---
title: "Price spreads worth shopping · Undominated.ai"
canonical: https://undominated.ai/spreads/
description: "45 models with an actionable multi-seller spread at equal-or-better precision, as of 2026-10-06. Distinct sellers only — not a vendor’s own service tiers."
---

# Price spreads worth shopping · Undominated.ai

> 45 models with an actionable multi-seller spread at equal-or-better precision, as of 2026-10-06. Distinct sellers only — not a vendor’s own service tiers.

# Spreads worth shopping

Ranked by actionable input-price spread across distinct sellers at equal-or-better serving precision, where the cheaper seller is also cheaper on the balanced blend (3 parts input to 1 part output). A vendor’s own service tiers are not competition. Unpriced models are excluded. Unrated is not scored zero.

 On this page [What was excluded](#ex-h)[Worth shopping](#worth-h)[Precision trades](#trade-h)

45 models

As of 2026-10-06 . Condition: equal-or-better declared precision; cheaper lower-precision is not a saving; the cheaper input seller is also cheaper on the balanced blend (3 input : 1 output).

## Worth shopping

Spread is the dearest ÷ cheapest input price among sellers at the reference precision or better, listed only where the cheaper seller is also cheaper on the balanced blend. Cheaper lower-precision endpoints do not enter this table as a saving.

