ModelPriceWatch.com
Last scan 2026-09-23 Models tracked 267 Providers 35 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

Best Open Source LLM APIs

Open source LLM APIs with open weights, ranked by independent capability index. Compare verified pricing for models like Kimi, GLM, Qwen, Mistral, and DeepSeek that you can self-host or use via managed API.

57 models qualify top 22 shown ranked by AA Intelligence Index
1Fireworks

Kimi K2.6

45.1 AA Intelligence Index

$1.71/1M blended · $0.950 in · $4.00 out

2Z.AI

GLM-5.3

44.9 AA Intelligence Index

$2.15/1M blended · $1.40 in · $4.40 out

3Moonshot

Kimi K3

43.8 AA Intelligence Index

$6.00/1M blended · $3.00 in · $15.00 out

MODELPRICEWATCH.COM · 2026-09-23

Cost calculator for this use casemonthly cost, top 3 models

1 Kimi K2.6
$—
2 GLM-5.3
$—
3 Kimi K3
$—

Full ranking — top 22 models

list prices, USD per 1M tokens
Top 22 models for Best Open Source LLM APIs, ranked by AA Intelligence Index
Model AA Intelligence Index Blended* Input Output Context Provider
1Kimi K2.6 45.1 $1.71 $0.950 $4.00 256K Fireworks
2GLM-5.3 44.9 $2.15 $1.40 $4.40 1M Z.AI
3Kimi K3 43.8 $6.00 $3.00 $15.00 1M Moonshot
4GLM-5.3-Flash 41.9 $0.237 $0.150 $0.500 1M Z.AI
5Qwen3.8-2.4T-A95B 40 $3.00 $2.00 $6.00 1M Alibaba
6Qwen3.7-Plus 39 $0.560 $0.320 $1.28 1M Together
7Qwen3.6-27B 37.7 $1.20 $0.600 $3.00 131K Groq
8GLM-5.2 34 $2.15 $1.40 $4.40 1M Z.AI
9Qwen3.8-27B 33.9 $1.13 $0.500 $3.00 1M Alibaba
10MiniMax-M3 29.6 $0.525 $0.300 $1.20 1M MiniMax
11GLM-5.1 26.4 $2.15 $1.40 $4.40 128K Z.AI
12Kimi K2.7 Code 26.3 $1.71 $0.950 $4.00 262K Moonshot
13Kimi K2.7 Code HighSpeed 26.3 $3.42 $1.90 $8.00 262K Moonshot
14Inkling Small 26.1 $0.525 $0.300 $1.20 262K Thinking Machines
15Inkling 25.5 $1.76 $1.00 $4.05 262K Thinking Machines
16NVIDIA Nemotron 3 Ultra 23.4 $1.05 $0.600 $2.40 128K Fireworks
17MiniMax-M2.7 23.2 $0.525 $0.300 $1.20 205K MiniMax
18LongCat-2.0 19.7 $1.30 $0.750 $2.95 262K Meituan
19Qwen3.5-397B-A17B 19.1 $1.35 $0.600 $3.60 262K Alibaba
20Qwen3.5-122B-A10B 16.2 $1.10 $0.400 $3.20 262K Alibaba
21GLM-5.3-FlashX $0.590 $0.370 $1.25 1M Z.AI
22Hy4 preview $1.25 $0.834 $2.50 1M Tencent
Ranked by AA Intelligence Index — independent leaderboard data; benchmark citations are on each model page. Scores flagged “vendor” are the maker's own claim, shown for reference and ranked below independently-scored models; models with no published score rank last, cheapest first. * Blended = (3×input + 1×output) ÷ 4. Every price links to its source on the model page.

Recent price movement in this ranking

price-only deltas · logged by the daily scan

2 of the top 22 open source models have re-priced since we began tracking · last checked .

Models in this Best Open Source LLM APIs ranking that have re-priced since tracking began, most recent move first
Model Changes Latest move Provider
GLM-5.3-Flash 1 price rise on : $0.075/$0.250 → $0.150/$0.500 /Mtok Z.AI
MiniMax-M3 1 price cut on : $0.600/$2.40 → $0.300/$1.20 /Mtok MiniMax
Changes = distinct price moves logged since tracking began; in/out prices are $ per 1M tokens. MODELPRICEWATCH.COM · 2026-09-23

Most recently, GLM-5.3-Flash raised its price on — a sign pricing in this category is still moving, so re-check before committing to a long-term choice. See all recent price moves →

How models are selected

Generally-available open-weight models, ranked by the Artificial Analysis Intelligence Index (an independent cross-benchmark composite). One row per model — host duplicates are collapsed to the canonical listing. Models without an index score rank below scored ones, cheapest first.

Prices are per million tokens (Mtok), sourced directly from — and linked to — official provider pricing pages. "Blended cost" is (3×input + 1×output) ÷ 4 — weighted toward input because real workloads read far more tokens than they generate.

Other use case rankings