---
title: "Price spreads worth shopping · Undominated.ai"
canonical: https://undominated.ai/sv/spreads/
description: "57 models with an actionable multi-seller spread at equal-or-better precision, as of 2026-08-28. Distinct sellers only — not a vendor’s own service tiers."
---

# Price spreads worth shopping · Undominated.ai

> 57 models with an actionable multi-seller spread at equal-or-better precision, as of 2026-08-28. Distinct sellers only — not a vendor’s own service tiers.

# Spreads worth shopping

Ranked by actionable price spread across distinct sellers at equal-or-better serving precision. A vendor’s own service tiers are not competition. Unpriced models are excluded. Unrated is not scored zero.

57 models

As of 2026-08-28 . Condition: equal-or-better declared precision; cheaper lower-precision is not a saving.

## Worth shopping

Spread is dearest ÷ cheapest among sellers at the reference precision or better. Cheaper lower-precision endpoints do not enter this table as a saving.

| Model | Spread | Sellers | Cheap | Dear | Precision |
| --- | --- | --- | --- | --- | --- |
| Gemma 4 31B | 12.38× | 5 | $0.080 OpenInference | $0.990 Cerebras | bf16 |
| gpt-oss-120b lower-quant also listed | 9.46× | 3 | $0.037 DeepInfra | $0.350 Cerebras | bf16 |
| GPT-5.6 Sol | 5.5× | 3 | $1.00 OpenAI | $5.50 Amazon Bedrock | unknown |
| Llama 3.3 70B Instruct lower-quant also listed | 5.26× | 3 | $0.135 Novita | $0.710 CoreWeave | bf16 |
| GPT-5.6 Sol Pro | 5× | 2 | $1.00 OpenAI | $5.00 Azure | unknown |
| MythoMax 13B lower-quant also listed | 5× | 2 | $0.080 Parasail | $0.400 DeepInfra | fp16 |
| DeepSeek V4 Pro 0423 | 3.33× | 9 | $0.522 StreamLake | $1.74 Parasail | fp8 |
| Qwen2.5 VL 72B Instruct | 3.2× | 2 | $0.250 Nebius | $0.800 Parasail | fp8 |
| Qwen2.5 7B Instruct | 3× | 2 | $0.100 Phala | $0.300 Together | unknown |
| GLM 5.2 | 2.8× | 15 | $0.500 Sail Research | $1.40 Venice | fp8 |
| DeepSeek V4 Flash 0423 | 2.5× | 10 | $0.056 StreamLake | $0.140 Mancer 2 | fp8 |
| Qwen3.6 35B A3B lower-quant also listed | 2.5× | 8 | $0.100 DeepInfra | $0.250 CoreWeave | fp8 |
| DeepSeek V3.1 lower-quant also listed | 2.41× | 5 | $0.270 SiliconFlow | $0.650 SambaNova | fp8 |
| Qwen3 235B A22B Instruct 2507 | 2.29× | 7 | $0.087 GMICloud | $0.200 AtlasCloud | fp8 |
| GPT-5.4 | 2.2× | 3 | $1.25 OpenAI | $2.75 Amazon Bedrock | unknown |
| GPT-5.5 | 2.2× | 3 | $2.50 OpenAI | $5.50 Amazon Bedrock | unknown |
| GPT-5.6 Luna | 2.2× | 3 | $0.100 OpenAI | $0.220 Amazon Bedrock | unknown |
| GPT-5.6 Terra | 2.2× | 3 | $1.00 OpenAI | $2.20 Amazon Bedrock | unknown |
| Gemini 2.5 Flash | 2× | 2 | $0.150 Google AI Studio | $0.300 Google | unknown |
| Gemini 2.5 Flash Lite | 2× | 2 | $0.050 Google AI Studio | $0.100 Google | unknown |
| Gemini 3.7 Flash | 2× | 2 | $0.188 Google | $0.375 Google AI Studio | unknown |