| Model | Input spread | Sellers | Cheapest input | Dearest input | Precision |
| --- | --- | --- | --- | --- | --- |
| [gpt-oss-120b](https://undominated.ai/models/openai__gpt-oss-120b/) | 11.67× | 5 | $0.030 DekaLLM | $0.350 Cerebras | bf16 |
| [GLM 5.3](https://undominated.ai/models/z-ai__glm-5.3/) lower-quant also listed | 11.05× | 11 | $0.190 AkashML | $2.10 BaseTen | fp8 |
| [DeepSeek V4 Flash 0731](https://undominated.ai/models/deepseek__deepseek-v4-flash-0731/) lower-quant also listed | 10× | 10 | $0.044 StreamLake | $0.440 Baidu | fp8 |
| [DeepSeek V4 Pro 0423](https://undominated.ai/models/deepseek__deepseek-v4-pro/) lower-quant also listed | 8.09× | 8 | $0.209 StreamLake | $1.69 Baidu | fp8 |
| [Qwen3.8 27B](https://undominated.ai/models/qwen__qwen3.8-27b/) lower-quant also listed | 6.6× | 2 | $0.150 DeepInfra | $0.990 Cerebras | bf16 |
| [DeepSeek V4.1 Flash](https://undominated.ai/models/deepseek__deepseek-v4.1-flash/) lower-quant also listed | 5.66× | 13 | $0.053 Morph | $0.300 Venice | fp8 |
| [Llama 3.3 70B Instruct](https://undominated.ai/models/meta-llama__llama-3.3-70b-instruct/) lower-quant also listed | 5.26× | 2 | $0.135 Novita | $0.710 CoreWeave | bf16 |
| [MythoMax 13B](https://undominated.ai/models/gryphe__mythomax-l2-13b/) | 5× | 2 | $0.080 Parasail | $0.400 DeepInfra | fp16 |
| [GLM 5.2](https://undominated.ai/models/z-ai__glm-5.2/) lower-quant also listed | 4.53× | 12 | $0.309 Morph | $1.40 Z.AI | fp8 |
| [DeepSeek V4 Flash 0423](https://undominated.ai/models/deepseek__deepseek-v4-flash/) lower-quant also listed | 4.52× | 9 | $0.042 StreamLake | $0.190 Mancer 2 | fp8 |
| [MiMo-V2.5](https://undominated.ai/models/xiaomi__mimo-v2.5/) | 3.36× | 4 | $0.119 GMICloud | $0.400 Venice | fp8 |
| [Ling 3.0 Flash VL](https://undominated.ai/models/inclusionai__ling-3.0-flash-vl/) | 2.86× | 2 | $0.021 Novita | $0.060 DeepInfra | bf16 |
| [GLM 5.3 Flash](https://undominated.ai/models/z-ai__glm-5.3-flash/) lower-quant also listed | 2.68× | 11 | $0.084 Novita | $0.225 Inceptron | fp8 |
| [Qwen3.6 35B A3B](https://undominated.ai/models/qwen__qwen3.6-35b-a3b/) lower-quant also listed | 2.5× | 7 | $0.100 AkashML | $0.250 CoreWeave | fp8 |
| [DeepSeek V3.1](https://undominated.ai/models/deepseek__deepseek-chat-v3.1/) lower-quant also listed | 2.41× | 3 | $0.270 SiliconFlow | $0.650 SambaNova | fp8 |
| [Qwen3 235B A22B Instruct 2507](https://undominated.ai/models/qwen__qwen3-235b-a22b-2507/) | 2.29× | 6 | $0.088 GMICloud | $0.200 Nebius | fp8 |
| [Gemma 4 26B A4B](https://undominated.ai/models/google__gemma-4-26b-a4b-it/) lower-quant also listed | 2.21× | 7 | $0.059 Io Net | $0.130 Novita | bf16 |
| [DeepSeek V4 Flash Vision Exp](https://undominated.ai/models/deepseek__deepseek-v4-flash-vision-exp/) | 2.04× | 3 | $0.216 DeepInfra | $0.440 SiliconFlow | fp8 |
| [DeepSeek V3.2](https://undominated.ai/models/deepseek__deepseek-v3.2/) | 1.77× | 5 | $0.209 GMICloud | $0.371 Alibaba | fp8 |
| [Qwen3 32B](https://undominated.ai/models/qwen__qwen3-32b/) | 1.75× | 3 | $0.080 DeepInfra | $0.140 SiliconFlow | fp8 |
| [Llama 3.1 Euryale 70B v2.2](https://undominated.ai/models/sao10k__l3.1-euryale-70b/) | 1.71× | 2 | $0.850 DeepInfra | $1.45 Novita | fp8 |
| [Qwen3.5-35B-A3B](https://undominated.ai/models/qwen__qwen3.5-35b-a3b/) lower-quant also listed | 1.71× | 4 | $0.140 DeepInfra | $0.240 SiliconFlow | fp8 |
