Google Gemini API vs DeepSeek
A comparison of Google Gemini API and DeepSeek built from values read directly from each provider's own documentation, with the source recorded against every figure.
The short answer
- Pick Google Gemini API if
- Getting to a working prototype without a card, then staying on the cheapest frontier-adjacent rates in this set — $0.75 per million input tokens is well under half what Anthropic and OpenAI charge for their top models.
- Pick DeepSeek if
- Batch-shaped work that can run outside weekday mornings UTC, where off-peak halves an already low rate and a cache hit costs about 3% of a cache miss.
7 sourced criteria separate them:
- Pricing model
- Google Gemini API: Per million tokens, with dated price changes published in advance — the current Gemini 3.x rates are explicitly promotional through 31 December 2026 and roughly double on 1 January 2027. A free tier exists, and its content is used to improve Google's products where the paid tier's is not.
- DeepSeek: Per million tokens, with every rate doubling at peak: off-peak is half price, and peak is 01:00–04:00 and 06:00–10:00 UTC on weekdays. Cache hits are priced roughly 30x below cache misses.
- Input price, top model
- Google Gemini API: $0.75 per million input tokens for Gemini 3.8 Flash through 31 December 2026, then $1.50. Gemini 3.1 Pro, still preview, is $2.00 for prompts up to 200k tokens and $4.00 above.
- DeepSeek: $1.32 per million input tokens for deepseek-v4-pro at peak on a cache miss, halving to $0.66 off-peak. A cache hit is $0.044 peak.
- Output price, top model
- Google Gemini API: $3.75 per million output tokens for Gemini 3.8 Flash through 31 December 2026, then $7.50. Thinking tokens are billed as output.
- DeepSeek: $3.96 per million output tokens for deepseek-v4-pro at peak, $1.98 off-peak.
- Input price, cheapest model
- Google Gemini API: $0.30 per million input tokens for Gemini 3.5 Flash-Lite, with output at $2.50.
- DeepSeek: $0.44 per million input tokens for deepseek-v4-flash at peak on a cache miss, $0.22 off-peak, with output at $1.32 peak.
- Context window
- Google Gemini API: 1,048,576 tokens for Gemini 3.8 Flash. Read from the Vertex AI model card: the Gemini API docs build their model cards client-side and publish no figure a fetch can read.
- DeepSeek: 1M tokens on every model in the current line.
- Max output tokens
- Google Gemini API: 65,536 tokens for Gemini 3.8 Flash, and Google counts thinking tokens as output.
- DeepSeek: 384K tokens maximum.
- Rate limits
- Google Gemini API: Tied to a usage tier — Free, then Tier 1/2/3 unlocked by cumulative spend — and enforced as requests per minute, input tokens per minute and requests per day. Google publishes no numbers in the docs: limits are viewed in AI Studio and are stated not to be guaranteed.
- DeepSeek: Concurrency rather than requests per minute: 500 concurrent requests on deepseek-v4-pro and 2,500 on deepseek-v4-flash, per account rather than per key. Exceeding it returns HTTP 429, and expansion is free on request.
Pick the criteria you care about. The chart counts how many of them lean toward each provider — the same read as scanning the bars below, just totalled for the ones you chose.
Google Gemini API 0
DeepSeek 0
At a glance.
| Criterion | Google Gemini API | DeepSeek |
|---|---|---|
| Pricing | ||
| Pricing model | Per million tokens, with dated price changes published in advance — the current Gemini 3.x rates are explicitly promotional through 31 December 2026 and roughly double on 1 January 2027. A free tier exists, and its content is used to improve Google's products where the paid tier's is not. | Per million tokens, with every rate doubling at peak: off-peak is half price, and peak is 01:00–04:00 and 06:00–10:00 UTC on weekdays. Cache hits are priced roughly 30x below cache misses. |
| Inference | ||
| Input price, top model | $0.75 per million input tokens for Gemini 3.8 Flash through 31 December 2026, then $1.50. Gemini 3.1 Pro, still preview, is $2.00 for prompts up to 200k tokens and $4.00 above. | $1.32 per million input tokens for deepseek-v4-pro at peak on a cache miss, halving to $0.66 off-peak. A cache hit is $0.044 peak. |
| Output price, top model | $3.75 per million output tokens for Gemini 3.8 Flash through 31 December 2026, then $7.50. Thinking tokens are billed as output. | $3.96 per million output tokens for deepseek-v4-pro at peak, $1.98 off-peak. |
| Input price, cheapest model | $0.30 per million input tokens for Gemini 3.5 Flash-Lite, with output at $2.50. | $0.44 per million input tokens for deepseek-v4-flash at peak on a cache miss, $0.22 off-peak, with output at $1.32 peak. |
| Context window | 1,048,576 tokens for Gemini 3.8 Flash. Read from the Vertex AI model card: the Gemini API docs build their model cards client-side and publish no figure a fetch can read. | 1M tokens on every model in the current line. |
| Max output tokens | 65,536 tokens for Gemini 3.8 Flash, and Google counts thinking tokens as output. | 384K tokens maximum. |
| Prompt caching | Supported | Supported |
| Rate limits | Tied to a usage tier — Free, then Tier 1/2/3 unlocked by cumulative spend — and enforced as requests per minute, input tokens per minute and requests per day. Google publishes no numbers in the docs: limits are viewed in AI Studio and are stated not to be guaranteed. | Concurrency rather than requests per minute: 500 concurrent requests on deepseek-v4-pro and 2,500 on deepseek-v4-flash, per account rather than per key. Exceeding it returns HTTP 429, and expansion is free on request. |
Where they differ.
