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 · 2026-08-09
Cost calculator for this use casemonthly cost, top 3 models
- 1 Kimi K3
- $—
- 2 GLM-5.2
- $—
- 3 MiniMax-M3
- $—
Full ranking — top 20 models
list prices, USD per 1M tokens| Model | AA Intelligence Index | Blended* | Input | Output | Context | Provider |
|---|---|---|---|---|---|---|
| 1Kimi K3 | 59.7 | $6.00 | $3.00 | $15.00 | 1M | Moonshot |
| 2GLM-5.2 | 52.6 | $2.15 | $1.40 | $4.40 | 1M | Z.AI |
| 3MiniMax-M3 | 45.4 | $0.525 | $0.300 | $1.20 | 1M | MiniMax |
| 4Kimi K2.6 | 45.1 | $1.71 | $0.950 | $4.00 | 262K | Moonshot |
| 5Kimi K2.7 Code | 43 | $1.71 | $0.950 | $4.00 | 262K | Moonshot |
| 6Kimi K2.7 Code HighSpeed | 43 | $3.42 | $1.90 | $8.00 | 262K | Moonshot |
| 7Inkling | 42.3 | $1.76 | $1.00 | $4.05 | 262K | Thinking Machines |
| 8Inkling Small | 41.2 | $0.525 | $0.300 | $1.20 | 262K | Thinking Machines |
| 9GLM-5.1 | 41 | $2.15 | $1.40 | $4.40 | 128K | Z.AI |
| 10Qwen 3.6 Plus | 40.5 | $1.13 | $0.500 | $3.00 | 128K | Fireworks |
| 11Qwen 3.7 Plus | 39.4 | $0.700 | $0.400 | $1.60 | 128K | Fireworks |
| 12MiniMax-M2.7 | 38.9 | $0.525 | $0.300 | $1.20 | 205K | MiniMax |
| 13NVIDIA Nemotron 3 Ultra | 38.3 | $1.05 | $0.600 | $2.40 | 128K | Fireworks |
| 14Qwen3.6-27B | 37.7 | $1.35 | $0.600 | $3.60 | 262K | Alibaba |
| 15Kimi K2.5 | 36 | $1.20 | $0.600 | $3.00 | 262K | Moonshot |
| 16GLM-4.7 | 34.5 | $1.00 | $0.600 | $2.20 | 128K | Z.AI |
| 17Qwen3.5-397B-A17B | 34.3 | $1.35 | $0.600 | $3.60 | 262K | Alibaba |
| 18LongCat-2.0 | 33.9 | $1.30 | $0.750 | $2.95 | 262K | Meituan |
| 19GLM-4.6 | 29.3 | $1.00 | $0.600 | $2.20 | 200K | Z.AI |
| 20GPT OSS 120B | 24.1 | $0.262 | $0.150 | $0.600 | 128K | Fireworks |
Recent price movement in this ranking
price-only deltas · logged by the daily scan1 of the top 20 open source models has re-priced since we began tracking · last checked Aug 9, 2026.
| Model | Changes | Latest move | Provider |
|---|---|---|---|
| MiniMax-M3 | 1 | price cut on Jun 17, 2026: $0.6/$2.4 → $0.3/$1.2 /Mtok | MiniMax |
Most recently, MiniMax-M3 cut its price on Jun 17, 2026 — 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.