| [GLM 5](https://undominated.ai/models/z-ai__glm-5/) | 1.67× | 7 | $0.600 StreamLake | $1.00 Z.AI | fp8 |
| [Granite 4.2 8B](https://undominated.ai/models/ibm-granite__granite-4.2-8b/) | 1.67× | 2 | $0.060 DeepInfra | $0.100 CoreWeave | bf16 |
| [Qwen3 235B A22B Thinking 2507](https://undominated.ai/models/qwen__qwen3-235b-a22b-thinking-2507/) lower-quant also listed | 1.5× | 2 | $0.300 Novita | $0.450 Venice | fp8 |
| [GLM 5.1](https://undominated.ai/models/z-ai__glm-5.1/) | 1.45× | 11 | $0.966 StreamLake | $1.40 Venice | fp8 |
| [MiniMax M2.7](https://undominated.ai/models/minimax__minimax-m2.7/) | 1.43× | 4 | $0.210 GMICloud | $0.300 Minimax | fp8 |
| [R1 0528](https://undominated.ai/models/deepseek__deepseek-r1-0528/) | 1.4× | 2 | $0.500 SiliconFlow | $0.700 Novita | fp8 |
| [DeepSeek V4 Pro 0813](https://undominated.ai/models/deepseek__deepseek-v4-pro-0813/) lower-quant also listed | 1.33× | 9 | $0.990 Novita | $1.32 SiliconFlow | fp8 |
| [Qwen3.5 397B A17B](https://undominated.ai/models/qwen__qwen3.5-397b-a17b/) lower-quant also listed | 1.33× | 4 | $0.450 DeepInfra | $0.600 GMICloud | fp8 |
| [Llama 4 Maverick](https://undominated.ai/models/meta-llama__llama-4-maverick/) lower-quant also listed | 1.3× | 2 | $0.270 Novita | $0.350 Parasail | fp8 |
| [Llama 3 8B Lunaris](https://undominated.ai/models/sao10k__l3-lunaris-8b/) | 1.25× | 2 | $0.040 Parasail | $0.050 Novita | bf16 |
| [MiniMax M3](https://undominated.ai/models/minimax__minimax-m3/) lower-quant also listed | 1.25× | 8 | $0.240 GMICloud | $0.300 Minimax | fp8 |
| [Kimi K3](https://undominated.ai/models/moonshotai__kimi-k3/) lower-quant also listed | 1.2× | 2 | $2.50 Morph | $3.00 BaseTen | fp8 |
| [Nemotron 3 Nano 30B A3B](https://undominated.ai/models/nvidia__nemotron-3-nano-30b-a3b/) | 1.2× | 2 | $0.050 Crusoe | $0.060 Nebius | fp8 |
| [MiniMax M2](https://undominated.ai/models/minimax__minimax-m2/) | 1.18× | 2 | $0.255 Minimax | $0.300 Novita | fp8 |
| [Nemotron 3.5 Lightning](https://undominated.ai/models/nvidia__nemotron-3.5-lightning/) lower-quant also listed | 1.17× | 2 | $0.060 DeepInfra | $0.070 CoreWeave | bf16 |
| [DeepSeek V3 0324](https://undominated.ai/models/deepseek__deepseek-chat-v3-0324/) | 1.16× | 2 | $0.250 SiliconFlow | $0.290 GMICloud | fp8 |
| [Kimi K2.7 Code](https://undominated.ai/models/moonshotai__kimi-k2.7-code/) lower-quant also listed | 1.11× | 3 | $0.859 SiliconFlow | $0.950 Alibaba | fp8 |
| [Qwen3 30B A3B Instruct 2507](https://undominated.ai/models/qwen__qwen3-30b-a3b-instruct-2507/) lower-quant also listed | 1.11× | 2 | $0.090 SiliconFlow | $0.100 Nebius | fp8 |
| [Kimi K2.5](https://undominated.ai/models/moonshotai__kimi-k2.5/) | 1.09× | 2 | $0.450 SiliconFlow | $0.490 AtlasCloud | int4 |
| [Qwen3 Coder 480B A35B](https://undominated.ai/models/qwen__qwen3-coder/) lower-quant also listed | 1.09× | 2 | $0.350 Venice | $0.380 Novita | fp8 |
| [Qwen3.6 27B](https://undominated.ai/models/qwen__qwen3.6-27b/) | 1.08× | 4 | $0.300 Chutes | $0.325 Venice | fp8 |
| [gpt-oss-20b](https://undominated.ai/models/openai__gpt-oss-20b/) lower-quant also listed | 1.03× | 2 | $0.029 DekaLLM | $0.030 DeepInfra | bf16 |
| [MiniMax M2.5](https://undominated.ai/models/minimax__minimax-m2.5/) lower-quant also listed | 1.02× | 4 | $0.295 AtlasCloud | $0.300 Minimax | fp8 |

