OpenAI · 2023-08-28
GPT-3.5 Turbo 16k pricing
This model offers four times the context length of gpt-3.5-turbo, allowing it to support approximately 20 pages of text in a single request at a higher cost.
Prices from OpenRouter’s models API, updated October 29, 2026
What GPT-3.5 Turbo 16k costs a month
| Workload | Standard |
|---|---|
| Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out | $183 |
| Daily summaries: 10,000 a day, 3,000 tokens in, 300 out | $3,060 |
| Coding agent: 400 calls a day, 60,000 tokens in (80% cached), 2,000 out | $2,256 |
30 days. Cached input billed at the cache-read price. Use your own numbers.
Cheaper models with a similar context window
| Model | Provider | Input /1M | Output /1M | Cache read /1M | Context | Chatbot, per month* |
|---|---|---|---|---|---|---|
| GLM 5.3 Flash | Z.ai | $0.046 | $0.074 | $0.03 | 1.05M | $2.95 |
| Mercury 2.5 | inception | $0.04 | $0.15 | $0.004 | 260K | $3.60 |
| Granite 4.2 8B | ibm-granite | $0.06 | $0.15 | $0.015 | 131K | $4.50 |
| Solar Mini 4 | upstage | $0.05 | $0.20 | $0.005 | 524K | $4.65 |
| Ling 3.0 Flash VL | inclusionai | $0.06 | $0.18 | $0.012 | 131K | $4.86 |
* Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out, 30 days, no caching. Prices in US dollars per 1M tokens.
Cheaper isn’t automatically as good. Glow’s GlowBench scores models on your kind of task before suggesting a swap.
Other GPT models
| Model | Input /1M | Output /1M | Cache read /1M | Context | Chatbot, per month* |
|---|---|---|---|---|---|
| GPT-6.1 Terra | $1 | $5 | $0.05 | 1.05M | $105 |
| GPT-6.1 Terra Pro | $1 | $5 | $0.05 | 1.05M | $105 |
| GPT-6.1 Sol | $2 | $10 | $0.10 | 1.05M | $210 |
| GPT-6.1 Sol Pro | $2 | $10 | $0.10 | 1.05M | $210 |
| GPT-6 Luna | $0.10 | $0.50 | $0.01 | 1.05M | $10.50 |
| GPT-6 Luna Pro | $0.10 | $0.50 | $0.01 | 1.05M | $10.50 |
* Support chatbot: 1,000 chats a day, 1,500 tokens in, 400 out, 30 days, no caching. Prices in US dollars per 1M tokens.
Related
GPT-3.5 Turbo 16k: questions
How much does GPT-3.5 Turbo 16k cost?
$3 per 1M input tokens and $4 per 1M output tokens. A 1,000-token prompt with a 500-token answer costs about $0.0050.
What is GPT-3.5 Turbo 16k’s context window?
16,385 tokens, with up to 4,096 output tokens per response.
Is there a cheaper alternative to GPT-3.5 Turbo 16k?
GLM 5.3 Flash costs $0.046 in and $0.074 out per 1M tokens with a similar context window. Whether it matches GPT-3.5 Turbo 16k’s quality depends on the task: test it on your own prompts (Glow’s GlowBench does this per task).
Know what each model really costs you.
Connect OpenRouter and Glow shows spend by model, key and product, and flags the swap that saves the most at the same quality.
- Read-only keys
- Never shown again
- 2FA + Face ID
- 7-day trial