ERNIE 4.5 Turbo API pricing
Official Baidu ERNIE list price, last checked Oct 29, 2026. Updated Oct 29, 2026.
ERNIE 4.5 Turbo costs $0.11 per 1M input tokens and $0.45 per 1M output tokens, cached input at $0.03, and a 128K-token context window, per Baidu ERNIE's official pricing page (checked Oct 29, 2026). It's one of the cheapest models we track: number 6 of 77 by blended price ($0.195 per 1M tokens at a 3 to 1 input to output mix). LMArena doesn't list it on the boards we track, so we don't rank its quality. For less, look at Qwen3.7 Flash ($0.055 blended).
ERNIE 4.5 Turbo price per million tokens
| ERNIE 4.5 Turbo price per million tokens | USD |
|---|---|
| Input | $0.11 |
| Cached input | $0.03 |
| Output | $0.45 |
| Blended, 3 parts input to 1 part output | $0.195 |
| Context window | 128K tokens |
Official note from Baidu ERNIE: Same price for the 32K and 128K versions.
What ERNIE 4.5 Turbo costs for real work
List-price estimates for a month, no discounts. Our math, not a quote: change the token counts in the plan vs API calculator.
| Workload | Tokens a month | ERNIE 4.5 Turbo | GPT-6 Luna | Qwen3.7 Flash |
|---|---|---|---|---|
| Light: a side project or personal assistant | 2M in, 0.5M out | $0.45 | $0.45 | $0.12 |
| Medium: a small team or one product feature | 20M in, 5M out | $4.45 | $4.50 | $1.25 |
| Heavy: a production app | 200M in, 50M out | $44.50 | $45.00 | $12.50 |
| Medium with 80% of input cached | 20M in (16M cached), 5M out | $3.17 | $3.06 | n/a |
How ERNIE 4.5 Turbo ranks on LMArena
It isn't on any LMArena board we track as of Oct 29, 2026. We don't estimate quality for unranked models. See the best model for each task for ranked options.
Closest rivals to ERNIE 4.5 Turbo
The models nearest in price, other makers first. Ranks are on LMArena, where we have them.
| Model | In / out | Blended | Verdict |
|---|---|---|---|
| GPT-6 Luna | $0.10 / $0.50 | $0.20 | Same price, no score to separate them. Compare |
| Claude Haiku 5.5 | $0.10 / $0.50 | $0.20 | Same price, no score to separate them. Compare |
| Qwen3.5 Flash | $0.10 / $0.40 | $0.175 | Qwen3.5 Flash wins on price. Compare |
| Seed 2.0 Mini | $0.10 / $0.40 | $0.175 | Seed 2.0 Mini wins on price. Compare |
Cheaper alternatives to ERNIE 4.5 Turbo
At least 40% cheaper blended, cheapest at the bottom of the list we found.
| Model | In / out | Blended | Verdict |
|---|---|---|---|
| Qwen3.7 Flash | $0.03 / $0.13 | $0.055 | Qwen3.7 Flash wins on price. Compare |
More from Baidu ERNIE
FAQ
How much does the ERNIE 4.5 Turbo API cost per million tokens?
$0.11 per 1M input tokens and $0.45 per 1M output tokens, plus $0.03 per 1M for cached input, as of Oct 29, 2026. A typical 3 to 1 input to output mix works out to $0.195 per 1M tokens.
Does ERNIE 4.5 Turbo charge more for long prompts?
Baidu ERNIE doesn't list a long-prompt surcharge for ERNIE 4.5 Turbo. Its pricing note says: Same price for the 32K and 128K versions.
Is ERNIE 4.5 Turbo cheaper than GPT-6 Luna?
Yes. A medium month (20M input and 5M output tokens) costs $4.45 on ERNIE 4.5 Turbo and $4.50 on GPT-6 Luna at list price.
How does ERNIE 4.5 Turbo rank on LMArena?
It isn't listed on the LMArena boards we track, so we show no quality rank rather than guess.
What is a cheaper alternative to ERNIE 4.5 Turbo?
Qwen3.7 Flash costs $0.03 in and $0.13 out per 1M tokens, about 3.5x less blended.
Where does this ERNIE 4.5 Turbo price come from?
From Baidu ERNIE's official pricing page, which we check every day. This page was last checked Oct 29, 2026.