## Precision differences — not established savings

These rates differ, but the cheapest endpoint has lower or undeclared precision. The raw ratio does not establish a saving at the reference precision.

| Model | Raw × | Cheap (lower / unknown quant) | Like-for-like |
| --- | --- | --- | --- |
| [Llama 3.1 8B Instruct](https://undominated.ai/models/meta-llama__llama-3.1-8b-instruct/) | 11× | $0.020 DeepInfra fp8 | $0.220 CoreWeave bf16 |
| [Gemma 4 31B](https://undominated.ai/models/google__gemma-4-31b-it/) | 8.33× | $0.090 DeepInfra fp4 | $0.140 Crusoe bf16 |
| [Mistral Nemo](https://undominated.ai/models/mistralai__mistral-nemo/) | 8.33× | $0.018 DekaLLM fp8 | $0.023 Io Net fp16 |
| [Ling 3.0 Flash](https://undominated.ai/models/inclusionai__ling-3.0-flash/) | 2.86× | $0.021 Novita unknown | $0.060 DeepInfra bf16 |
| [Llama 4 Scout](https://undominated.ai/models/meta-llama__llama-4-scout/) | 2.5× | $0.100 DeepInfra fp8 | $0.180 Novita bf16 |
| [Qwen3 VL 235B A22B Thinking](https://undominated.ai/models/qwen__qwen3-vl-235b-a22b-thinking/) | 2.45× | $0.400 Alibaba unknown | $0.980 Novita bf16 |
| [Kimi K2.6](https://undominated.ai/models/moonshotai__kimi-k2.6/) | 2.34× | $0.465 Inceptron int4 | $0.700 Crusoe bf16 |
| [Qwen3 14B](https://undominated.ai/models/qwen__qwen3-14b/) | 2.28× | $0.100 NextBit int4 | $0.120 DeepInfra fp8 |
| [Qwen3 VL 30B A3B Instruct](https://undominated.ai/models/qwen__qwen3-vl-30b-a3b-instruct/) | 2.23× | $0.130 Alibaba unknown | $0.200 Novita bf16 |
| [Qwen3 VL 8B Instruct](https://undominated.ai/models/qwen__qwen3-vl-8b-instruct/) | 2.14× | $0.117 Alibaba unknown | $0.250 Parasail bf16 |
| [Qwen3.5-9B](https://undominated.ai/models/qwen__qwen3.5-9b/) | 2.13× | $0.080 Darkbloom fp4 | $0.100 DeepInfra bf16 |
| [GLM 4.7](https://undominated.ai/models/z-ai__glm-4.7/) | 1.75× | $0.400 DeepInfra fp4 | $0.540 Novita fp8 |
| [MiMo-V2.6-Flash](https://undominated.ai/models/xiaomi__mimo-v2.6-flash/) | 1.75× | $0.100 Darkbloom fp4 | $0.140 GMICloud bf16 |
| [Qwen3 Next 80B A3B Instruct](https://undominated.ai/models/qwen__qwen3-next-80b-a3b-instruct/) | 1.67× | $0.090 DeepInfra fp8 | $0.150 Novita bf16 |
| [Hy3](https://undominated.ai/models/tencent__hy3/) | 1.54× | $0.130 DeepInfra fp4 | $0.140 GMICloud bf16 |
| [Qwen3.5-122B-A10B](https://undominated.ai/models/qwen__qwen3.5-122b-a10b/) | 1.54× | $0.260 SiliconFlow fp8 | $0.400 Novita bf16 |
| [Qwen3.5-27B](https://undominated.ai/models/qwen__qwen3.5-27b/) | 1.54× | $0.195 Alibaba unknown | $0.300 Novita bf16 |
| [Qwen3 VL 235B A22B Instruct](https://undominated.ai/models/qwen__qwen3-vl-235b-a22b-instruct/) | 1.5× | $0.200 DeepInfra fp8 | $0.300 Novita bf16 |
| [Gemma 3 27B](https://undominated.ai/models/google__gemma-3-27b-it/) | 1.49× | $0.080 DeepInfra fp8 | $0.119 Novita bf16 |
| [Qwen3 VL 30B A3B Thinking](https://undominated.ai/models/qwen__qwen3-vl-30b-a3b-thinking/) | 1.45× | $0.200 Alibaba unknown | $0.290 SiliconFlow fp8 |
| [Ling 3.0 Flash Fin](https://undominated.ai/models/inclusionai__ling-3.0-flash-fin/) | 1.43× | $0.042 Novita unknown | $0.060 DeepInfra fp4 |
| [GLM 4.6](https://undominated.ai/models/z-ai__glm-4.6/) | 1.4× | $0.430 Venice fp4 | $0.550 Novita bf16 |
| [MiniMax M1](https://undominated.ai/models/minimax__minimax-m1/) | 1.38× | $0.400 Minimax unknown | $0.550 Novita bf16 |
| [Mistral Small 3.2 24B](https://undominated.ai/models/mistralai__mistral-small-3.2-24b-instruct/) | 1.33× | $0.075 DeepInfra fp8 | $0.090 Parasail bf16 |
| [ReMM SLERP 13B](https://undominated.ai/models/undi95__remm-slerp-l2-13b/) | 1.29× | $0.350 Mancer 2 fp8 | $0.450 NextBit bf16 |
| [Nemotron 3 Ultra](https://undominated.ai/models/nvidia__nemotron-3-ultra-550b-a55b/) | 1.25× | $0.500 DeepInfra fp4 | $0.625 Venice fp8 |
| [DeepSeek V3](https://undominated.ai/models/deepseek__deepseek-chat/) | 1.24× | $0.257 StreamLake unknown | $0.320 DeepInfra fp4 |
| [GLM 4.7 Flash](https://undominated.ai/models/z-ai__glm-4.7-flash/) | 1.17× | $0.060 Venice fp8 | $0.070 Novita bf16 |
| [Nemotron 3 Super](https://undominated.ai/models/nvidia__nemotron-3-super-120b-a12b/) | 1.06× | $0.080 DekaLLM fp8 | $0.085 DeepInfra bf16 |
| [Qwen2.5 72B Instruct](https://undominated.ai/models/qwen__qwen-2.5-72b-instruct/) | 1.06× | $0.360 DeepInfra fp8 | $0.380 Novita bf16 |
| [MiMo-V2.6-Pro](https://undominated.ai/models/xiaomi__mimo-v2.6-pro/) | 1.01× | $0.430 DeepInfra fp8 | $0.435 GMICloud bf16 |

