Claude Haiku 5.5 vs Gemini 3.8 Flash
anthropic/claude-haiku-5.5 · google/gemini-3.8-flash
As of November 20, 2026, Claude Haiku 5.5 is the cheaper API on MartLLM: $0.0180 per million input tokens and $0.0900 per million output, versus $0.0748 / $0.3743 for Gemini 3.8 Flash, about 76% less when output is 3 tokens for every input token. These are the best prices on the market right now. Both work with one OpenAI-compatible key and MartLLM adds no fee. Choose Claude Haiku 5.5 to cut cost; choose Gemini 3.8 Flash when context size wins. Gemini 3.8 Flash carries the larger context window (1,048,576 vs 1,000,000 tokens), which can matter for long-document work.
Claude Haiku 5.5 vs Gemini 3.8 Flash, side by side
| Spec | ||
|---|---|---|
| Price · input / 1M | $0.0180 | $0.0748 |
| Price · output / 1M | $0.0900 | $0.3743 |
| Context length | 1,000,000 | 1,048,576 |
| Max output tokens | 128,000 | 65,536 |
| Input modalities | text, image, file | text, image, video, audio, file |
| Output modalities | text | text |
| Tools / functions | Yes | Yes |
| Vision (image input) | Yes | Yes |
| Reasoning | Yes | Yes |
| % off list | 82% off | 90% off |
| First token, median (7 days) | 1.9 s (941 requests) | 3.3 s (29,091 requests) |
Best prices on MartLLM right now. No MartLLM fee on requests; adding credit by card costs 5.5% + $0.50. Updated November 20, 2026. A price more than 70% below list is what buyers were billed, not an error. Why so cheap?
Claude Haiku 5.5 vs Gemini 3.8 Flash — FAQ
Is Claude Haiku 5.5 or Gemini 3.8 Flash cheaper?
Claude Haiku 5.5 is cheaper on a blended token mix, by about 76%. A request costs what its provider charged, MartLLM adds no fee, and every request is listed with its cost in Activity.
What's the price difference between Claude Haiku 5.5 and Gemini 3.8 Flash?
Claude Haiku 5.5: $0.0180 in / $0.0900 out per 1M tokens. Gemini 3.8 Flash: $0.0748 in / $0.3743 out per 1M tokens. That's roughly a 76% blended difference. Prices are live; MartLLM adds no fee.
Can I use both Claude Haiku 5.5 and Gemini 3.8 Flash with one API?
Yes. Both are served through a single OpenAI-compatible endpoint — set the base URL to https://api.martllm.com/v1 and your MartLLM key, then switch between them by changing the model id. Anthropic SDKs work via https://api.martllm.com/v1/messages.