Claude Haiku 4.5 vs Gemini 3.8 Flash API pricing
Updated
Claude Haiku 4.5: USD 1 input, USD 5 output per 1M tokens (Anthropic and 3 others). Gemini 3.8 Flash: USD 0.75 input, USD 3.75 output per 1M tokens (Google Gemini API and 2 others, promotional). At 3 input tokens per output token, Claude Haiku 4.5 costs 33% more than Gemini 3.8 Flash (USD 2 vs USD 1.50 per 1M).
How do Claude Haiku 4.5 and Gemini 3.8 Flash differ on price?
- Cheapest input price: Gemini 3.8 Flash USD 0.75 against USD 1 per 1M tokens, so Claude Haiku 4.5 costs 1.33× as much (33% more).
- Cheapest output price: Gemini 3.8 Flash USD 3.75 against USD 5 per 1M tokens, so Claude Haiku 4.5 costs 1.33× as much (33% more).
- Among the 201 indexed models, Claude Haiku 4.5 ranks 154th cheapest and Gemini 3.8 Flash 144th on the 3:1 blend.
- No input:output mix changes the answer: Gemini 3.8 Flash is cheaper at every mix before cache discounts.
- Both list cached-input discounts: Claude Haiku 4.5 at 4 standard prices of 5, from USD 0.10 (Anthropic, 90% below that provider's input price); Gemini 3.8 Flash at 3 standard prices of 3, from USD 0.075 (Google Gemini API, 90% below that provider's input price).
- Gemini 3.8 Flash states up to 1,048,576 tokens of context, 5.2× the 200,000 of Claude Haiku 4.5.
- Claude Haiku 4.5 has 5 providers with a standard price, 2 more than Gemini 3.8 Flash; 1 provider sells both (Google Vertex AI).
- On one account, Google Vertex AI charges USD 2 for Claude Haiku 4.5 (its cheapest price) and USD 1.50 for Gemini 3.8 Flash (its cheapest price) at 3:1, the lowest combined price among the providers that sell both.
- Shopping around matters more for Claude Haiku 4.5: its dearest standard price is 1.1× its cheapest, against 1× for Gemini 3.8 Flash.
- Anthropic's own API is one of 4 providers tied for the lowest standard price we found for Claude Haiku 4.5, USD 2 at 3:1.
- Google's own API is one of 3 providers tied for the lowest standard price we found for Gemini 3.8 Flash, USD 1.50 at 3:1.
- Claude Haiku 4.5 has a batch price at 3 providers, from USD 1 at 3:1 (Anthropic); Gemini 3.8 Flash has a batch price at 2 providers, from USD 0.75 at 3:1 (Google Gemini API).
- For the one-developer coding agent preset, the gap is USD 2,619 a year in Gemini 3.8 Flash's favour (Claude Haiku 4.5 USD 873.00 a month, Gemini 3.8 Flash USD 654.75).
Claude Haiku 4.5 and Gemini 3.8 Flash prices side by side
USD per 1M tokens, standard tier. "Cheapest" is the lowest price at 3 input tokens to 1 output token; each line can come from a different provider.
| Price | Claude Haiku 4.5 | Gemini 3.8 Flash |
|---|---|---|
| Model page | Claude Haiku 4.5 Anthropic · 5 providers | Gemini 3.8 Flash Google · 3 providers |
| Cheapest standard price, blended 3:1 | USD 2 USD 1 in / USD 5 out at Anthropic and 3 others Anthropic page checked 2026-11-14 | USD 1.50 lower promo USD 0.75 in / USD 3.75 out at Google Gemini API and 2 others Google Gemini API page checked 2026-11-14 |
| Cheapest input | USD 1 Anthropic source | USD 0.75 lower promo Google Gemini API source |
| Cheapest cached input | USD 0.10 Anthropic source | USD 0.075 lower promo Google Gemini API source |
| Cheapest output | USD 5 Anthropic source | USD 3.75 lower promo Google Gemini API source |
| Cheapest non-promotional price | The cheapest price is not promotional. | USD 0.75 / USD 3.75 GMI Cloud, USD 1.50 blended source |
| Maker's own API | USD 1 / USD 5 Anthropic source | USD 0.75 / USD 3.75 promo Google Gemini API source |
| Median standard price | USD 1 / USD 5 input / output, 5 prices | USD 0.75 / USD 3.75 input / output, 3 prices |
| Context window | 200,000 tokens, largest stated | 1,048,576 tokens, largest stated |
| Providers with a standard price | 5 | 3 |
- Lower marks the lower price on a line; tie, equal prices. Other tiers and free rows are on the model pages.
- Promo: the provider calls the price promotional or discounted, so it is current now and can end without notice.
Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).
What do Claude Haiku 4.5 and Gemini 3.8 Flash cost for a real workload?
30 days at each model's cheapest standard price for the workload (presets of the cost calculator; cached input at the cached price where listed).
| Workload | Claude Haiku 4.5 | Gemini 3.8 Flash | Difference |
|---|---|---|---|
| Support chatbot 2,000 requests a day, 1,500 input tokens (60% cached), 300 output | USD 131.40 Anthropic | USD 98.55 Google Gemini API | USD 32.85 Gemini 3.8 Flash lower |
| RAG over documents 1,000 requests a day, 8,000 input tokens (30% cached), 500 output | USD 250.20 Anthropic | USD 187.65 Google Gemini API | USD 62.55 Gemini 3.8 Flash lower |
| Coding agent (one developer) 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning | USD 873.00 Anthropic | USD 654.75 Google Gemini API | USD 218.25 Gemini 3.8 Flash lower |
Gemini 3.8 Flash is cheaper on all three workloads. The widest gap is on Support chatbot: the dearer model costs 33% more than the cheaper one.
