. $0.415 $0.086 $1.40  – 1M Go to offer at NanoGPT (opens in a new tab)
GLM 5.3 (z-ai/glm-5.3)Thinking: Thinking: a mode of the model+1Price drop observed: The blended price is 53% lower than before this drop; possibly temporary. · Price drop observed since Oct 8, 2026 $0.725 $0.60  $1.10  +60% Lowest on InferIndex: $0.43. 1M Go to offer at NanoGPT (opens in a new tab)
GLM 5.3 Flash (z-ai/glm-5.3-flash) $0.15  $0.10  $0.30  2.5× Lowest on InferIndex: $0.059. 1M Go to offer at NanoGPT (opens in a new tab)
GLM 5V Turbo (z-ai/glm-5v-turbo)Thinking: Thinking: a mode of the model $1.90  $1.20  $4.00  +41% Lowest on InferIndex: $1.34. 203k Go to offer at NanoGPT (opens in a new tab)

NanoGPT Every offer of this provider is sold by NanoGPT.

Show the first 50 only

One row per offer, at its cheapest route at this provider; the other routes (hosted API, aggregators) open on the row. Blended = (3 × input + output) / 4, per million tokens. Prices in USD, converted at the ECB rate when the provider bills in another currency.