Token Pricing Comparison
Prices are per 1 million tokens. All figures are approximate and subject to change.
OpenAI
| Model | Input | Output |
|---|
| GPT-4o | $2.50 | $10.00 |
| GPT-4o mini | $0.15 | $0.60 |
| GPT-4 Turbo | $10.00 | $30.00 |
| GPT-3.5 Turbo | $0.50 | $1.50 |
Anthropic
| Model | Input | Output |
|---|
| Claude 3.5 Sonnet | $3.00 | $15.00 |
| Claude 3 Opus | $15.00 | $75.00 |
| Claude 3 Sonnet | $3.00 | $15.00 |
| Claude 3 Haiku | $0.25 | $1.25 |
Google
| Model | Input | Output |
|---|
| Gemini 1.5 Pro | $3.50 | $10.50 |
| Gemini 1.5 Flash | $0.075 | $0.30 |
| Gemini 1.0 Pro | $0.50 | $1.50 |
Mistral
| Model | Input | Output |
|---|
| Mistral Large | $4.00 | $12.00 |
| Mistral Medium | $2.75 | $8.10 |
| Mistral Small | $1.00 | $3.00 |
| Mistral Tiny | $0.25 | $0.25 |
Cohere
| Model | Input | Output |
|---|
| Command R+ | $3.00 | $15.00 |
| Command R | $0.50 | $1.50 |
Cost Optimization Tips
- Use smaller models first. Start with mini/flash/tiny variants and escalate to larger models only when needed.
- Cache repeated prompts. Prompt caching can reduce costs for repeated context.
- Shorten output where possible. Set
max_tokens to reasonable limits.
- Batch requests. Some providers offer discounted batch pricing.