Pricing model
- Google Gemini API
- Per million tokens, with dated price changes published in advance — the current Gemini 3.x rates are explicitly promotional through 31 December 2026 and roughly double on 1 January 2027. A free tier exists, and its content is used to improve Google's products where the paid tier's is not.
- DeepSeek
- Per million tokens, with every rate doubling at peak: off-peak is half price, and peak is 01:00–04:00 and 06:00–10:00 UTC on weekdays. Cache hits are priced roughly 30x below cache misses.
Sources (2) →Sources ↓
- Gemini Developer API Pricing ↗
“Paid Tier, per 1M tokens in USD [...] $0.75 through December 31, 2026. $1.50 starting January 1, 2027. [...] Used to improve our products | Yes | No”
Read 2026-09-06 · official pricing
- Models & Pricing — DeepSeek API Docs ↗
“The prices listed below are in units of per 1M tokens. [...] Off-peak rates are half of the peak rates. Peak hours are 01:00 - 04:00 and 06:00 - 10:00 UTC, Monday through Friday (all other hours are off-peak).”
Read 2026-09-06 · official pricing
Input price, top model
- Google Gemini API
- $0.75 per million input tokens for Gemini 3.8 Flash through 31 December 2026, then $1.50. Gemini 3.1 Pro, still preview, is $2.00 for prompts up to 200k tokens and $4.00 above.
- DeepSeek
- $1.32 per million input tokens for deepseek-v4-pro at peak on a cache miss, halving to $0.66 off-peak. A cache hit is $0.044 peak.
Sources (2) →Sources ↓
- Gemini Developer API Pricing ↗
“Gemini 3.8 Flash [...] Input price | Free of charge | $0.75 through December 31, 2026. $1.50 starting January 1, 2027. [...] Gemini 3.1 Pro Preview [...] Input price | Not available | $2.00, prompts <= 200k tokens $4.00, prompts > 200k tokens”
Read 2026-09-06 · official pricing
- Models & Pricing — DeepSeek API Docs ↗
“1M INPUT TOKENS (CACHE MISS) OFF-PEAK $0.22 $0.66 $0.22 PEAK $0.44 $1.32 $0.44 [...] 1M INPUT TOKENS (CACHE HIT) OFF-PEAK $0.007 $0.022 $0.007 PEAK $0.014 $0.044 $0.014”
Read 2026-09-06 · official pricing
Output price, top model
- Google Gemini API
- $3.75 per million output tokens for Gemini 3.8 Flash through 31 December 2026, then $7.50. Thinking tokens are billed as output.
- DeepSeek
- $3.96 per million output tokens for deepseek-v4-pro at peak, $1.98 off-peak.
Sources (2) →Sources ↓
- Gemini Developer API Pricing ↗
“Output price (including thinking tokens) | Free of charge | $3.75 through December 31, 2026. $7.50 starting January 1, 2027.”
Read 2026-09-06 · official pricing
- Models & Pricing — DeepSeek API Docs ↗
“1M OUTPUT TOKENS OFF-PEAK $0.66 $1.98 $0.66 PEAK $1.32 $3.96 $1.32”
Read 2026-09-06 · official pricing
Input price, cheapest model
- Google Gemini API
- $0.30 per million input tokens for Gemini 3.5 Flash-Lite, with output at $2.50.
- DeepSeek
- $0.44 per million input tokens for deepseek-v4-flash at peak on a cache miss, $0.22 off-peak, with output at $1.32 peak.
