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.
MODELPRICEWATCH.COM · 2026-11-07
Cost calculator for this use casemonthly cost, top 3 models
- 1 Kimi K3
- $—
- 2 Qwen3.8-2.4T-A95B
- $—
- 3 Qwen3.7-Plus
- $—
Full ranking — top 24 models
list prices, USD per 1M tokens| Model | AA Intelligence Index | Blended* | Input | Output | Context | Provider |
|---|---|---|---|---|---|---|
| 1Kimi K3 | 43.6 | $6.00 | $3.00 | $15.00 | 1M | Moonshot |
| 2Qwen3.8-2.4T-A95B | 39.9 | $3.00 | $2.00 | $6.00 | 1M | Alibaba |
| 3Qwen3.7-Plus | 39 | $0.560 | $0.320 | $1.28 | 1M | Together |
| 4GLM-5.2 | 33.7 | $2.15 | $1.40 | $4.40 | 1M | Z.AI |
| 5GLM-5.3 | 31.7 | $2.15 | $1.40 | $4.40 | 1M | Z.AI |
| 6GLM-5.3-Flash | 27.8 | $0.237 | $0.150 | $0.500 | 1M | Z.AI |
| 7Kimi K2.6 | 27 | $1.71 | $0.950 | $4.00 | 262K | Moonshot |
| 8GLM-5.1 | 26.1 | $2.15 | $1.40 | $4.40 | 128K | Z.AI |
| 9Kimi K2.7 Code | 25.8 | $1.71 | $0.950 | $4.00 | 262K | Moonshot |
| 10Kimi K2.7 Code HighSpeed | 25.8 | $3.42 | $1.90 | $8.00 | 262K | Moonshot |
| 11MiniMax-M2.7 | 22.8 | $0.525 | $0.300 | $1.20 | 128K | Fireworks |
| 12Qwen3.6-27B | 21.4 | $1.35 | $0.600 | $3.60 | 262K | Alibaba |
| 13Qwen3.8-27B | 20.1 | $1.13 | $0.500 | $3.00 | 1M | Alibaba |
| 14MiniMax-M3 | 18.7 | $0.525 | $0.300 | $1.20 | 1M | MiniMax |
| 15Qwen3.5-397B-A17B | 18.4 | $1.35 | $0.600 | $3.60 | 262K | Alibaba |
| 16Qwen3.5-122B-A10B | 15.6 | $1.10 | $0.400 | $3.20 | 262K | Alibaba |
| 17Inkling Small | 12.9 | $0.525 | $0.300 | $1.20 | 262K | Thinking Machines |
| 18Inkling | 12.5 | $1.76 | $1.00 | $4.05 | 262K | Thinking Machines |
| 19NVIDIA Nemotron 3 Ultra | 11.8 | $1.05 | $0.600 | $2.40 | 128K | Fireworks |
| 20GPT-OSS 120B | 11.6 | $0.262 | $0.150 | $0.600 | 128K | Fireworks |
| 21Apodex 1.1 Mini | — | $0.325 | $0.100 | $1.00 | 262K | Apodex |
| 22GLM-5.3-FlashX | — | $0.590 | $0.370 | $1.25 | 1M | Z.AI |
| 23Hy4 preview | — | $1.25 | $0.834 | $2.50 | 1M | Tencent |
| 24GLM-5.3-Prime | — | $4.30 | $2.80 | $8.80 | 1M | Alibaba |
Recent price movement in this ranking
price-only deltas · logged by the daily scan2 of the top 24 open source models have re-priced since we began tracking · last checked .
| 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 |
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.