## Serving precision not established

49 models have multiple seller owners, but no declared serving precision. These price observations are excluded from the declared-precision ranking. Verify precision, context, tools, reliability and terms with the endpoint provider.

 - [Claude Fable 5](https://undominated.ai/models/anthropic__claude-fable-5/) · 5 sellers · $10.00–$10.00 per million input tokens
- [Claude Fable 5.1](https://undominated.ai/models/anthropic__claude-fable-5.1/) · 4 sellers · $10.00–$10.00 per million input tokens
- [Claude Haiku 4.5](https://undominated.ai/models/anthropic__claude-haiku-4.5/) · 4 sellers · $1.00–$1.00 per million input tokens
- [Claude Opus 4.5](https://undominated.ai/models/anthropic__claude-opus-4.5/) · 5 sellers · $5.00–$5.00 per million input tokens
- [Claude Opus 4.6](https://undominated.ai/models/anthropic__claude-opus-4.6/) · 5 sellers · $5.00–$5.00 per million input tokens
- [Claude Opus 4.7](https://undominated.ai/models/anthropic__claude-opus-4.7/) · 5 sellers · $5.00–$5.00 per million input tokens
- [Claude Opus 4.8](https://undominated.ai/models/anthropic__claude-opus-4.8/) · 5 sellers · $5.00–$5.00 per million input tokens
- [Claude Opus 5](https://undominated.ai/models/anthropic__claude-opus-5/) · 5 sellers · $5.00–$5.00 per million input tokens
- [Claude Opus 5.5](https://undominated.ai/models/anthropic__claude-opus-5.5/) · 5 sellers · $4.00–$4.00 per million input tokens
- [Claude Sonnet 4.5](https://undominated.ai/models/anthropic__claude-sonnet-4.5/) · 5 sellers · $3.00–$3.00 per million input tokens
- [Claude Sonnet 4.6](https://undominated.ai/models/anthropic__claude-sonnet-4.6/) · 5 sellers · $3.00–$3.00 per million input tokens
- [Claude Sonnet 5](https://undominated.ai/models/anthropic__claude-sonnet-5/) · 5 sellers · $2.00–$2.00 per million input tokens
- [Claude Sonnet 5.5](https://undominated.ai/models/anthropic__claude-sonnet-5.5/) · 5 sellers · $2.00–$2.00 per million input tokens
- [GPT-3.5 Turbo 16k](https://undominated.ai/models/openai__gpt-3.5-turbo-16k/) · 2 sellers · $3.00–$3.00 per million input tokens
- [GPT-4](https://undominated.ai/models/openai__gpt-4/) · 2 sellers · $30.00–$30.00 per million input tokens
- [GPT-4.1](https://undominated.ai/models/openai__gpt-4.1/) · 2 sellers · $2.00–$2.00 per million input tokens
- [GPT-4.1 Mini](https://undominated.ai/models/openai__gpt-4.1-mini/) · 2 sellers · $0.400–$0.400 per million input tokens
- [GPT-4.1 Nano](https://undominated.ai/models/openai__gpt-4.1-nano/) · 2 sellers · $0.100–$0.100 per million input tokens
- [GPT-4o](https://undominated.ai/models/openai__gpt-4o/) · 2 sellers · $2.50–$2.50 per million input tokens
- [GPT-4o (2024-05-13)](https://undominated.ai/models/openai__gpt-4o-2024-05-13/) · 2 sellers · $5.00–$5.00 per million input tokens
- [GPT-4o (2024-08-06)](https://undominated.ai/models/openai__gpt-4o-2024-08-06/) · 2 sellers · $2.50–$2.50 per million input tokens
- [GPT-4o-mini](https://undominated.ai/models/openai__gpt-4o-mini/) · 2 sellers · $0.150–$0.150 per million input tokens
- [GPT-5](https://undominated.ai/models/openai__gpt-5/) · 2 sellers · $1.25–$1.25 per million input tokens
