Fastest LLM APIs for Low-Latency Apps
LLM APIs optimized for fast inference and low latency, ranked by measured throughput (tokens/sec). Compare verified pricing on fast inference providers like Groq, Together, and Fireworks.
MODELPRICEWATCH.COM · 2026-08-09
Cost calculator for this use casemonthly cost, top 3 models
- 1 Llama 4 Scout
- $—
- 2 Llama 3.3 70B
- $—
- 3 GPT OSS 120B
- $—
Full ranking — top 27 models
list prices, USD per 1M tokens| Model | Throughput | Blended* | Input | Output | Context | Provider |
|---|---|---|---|---|---|---|
| 1Llama 4 Scout | 2600 tok/s | $0.168 | $0.110 | $0.340 | 10M | Meta |
| 2Llama 3.3 70B | 2500 tok/s | $0.640 | $0.590 | $0.790 | 128K | Meta |
| 3GPT OSS 120B | 1829 tok/s | $0.262 | $0.150 | $0.600 | 128K | Fireworks |
| 4Llama 3.1 8B | 1800 tok/s | $0.058 | $0.050 | $0.080 | 128K | Meta |
| 5GPT OSS 20B | 942 tok/s | $0.128 | $0.070 | $0.300 | 128K | Fireworks |
| 6Qwen 3.6 27B | 472 tok/s | $1.20 | $0.600 | $3.00 | 128K | Groq |
| 7Granite 4 H Small | 415 tok/s | $0.107 | $0.060 | $0.250 | 128K | IBM |
| 8GLM-5.2 | 347 tok/s | $2.15 | $1.40 | $4.40 | 1M | Z.AI |
| 9Kimi K2.6 | 343 tok/s | $1.71 | $0.950 | $4.00 | 262K | Moonshot |
| 10Kimi K2.5 | 338 tok/s | $1.20 | $0.600 | $3.00 | 262K | Moonshot |
| 11Nova Micro | 300 tok/s | $0.061 | $0.035 | $0.140 | 128K | Amazon |
| 12Nova Lite | 200 tok/s | $0.105 | $0.060 | $0.240 | 300K | Amazon |
| 13DeepSeek V4 Flash | 200 tok/s | $0.175 | $0.140 | $0.280 | 1M | Fireworks |
| 14Granite 4 H Medium | 200 tok/s | $0.262 | $0.150 | $0.600 | 128K | IBM |
| 15Codestral 2508 | 200 tok/s | $0.450 | $0.300 | $0.900 | 256K | Mistral |
| 16GPT-4.1 mini | 200 tok/s | $0.700 | $0.400 | $1.60 | 1M | OpenAI |
| 17GPT-5.4 nano | 191 tok/s | $0.463 | $0.200 | $1.25 | 400K | OpenAI |
| 18GPT-5.6 Luna | 185 tok/s | $0.450 | $0.200 | $1.20 | 1M | OpenAI |
| 19GPT-5.4 mini | 180 tok/s | $1.69 | $0.750 | $4.50 | 1M | OpenAI |
| 20Gemini 3.5 Flash | 175 tok/s | $3.38 | $1.50 | $9.00 | 1M | |
| 21GPT-5.6 Terra | 136 tok/s | $4.50 | $2.00 | $12.00 | 1M | OpenAI |
| 22Grok 4.5 | 88 tok/s | $3.00 | $2.00 | $6.00 | 500K | xAI |
| 23GPT-5.6 Sol | 54 tok/s | $11.25 | $5.00 | $30.00 | 1M | OpenAI |
| 24Kimi K3 | 35 tok/s | $6.00 | $3.00 | $15.00 | 1M | Moonshot |
| 25Qwen3.7-Flash | — | $0.055 | $0.030 | $0.130 | 1M | Alibaba |
| 26Gemini 3.5 Flash-Lite | — | $0.850 | $0.300 | $2.50 | 1M | |
| 27Gemini 3.6 Flash | — | $3.00 | $1.50 | $7.50 | 1M |
Recent price movement in this ranking
price-only deltas · logged by the daily scan2 of the top 27 fast inference models have re-priced since we began tracking · last checked Aug 9, 2026.
| Model | Changes | Latest move | Provider |
|---|---|---|---|
| GPT-5.6 Luna | 1 | price cut on Aug 1, 2026: $1/$6 → $0.2/$1.2 /Mtok | OpenAI |
| GPT-5.6 Terra | 1 | price cut on Aug 1, 2026: $2.5/$15 → $2/$12 /Mtok | OpenAI |
Most recently, GPT-5.6 Luna cut its price on Aug 1, 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 models with independently measured throughput (output tokens per second) or a speed-optimized release, ranked by measured throughput. One row per model — host duplicates are collapsed. Models without a speed measurement rank below measured 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.