gpt-3-5-turbo
Developer: OpenAI
Also known as
GPT-3.5 Turbo by OpenAI is available through 141 API providers on LMSpeed. Compare API pricing from $0.300 to $75.00 per million input tokens across providers. Free API access is offered by 1 provider. In speed benchmarks, the fastest provider reaches 161 tok/s.
Compare GPT-3.5 Turbo API pricing across 140 providers. Input prices range from $0.300 to $75.00 per million input. 人人 API offers the lowest rate at $0.300/M.
| Provider | Model Variant | Input ($/M) | Output ($/M) | Speed (t/s) |
|---|---|---|---|---|
| 梦德 API | gpt-3.5-turbo | Free | Free | — |
| 人人 API | gpt-3.5-turbo | $0.300 | $2.40 | — |
 KKSJ-AI | gpt-3.5-turbo | $0.450 | $0.900 | — |
| KKSJ-AI | gpt-3.5-turbo-0125 | $0.450 | $0.900 | — |
 OpenRouter Fans | openai/gpt-3.5-turbo | $0.450 | $1.40 | — |
| AAAI | gpt-3.5-turbo | $0.500 | $1.50 | — |
| AAAI | gpt-3.5-turbo-0125 | $0.500 | $1.50 | — |
 SanShui API | gpt-3.5-turbo-0125 | $0.500 | $1.50 | — |
 柏拉图AI | gpt-3.5-turbo | $0.500 | $1.00 | — |
| 柏拉图AI | gpt-3.5-turbo-0125 | $0.500 | $1.00 | — |
 UnifyLLM | gpt-3.5-turbo | $0.500 | $1.00 | — |
| UnifyLLM | gpt-3.5-turbo-0125 | $0.500 | $1.00 | — |
 V-API | gpt-3.5-turbo | $0.500 | $1.50 | — |
| V-API | gpt-3.5-turbo-0125 | $0.500 | $1.50 | — |
 毫秒API | gpt-3.5-turbo | $0.500 | $1.00 | — |
| 毫秒API | gpt-3.5-turbo-0125 | $0.500 | $1.00 | — |
| gpt-3.5-turbo | $0.500 | $1.00 | — | |
| gpt-3.5-turbo-0125 | $0.500 | $1.00 | — | |
 AIO通用智能服务平台 | gpt-3.5-turbo | $0.500 | $1.00 | — |
| AIO通用智能服务平台 | gpt-3.5-turbo-0125 | $0.500 | $1.00 | — |
Pricing data from provider public APIs
GPT-3.5 Turbo is free to use through 1 provider with no per-token charges. These providers offer free API credits or a free tier:
| Provider | Speed (t/s) |
|---|---|
| 梦德 API | — |
Compare speed and latency performance across all API providers.
Showing 1-11 of 11 providers
| Provider | Speed | Latency | Tests |
|---|---|---|---|
 Dream APIgpt-3.5-turbo-16k | 160.99 tok/s | 0.75s | 2 |
| Dream API gpt-3.5-turbo-1106 | 157.63 tok/s | 1.23s | 1 |
 gpt-3.5-turbo-1106 | 156.06 tok/s | 0.71s | 4 |
gpt-3.5-turbo-0613 | 142.12 tok/s | 0.66s | 1 |
 gpt-3.5-turbo-0613 | 139.83 tok/s | 0.46s | 4 |
gpt-3.5-turbo-16k | 135.58 tok/s | 0.56s | 3 |
gpt-3.5-turbo-0125 | 123.25 tok/s | 0.69s | 4 |
gpt-3.5-turbo | 108.16 tok/s | 2.28s | 24 |
gpt-3.5-turbo-16k-0613 | 108.01 tok/s | 0.73s | 5 |
gpt-3.5-turbo | 103.80 tok/s | 0.36s | 1 |
gpt-3.5-turbo-0125 | 54.37 tok/s | 9.59s | 5 |
Latest benchmark results measuring API response speed and first-token latency.
| Time | Model | Speed | Latency |
|---|---|---|---|
| 04/13/2026, 09:22 | gpt-3.5-turbo-0125 | 56.19 tok/s | 6.69s |
| 04/13/2026, 09:22 | gpt-3.5-turbo-0125 | 89.33 tok/s | 7.43s |
| 04/13/2026, 09:22 | gpt-3.5-turbo-0125 | 38.66 tok/s | 17.32s |
| 04/13/2026, 09:22 | gpt-3.5-turbo-0125 | 36.48 tok/s | 4.22s |
| 04/13/2026, 09:22 | gpt-3.5-turbo-0125 | 51.20 tok/s | 12.30s |
| 07/12/2025, 12:26 | gpt-3.5-turbo | 53.23 tok/s | 2.66s |
| 07/12/2025, 12:26 | gpt-3.5-turbo | 85.88 tok/s | 2.63s |
| 07/12/2025, 12:26 | gpt-3.5-turbo | 76.75 tok/s | 4.87s |
| 07/12/2025, 12:26 | gpt-3.5-turbo | 57.59 tok/s | 1.28s |
| 07/12/2025, 12:26 | gpt-3.5-turbo | 89.46 tok/s | 2.70s |
| 07/12/2025, 11:23 | gpt-3.5-turbo | 50.09 tok/s | 2.51s |
| 07/12/2025, 11:23 | gpt-3.5-turbo | 74.24 tok/s | 3.90s |
| 07/12/2025, 11:23 | gpt-3.5-turbo | 82.81 tok/s | 3.93s |
| 07/12/2025, 11:23 | gpt-3.5-turbo | 35.04 tok/s | 2.18s |
| 07/12/2025, 11:23 | gpt-3.5-turbo | 74.27 tok/s | 2.99s |
| 07/12/2025, 11:21 | gpt-3.5-turbo | 60.44 tok/s | 2.38s |
| 07/12/2025, 11:21 | gpt-3.5-turbo | 78.56 tok/s | 3.54s |
| 07/12/2025, 11:21 | gpt-3.5-turbo | 73.81 tok/s | 4.51s |
| 07/12/2025, 11:21 | gpt-3.5-turbo | 233.22 tok/s | 1.60s |
| 07/12/2025, 11:21 | gpt-3.5-turbo | 360.11 tok/s | 2.40s |