| GLM 5.3 Flash | 2× | 5 | $0.075 Z.AI | $0.150 Io Net | fp8 |
| GPT-5 Mini | 2× | 2 | $0.125 OpenAI | $0.250 Azure | unknown |
| GPT-5 Nano | 2× | 2 | $0.025 OpenAI | $0.050 Azure | unknown |
| GPT-5.1 | 2× | 2 | $0.625 OpenAI | $1.25 Azure | unknown |
| GPT-5.2 | 2× | 2 | $0.875 OpenAI | $1.75 Azure | unknown |
| GPT-5.4 Mini | 2× | 2 | $0.375 OpenAI | $0.750 Azure | unknown |
| GPT-5.4 Nano | 2× | 2 | $0.100 OpenAI | $0.200 Azure | unknown |
| GPT-5.4 Pro | 2× | 2 | $15.00 OpenAI | $30.00 Azure | unknown |
| GPT-5.6 Luna Pro | 2× | 2 | $0.100 OpenAI | $0.200 Azure | unknown |
| GPT-5.6 Terra Pro | 2× | 2 | $1.00 OpenAI | $2.00 Azure | unknown |
| Qwen3.6 27B | 2× | 5 | $0.300 Chutes | $0.600 CoreWeave | fp8 |
| Qwen3.5-35B-A3B | 1.79× | 5 | $0.140 DeepInfra | $0.250 CoreWeave | fp8 |
| DeepSeek V3.2 | 1.77× | 7 | $0.209 GMICloud | $0.370 Alibaba | fp8 |
| Llama 4 Maverick | 1.75× | 3 | $0.200 DeepInfra | $0.350 Parasail | fp8 |
| Qwen3 32B | 1.75× | 3 | $0.080 DeepInfra | $0.140 SiliconFlow | fp8 |
| Llama 3.1 Euryale 70B v2.2 | 1.71× | 2 | $0.850 DeepInfra | $1.45 Novita | fp8 |
| GLM 5.1 | 1.69× | 13 | $0.910 GMICloud | $1.54 Venice | fp8 |
| GLM 5 | 1.67× | 8 | $0.600 GMICloud | $1.00 Novita | fp8 |
| Qwen3 235B A22B Thinking 2507 lower-quant also listed | 1.5× | 2 | $0.300 Novita | $0.450 Venice | fp8 |
| R1 0528 | 1.4× | 2 | $0.500 SiliconFlow | $0.700 Novita | fp8 |
| Qwen3.5 397B A17B lower-quant also listed | 1.33× | 4 | $0.450 DeepInfra | $0.600 GMICloud | fp8 |
| Gemma 4 26B A4B lower-quant also listed | 1.3× | 4 | $0.100 NextBit | $0.130 Parasail | bf16 |
| Llama 3 8B Lunaris | 1.25× | 2 | $0.040 Parasail | $0.050 Novita | bf16 |
| MiniMax M2.7 | 1.25× | 5 | $0.240 GMICloud | $0.300 Minimax | fp8 |
| MiniMax M3 lower-quant also listed | 1.25× | 8 | $0.240 GMICloud | $0.300 Minimax | fp8 |
| Nemotron 3.5 Lightning | 1.25× | 2 | $0.080 DeepInfra | $0.100 CoreWeave | bf16 |
| DeepSeek V4 Pro 0813 lower-quant also listed | 1.18× | 5 | $1.12 GMICloud | $1.32 SiliconFlow | fp8 |
| MiniMax M2 | 1.18× | 2 | $0.255 Minimax | $0.300 Novita | fp8 |
| GLM 4.7 Flash | 1.17× | 2 | $0.060 DeepInfra | $0.070 Novita | bf16 |
| GLM 4.7 lower-quant also listed | 1.13× | 3 | $0.480 StreamLake | $0.540 Novita | fp8 |
| DeepSeek V3.1 Terminus | 1.11× | 3 | $0.270 Novita | $0.300 AtlasCloud | fp8 |
| Inkling Small | 1.11× | 2 | $0.450 DeepInfra | $0.500 BaseTen | fp8 |
| Kimi K2.7 Code lower-quant also listed | 1.11× | 3 | $0.859 SiliconFlow | $0.950 Alibaba | fp8 |
| Qwen3 Coder 480B A35B lower-quant also listed | 1.09× | 2 | $0.350 Venice | $0.380 Novita | fp8 |
| Inkling | 1.05× | 2 | $0.950 DeepInfra | $1.00 BaseTen | fp8 |
| MiniMax M2.5 lower-quant also listed | 1.02× | 4 | $0.295 AtlasCloud | $0.300 SiliconFlow | fp8 |

