per 1M tokens
OpenAI: GPT-4
openai/gpt-4
OpenAI's flagship model, GPT-4 is a large-scale multimodal language model capable of solving difficult problems with greater accuracy than previous models due to its broader general knowledge and advanced reasoning...
Price
per 1M tokens
Providers
Each row is one seller. Prices are the published rate from that source. A dash means that source did not publish the amount. Sorted by a 3:1 blend of input and output.
| Provider | Tag | Quant | Input | Output | Context | Uptime | Status | Source |
|---|---|---|---|---|---|---|---|---|
| Azure | azure | — | $30/1M | $60/1M | 8K | — | Live | openrouter-endpoints |
Monthly bill
Token models use the token counts. Image, video, and audio models use units times the flat rate.
$90.00 at list price for this workload
Every rate
| Unit | Input | Output | Flat | Confidence |
|---|---|---|---|---|
| token | $30/1M | $60/1M | Not published— | official |
Price history
input or flat output
Daily snapshots
| UTC date | Unit | Input | Output | Flat |
|---|---|---|---|---|
| 2026-09-15 | token | $30 | $60 | Not published— |
| 2026-09-16 | token | $30 | $60 | Not published— |
| 2026-09-17 | token | $30 | $60 | Not published— |
| 2026-09-18 | token | $30 | $60 | Not published— |
| 2026-09-19 | token | $30 | $60 | Not published— |
| 2026-09-20 | token | $30 | $60 | Not published— |
| 2026-09-21 | token | $30 | $60 | Not published— |
| 2026-09-22 | token | $30 | $60 | Not published— |
| 2026-09-23 | token | $30 | $60 | Not published— |
| 2026-09-24 | token | $30 | $60 | Not published— |
| 2026-09-25 | token | $30 | $60 | Not published— |
| 2026-09-26 | token | $30 | $60 | Not published— |
| 2026-09-27 | token | $30 | $60 | Not published— |
| 2026-09-28 | token | $30 | $60 | Not published— |
| 2026-09-29 | token | $30 | $60 | Not published— |
| 2026-09-30 | token | $30 | $60 | Not published— |
| 2026-10-01 | token | $30 | $60 | Not published— |
| 2026-10-02 | token | $30 | $60 | Not published— |
| 2026-10-03 | token | $30 | $60 | Not published— |
| 2026-10-04 | token | $30 | $60 | Not published— |
| 2026-10-05 | token | $30 | $60 | Not published— |
| 2026-10-06 | token | $30 | $60 | Not published— |
| 2026-10-07 | token | $30 | $60 | Not published— |
| 2026-10-08 | token | $30 | $60 | Not published— |
| 2026-10-09 | token | $30 | $60 | Not published— |
| 2026-10-10 | token | $30 | $60 | Not published— |
| 2026-10-11 | token | $30 | $60 | Not published— |
| 2026-10-12 | token | $30 | $60 | Not published— |
| 2026-10-13 | token | $30 | $60 | Not published— |
| 2026-10-14 | token | $30 | $60 | Not published— |
| 2026-10-15 | token | $30 | $60 | Not published— |
| 2026-10-16 | token | $30 | $60 | Not published— |
| 2026-10-17 | token | $30 | $60 | Not published— |
| 2026-10-18 | token | $30 | $60 | Not published— |
| 2026-10-19 | token | $30 | $60 | Not published— |
| 2026-10-20 | token | $30 | $60 | Not published— |
| 2026-10-21 | token | $30 | $60 | Not published— |
| 2026-10-22 | token | $30 | $60 | Not published— |
| 2026-10-23 | token | $30 | $60 | Not published— |
| 2026-10-24 | token | $30 | $60 | Not published— |
| 2026-10-25 | token | $30 | $60 | Not published— |
| 2026-10-26 | token | $30 | $60 | Not published— |
| 2026-10-27 | token | $30 | $60 | Not published— |
| 2026-10-28 | token | $30 | $60 | Not published— |
| 2026-10-29 | token | $30 | $60 | Not published— |
| 2026-10-30 | token | $30 | $60 | Not published— |
Alternatives
- openai-gpt-54-pro$30/1M · Compare
- openai-gpt-55-pro$30/1M · Compare
- OpenAI: GPT-5.4 Pro$30/1M · Compare
- OpenAI: GPT-5.5 Pro$30/1M · Compare
- Sourceful: Riverflow V2.5 Pro$31.138/1M · Compare
- Sourceful: Riverflow V2.6 Pro$31.138/1M · Compare
Parameters (13)
frequency_penaltylogit_biaslogprobsmax_completion_tokenspresence_penaltyresponse_formatseedstoptemperaturetool_choicetoolstop_logprobstop_p
Call this model
OpenRouter id openai/gpt-4. InferenceList does not send the request.
curl
curl https://openrouter.ai/api/v1/chat/completions \
-H "Authorization: Bearer $OPENROUTER_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"openai/gpt-4","messages":[{"role":"user","content":"Hello"}]}'
JavaScript
await fetch("https://openrouter.ai/api/v1/chat/completions", {
method: "POST",
headers: {
Authorization: "Bearer " + process.env.OPENROUTER_API_KEY,
"Content-Type": "application/json",
},
body: JSON.stringify({
model: "openai/gpt-4",
messages: [{ role: "user", content: "Hello" }],
}),
});
Python
import os, json, urllib.request
req = urllib.request.Request(
"https://openrouter.ai/api/v1/chat/completions",
data=json.dumps({"model": "openai/gpt-4", "messages": [{"role": "user", "content": "Hello"}]}).encode(),
headers={"Authorization": "Bearer " + os.environ["OPENROUTER_API_KEY"], "Content-Type": "application/json"},
)
print(urllib.request.urlopen(req).read().decode())