Sources (2) →Sources ↓
- Gemini Developer API Pricing ↗
“Gemini 3.5 Flash-Lite [...] Input price | Free of charge | $0.30 (text / image / video / audio) Output price (including thinking tokens) | Free of charge | $2.50”
Read 2026-09-06 · official pricing
- Models & Pricing — DeepSeek API Docs ↗
“MODEL deepseek-v4-flash [...] 1M INPUT TOKENS (CACHE MISS) OFF-PEAK $0.22 [...] PEAK $0.44 [...] 1M OUTPUT TOKENS [...] PEAK $1.32”
Read 2026-09-06 · official pricing
Context window
1,048,576 tokens for Gemini 3.8 Flash. Read from the Vertex AI model card: the Gemini API docs build their model cards client-side and publish no figure a fetch can read.
1M tokens on every model in the current line.
Sources (2) →Sources ↓
- Gemini 3.8 Flash — Vertex AI model card, Google Cloud ↗
“Token limits Context window 1,048,576 Maximum output tokens 65,536”
Read 2026-09-06 · official docs
- Models & Pricing — DeepSeek API Docs ↗
“CONTEXT LENGTH 1M”
Read 2026-09-06 · official pricing
Max output tokens
65,536 tokens for Gemini 3.8 Flash, and Google counts thinking tokens as output.
384K tokens maximum.
Sources (2) →Sources ↓
- Gemini 3.8 Flash — Vertex AI model card, Google Cloud ↗
“Token limits Context window 1,048,576 Maximum output tokens 65,536”
Read 2026-09-06 · official docs
- Models & Pricing — DeepSeek API Docs ↗
“MAX OUTPUT MAXIMUM: 384K”
Read 2026-09-06 · official pricing
Rate limits
- Google Gemini API
- Tied to a usage tier — Free, then Tier 1/2/3 unlocked by cumulative spend — and enforced as requests per minute, input tokens per minute and requests per day. Google publishes no numbers in the docs: limits are viewed in AI Studio and are stated not to be guaranteed.
- DeepSeek
- Concurrency rather than requests per minute: 500 concurrent requests on deepseek-v4-pro and 2,500 on deepseek-v4-flash, per account rather than per key. Exceeding it returns HTTP 429, and expansion is free on request.
Sources (2) →Sources ↓
- Rate limits — Gemini API ↗
“Rate limits depend on a variety of factors (such as your usage tier) and can be viewed in Google AI Studio. [...] Specified rate limits are not guaranteed and actual capacity may vary. [...] Usage tier | Qualification | Billing tier cap Free | Active project or free trial | N/A Tier 1 | Set up and link an active billing account | $250”
Read 2026-09-06 · official docs
- Rate Limit & Isolation — DeepSeek API Docs ↗
“Concurrency Limit | 500 | 2500 | 2500 [...] Concurrency limits are calculated at the account level, regardless of which API Key is used [...] when the concurrency limit is exceeded, you will receive an HTTP 429 error code [...] There is no additional cost for capacity expansion.”
Read 2026-09-06 · official docs
Which should you choose?
Choose Google Gemini API if…
Getting to a working prototype without a card, then staying on the cheapest frontier-adjacent rates in this set — $0.75 per million input tokens is well under half what Anthropic and OpenAI charge for their top models.
Editorial · Palash Bagchi · approved
Choose DeepSeek if…
Batch-shaped work that can run outside weekday mornings UTC, where off-peak halves an already low rate and a cache hit costs about 3% of a cache miss.
Editorial · Palash Bagchi · approved
Consider something else if…
- Google Gemini API: The rates are dated: they roughly double on 1 January 2027, free-tier content is used to improve Google's products, and rate limits are not published anywhere you can read before signing up.
- DeepSeek: Capacity is expressed as concurrent requests rather than tokens per minute, which is a different thing to plan against, and the peak window lands on European working hours.
Documented by only one.
These criteria are published by one provider and not the other. An absence here means we have not found a source, not that the feature is missing.
Questions this comparison answers.
Should I choose Google Gemini API or DeepSeek?
Pick Google Gemini API if Getting to a working prototype without a card, then staying on the cheapest frontier-adjacent rates in this set — $0.75 per million input tokens is well under half what Anthropic and OpenAI charge for their top models.
Pick DeepSeek if Batch-shaped work that can run outside weekday mornings UTC, where off-peak halves an already low rate and a cache hit costs about 3% of a cache miss.