- [GPT-5 Mini](https://undominated.ai/models/openai__gpt-5-mini/) · 2 sellers · $0.125–$0.250 per million input tokens
- [GPT-5 Nano](https://undominated.ai/models/openai__gpt-5-nano/) · 2 sellers · $0.025–$0.050 per million input tokens
- [GPT-5.1](https://undominated.ai/models/openai__gpt-5.1/) · 2 sellers · $0.625–$1.25 per million input tokens
- [GPT-5.2](https://undominated.ai/models/openai__gpt-5.2/) · 2 sellers · $0.875–$1.75 per million input tokens
- [GPT-5.3-Codex](https://undominated.ai/models/openai__gpt-5.3-codex/) · 2 sellers · $1.75–$1.75 per million input tokens
- [GPT-5.4](https://undominated.ai/models/openai__gpt-5.4/) · 3 sellers · $1.25–$2.75 per million input tokens
- [GPT-5.4 Mini](https://undominated.ai/models/openai__gpt-5.4-mini/) · 2 sellers · $0.375–$0.750 per million input tokens
- [GPT-5.4 Nano](https://undominated.ai/models/openai__gpt-5.4-nano/) · 2 sellers · $0.100–$0.200 per million input tokens
- [GPT-5.4 Pro](https://undominated.ai/models/openai__gpt-5.4-pro/) · 2 sellers · $15.00–$30.00 per million input tokens
- [GPT-5.5](https://undominated.ai/models/openai__gpt-5.5/) · 3 sellers · $2.50–$5.50 per million input tokens
- [GPT-5.6 Luna](https://undominated.ai/models/openai__gpt-5.6-luna/) · 3 sellers · $0.100–$0.220 per million input tokens
- [GPT-5.6 Luna Pro](https://undominated.ai/models/openai__gpt-5.6-luna-pro/) · 2 sellers · $0.100–$0.200 per million input tokens
- [GPT-5.6 Sol](https://undominated.ai/models/openai__gpt-5.6-sol/) · 3 sellers · $1.00–$4.40 per million input tokens
- [GPT-5.6 Sol Pro](https://undominated.ai/models/openai__gpt-5.6-sol-pro/) · 2 sellers · $1.00–$4.00 per million input tokens
- [GPT-5.6 Terra](https://undominated.ai/models/openai__gpt-5.6-terra/) · 3 sellers · $1.00–$2.20 per million input tokens
- [GPT-5.6 Terra Pro](https://undominated.ai/models/openai__gpt-5.6-terra-pro/) · 2 sellers · $1.00–$2.00 per million input tokens
- [GPT-6 Astra](https://undominated.ai/models/openai__gpt-6-astra/) · 3 sellers · $5.00–$11.00 per million input tokens
- [GPT-6 Astra Pro](https://undominated.ai/models/openai__gpt-6-astra-pro/) · 2 sellers · $5.00–$10.00 per million input tokens
- [GPT-6 Luna](https://undominated.ai/models/openai__gpt-6-luna/) · 3 sellers · $0.050–$0.110 per million input tokens
- [GPT-6 Luna Pro](https://undominated.ai/models/openai__gpt-6-luna-pro/) · 2 sellers · $0.050–$0.100 per million input tokens
- [GPT-6 Sol](https://undominated.ai/models/openai__gpt-6-sol/) · 3 sellers · $1.00–$2.20 per million input tokens
- [GPT-6 Sol Pro](https://undominated.ai/models/openai__gpt-6-sol-pro/) · 2 sellers · $1.00–$2.00 per million input tokens
- [GPT-6.1 Sol](https://undominated.ai/models/openai__gpt-6.1-sol/) · 3 sellers · $1.00–$2.20 per million input tokens
- [GPT-6.1 Sol Pro](https://undominated.ai/models/openai__gpt-6.1-sol-pro/) · 2 sellers · $1.00–$2.00 per million input tokens
- [Grok 4.6](https://undominated.ai/models/x-ai__grok-4.6/) · 2 sellers · $2.00–$2.20 per million input tokens
- [Qwen3 Next 80B A3B Thinking](https://undominated.ai/models/qwen__qwen3-next-80b-a3b-thinking/) · 2 sellers · $0.150–$0.150 per million input tokens