Does the cheaper model change with your input:output ratio?
Gemini 3.8 Flash is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Claude Haiku 4.5's, so the input:output ratio never changes the answer.
| Input : output tokens | Claude Haiku 4.5 | Gemini 3.8 Flash |
|---|---|---|
| 1 : 3 (long answers) | USD 4 Anthropic | USD 3 lower Google Gemini API |
| 1 : 1 | USD 3 Anthropic | USD 2.25 lower Google Gemini API |
| 3 : 1 (the site’s blend) | USD 2 Anthropic | USD 1.50 lower Google Gemini API |
| 10 : 1 (retrieval, long prompts) | USD 1.364 Anthropic | USD 1.023 lower Google Gemini API |
| 30 : 1 (agents, big contexts) | USD 1.129 Anthropic | USD 0.8468 lower Google Gemini API |
USD per 1M tokens at the cheapest standard provider for each mix, before cache discounts. Thinking tokens bill as output.
What do Claude Haiku 4.5 and Gemini 3.8 Flash cost per character in other languages?
Not measured: the real cost by language dataset covers only tokenizers we could measure from published files, and Claude Haiku 4.5 and Gemini 3.8 Flash are not among them. Count tokens on your own text with the counters below.
Check it on your own traffic
- Claude Haiku 4.5 API pricing: all 5 providers and other tiers.
- Gemini 3.8 Flash API pricing: all 3 providers and other tiers.
- Cost calculator with Claude Haiku 4.5 and Gemini 3.8 Flash preloaded
- Token counter
- Prompt caching calculator
More comparisons: Claude Haiku 5.5 vs Claude Haiku 4.5 · Gemini 3.8 Flash vs Gemini 3.7 Flash · Claude Haiku 5.5 vs Gemini 3.8 Flash · GPT-6 Luna vs Gemini 3.8 Flash · Gemini 3.8 Flash vs DeepSeek V4.1 Flash · every Claude Haiku 4.5 comparison · every Gemini 3.8 Flash comparison · all 662 price comparisons
Questions
Is Claude Haiku 4.5 cheaper than Gemini 3.8 Flash?
No. On a blend of 3 input tokens to 1 output token, Gemini 3.8 Flash costs USD 1.50 per 1M tokens and Claude Haiku 4.5 USD 2, at each model's cheapest standard price. For input alone, Gemini 3.8 Flash is cheaper (USD 0.75 against USD 1 per 1M); for output alone, Gemini 3.8 Flash is (USD 3.75 against USD 5). This compares price only, not quality.
What do Claude Haiku 4.5 and Gemini 3.8 Flash cost per 1M tokens?
Claude Haiku 4.5: from USD 1 input and USD 5 output at Anthropic and 3 others; Anthropic's own API charges USD 1 / USD 5; median of 5 standard prices USD 1 / USD 5. Gemini 3.8 Flash: from USD 0.75 input and USD 3.75 output at Google Gemini API and 2 others (promotional); Google Gemini API's own API charges USD 0.75 / USD 3.75; median of 3 standard prices USD 0.75 / USD 3.75. Each price is read from the provider's own pricing page; the source is linked in the table.
Which providers sell both Claude Haiku 4.5 and Gemini 3.8 Flash?
1 provider has a standard price for both: Google Vertex AI (USD 2 and USD 1.50 at 3:1). Buying each model from its own cheapest provider costs USD 2 and USD 1.50.
Which is cheaper for a coding agent or a chatbot, Claude Haiku 4.5 or Gemini 3.8 Flash?
For a coding agent (1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning): USD 873.00 a month on Claude Haiku 4.5 (Anthropic) against USD 654.75 on Gemini 3.8 Flash (Google Gemini API), a difference of USD 218.25. For a support chatbot (2,000 requests a day, 1,500 input tokens (60% cached), 300 output): USD 131.40 a month on Claude Haiku 4.5 (Anthropic) against USD 98.55 on Gemini 3.8 Flash (Google Gemini API), a difference of USD 32.85. Each uses the cheapest standard price for that workload, cached input included. Try your own numbers.
At what input:output ratio does the cheaper of Claude Haiku 4.5 and Gemini 3.8 Flash change?
Gemini 3.8 Flash is cheaper at every mix of input and output tokens, before cache discounts: its cheapest input price and its cheapest output price are both at or below Claude Haiku 4.5's, so the input:output ratio never changes the answer.
Do Claude Haiku 4.5 and Gemini 3.8 Flash have cached input pricing?
Claude Haiku 4.5 from USD 0.10 per 1M cached input tokens (Anthropic; 4 of 5 standard prices list a discount). Gemini 3.8 Flash from USD 0.075 per 1M cached input tokens (Google Gemini API; 3 of 3 standard prices list a discount). Cached tokens are billed at the input price where no cache price is published.
Which has the larger context window, Claude Haiku 4.5 or Gemini 3.8 Flash?
Gemini 3.8 Flash: up to 1,048,576 tokens, against 200,000 for Claude Haiku 4.5, as stated on providers' pricing pages. Some providers offer less than the maximum; check the model pages before you pick the cheapest row for long prompts.
Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity
Sources
- Anthropic: own API pricing (checked 2026-11-14)
- DeepInfra: pricing (checked 2026-11-14)
- DigitalOcean: pricing (checked 2026-11-14)
- Google Vertex AI: pricing (checked 2026-11-14)
- Google Gemini API: own API pricing (checked 2026-11-14)
- GMI Cloud: pricing (checked 2026-11-15)
- Google Vertex AI: pricing (checked 2026-11-14)