## Precision trades — not like-for-like savings

These look wide if you ignore quantisation. The cheap row is a lower precision; the figure is named so it is not mistaken for a shopping win.

| Model | Raw × | Cheap (lower quant) | Like-for-like |
| --- | --- | --- | --- |
| DeepSeek V4 Flash 0731 | 11× | $0.040 Relace fp4 | $0.079 Morph bf16 |
| Llama 3.1 8B Instruct | 11× | $0.020 DeepInfra fp8 | $0.220 CoreWeave bf16 |
| Qwen3 Coder 30B A3B Instruct | 4.18× | $0.070 Novita fp8 | $0.070 Novita fp8 |
| Nemotron 3 Super | 3.53× | $0.085 DeepInfra bf16 | $0.085 DeepInfra bf16 |
| MiMo-V2.5 | 3.36× | $0.119 GMICloud fp8 | $0.400 DeepInfra bf16 |
| MiMo-V2.5-Pro | 3.28× | $0.304 GMICloud bf16 | $0.304 GMICloud bf16 |
| Ling-3.0-flash | 2.86× | $0.021 Novita unknown | $0.060 DeepInfra bf16 |
| Qwen3 30B A3B Instruct 2507 | 2.7× | $0.048 StreamLake unknown | $0.100 CoreWeave bf16 |
| gpt-oss-20b | 2.5× | $0.030 DeepInfra bf16 | $0.030 DeepInfra bf16 |
| Llama 4 Scout | 2.5× | $0.100 DeepInfra fp8 | $0.180 Novita bf16 |
| Qwen3 Coder Next | 2.5× | $0.120 Parasail bf16 | $0.120 Parasail bf16 |
| Qwen3 VL 235B A22B Thinking | 2.45× | $0.400 Alibaba unknown | $0.980 Novita bf16 |
| Mistral Nemo | 2.32× | $0.019 DeepInfra fp8 | $0.044 Io Net fp16 |
| Qwen3 14B | 2.27× | $0.100 NextBit int4 | $0.120 DeepInfra fp8 |
| Qwen3 VL 30B A3B Instruct | 2.23× | $0.130 Alibaba unknown | $0.200 Novita bf16 |
| Qwen3 VL 8B Instruct | 2.14× | $0.117 Alibaba unknown | $0.250 Parasail bf16 |
| DeepSeek V3 0324 | 2.08× | $0.240 DeepInfra fp4 | $0.500 Crusoe bf16 |
| Llama 3.1 70B Instruct | 2× | $0.400 DeepInfra fp8 | $0.800 CoreWeave bf16 |
| Nex-N2-Pro | 2× | $0.250 Nex AGI fp8 | $0.250 Nex AGI fp8 |
| Gemma 3 27B | 1.88× | $0.080 DeepInfra fp8 | $0.119 Novita bf16 |
| Kimi K2.6 | 1.88× | $0.580 Chutes int4 | $0.700 Crusoe bf16 |
| Qwen3.5-9B | 1.7× | $0.100 DeepInfra bf16 | $0.100 DeepInfra bf16 |
| Qwen3 Next 80B A3B Instruct | 1.67× | $0.090 DeepInfra fp8 | $0.150 Novita bf16 |
| Hy3 | 1.59× | $0.126 GMICloud bf16 | $0.126 GMICloud bf16 |
| DeepSeek V3 | 1.55× | $0.257 StreamLake unknown | $0.400 Novita fp8 |
| GLM 4.5 Air | 1.54× | $0.130 Novita bf16 | $0.130 Novita bf16 |
| Qwen3.5-122B-A10B | 1.54× | $0.260 SiliconFlow fp8 | $0.400 Novita bf16 |
| Qwen3.5-27B | 1.54× | $0.195 Alibaba unknown | $0.300 Novita bf16 |
| Qwen3 VL 235B A22B Instruct | 1.5× | $0.200 DeepInfra fp8 | $0.300 Novita bf16 |
| Qwen3 VL 30B A3B Thinking | 1.45× | $0.200 Alibaba unknown | $0.290 SiliconFlow fp8 |
| GLM 4.6 | 1.4× | $0.430 Venice fp4 | $0.550 Novita bf16 |
| MiniMax M1 | 1.38× | $0.400 Minimax unknown | $0.550 Novita bf16 |
| Qwen3.8 27B | 1.37× | $0.350 Chutes fp8 | $0.400 AkashML bf16 |
| Kimi K2.5 | 1.33× | $0.450 DeepInfra fp4 | $0.540 StreamLake fp8 |
| Kimi K3 | 1.33× | $2.60 Sail Research fp4 | $2.85 DeepInfra bf16 |
| Mistral Small 4 | 1.25× | $0.150 Mistral unknown | $0.188 Venice fp8 |
| Nemotron 3 Ultra | 1.25× | $0.500 DeepInfra fp4 | $0.625 Venice fp8 |
| Qwen3.8 2.4T A95B | 1.25× | $2.00 SiliconFlow fp8 | $2.00 SiliconFlow fp8 |
| Mistral Small 3.2 24B | 1.2× | $0.075 DeepInfra fp8 | $0.090 Parasail bf16 |
| Muse Glimmer 30B | 1.17× | $0.300 Parasail bf16 | $0.300 Parasail bf16 |
| Trinity Large Thinking | 1.14× | $0.220 Parasail fp4 | $0.220 Parasail fp4 |
| Llama Guard 4 12B | 1.11× | $0.180 DeepInfra bf16 | $0.180 DeepInfra bf16 |
| Qwen3 30B A3B | 1.08× | $0.120 DeepInfra fp8 | $0.120 DeepInfra fp8 |
| Qwen2.5 72B Instruct | 1.06× | $0.360 DeepInfra fp8 | $0.380 Novita bf16 |
| Llama 3.2 3B Instruct | 1.02× | $0.050 Parasail bf16 | $0.050 Parasail bf16 |

## Excluded from the ranked list

 - 0 unpriced — no finite input price (missing price is not free).
 - 171 single-seller — one shop is not a market.
 - 47 no actionable equal-or-better spread.
 - 45 precision trades — listed above, not as savings.
 - 0 publication denylist (FakeProvider / Stealth) — never shown.