## Excluded from the ranked list

 - 0 unpriced — no finite input price (missing price is not free).
 - 206 single-seller — one shop is not a market.
 - 17 no actionable equal-or-better spread.
 - 31 lower or unknown precision — listed above, not as savings.
 - 0 where the cheaper input seller is not, or cannot be shown to be, cheaper on the balanced blend .
 - 49 no declared serving precision across sellers.
 - 0 on the publication denylist — never shown.

## Questions this page answers

 How is spread computed on this page?

Spread is dearest ÷ cheapest input price among distinct sellers at the reference serving precision or better. A vendor listing the same model at its own service tiers is not competition. A spread is listed only when the cheaper seller is also cheaper on the balanced blend the site ranks by (3 parts input to 1 part output); otherwise the input spread would point at the dearer seller.

 Why are some models excluded?

Unpriced models are excluded. Cheaper endpoints at lower precision do not count as a saving if the reference precision is higher.

 Does a high spread mean I should switch?

It means multiple sellers publish different rates at equal-or-better precision. Capability dominance is on /check/ and /frontier/; this page is shopping geometry only.

 Copy evidence Download CSV · 45 rows [Input hashes & method version](/data/publications/manifests/ecef83f767cd4d2c21766f6a5b4dffa36c06351f23657542d473bc1a030c0932.json)

 Read citation text and BibTeX 45 models have actionable spreads. Condition: equal-or-better declared precision; cheaper lower-precision is not a saving; the cheaper input seller is also cheaper on the balanced blend (3 input : 1 output). Prices are USD per million input tokens. As of 2026-10-06. Lens: Published provider prices in the accepted OpenRouter-derived catalogue. https://undominated.ai/spreads/
Method: https://undominated.ai/methodology/
Publication: sha256:ecef83f767cd4d2c21766f6a5b4dffa36c06351f23657542d473bc1a030c0932; calculation SHA-256: 5ae4d0bee9b70298dd437b05df87c32acb407040b50bf88240677f295f25955d; permitted inputs: https://undominated.ai/data/publications/manifests/ecef83f767cd4d2c21766f6a5b4dffa36c06351f23657542d473bc1a030c0932.json

Copy BibTeX Download citation

 @misc{undominated-spreads-2026-10-06,
 author = {{Undominated.ai}},
 title = {spreads evidence — Undominated.ai},
 year = {2026},
 url = {https://undominated.ai/spreads/},
 note = {as of 2026-10-06; Published provider prices in the accepted OpenRouter-derived catalogue},
 annote = {Publication: sha256:ecef83f767cd4d2c21766f6a5b4dffa36c06351f23657542d473bc1a030c0932; calculation SHA-256: 5ae4d0bee9b70298dd437b05df87c32acb407040b50bf88240677f295f25955d; permitted inputs: https://undominated.ai/data/publications/manifests/ecef83f767cd4d2c21766f6a5b4dffa36c06351f23657542d473bc1a030c0932.json}
}

## Continue your investigation

 - [Inspect sellers](/providers/)
- [Compare routes](/openrouter-vs-direct/)
- [Check context prices](/cliffs/)
- [Audit real usage](/audit/)