Claude Haiku 4.5 vs Gemini 2.5 Flash
Gemini 2.5 Flash is cheaper for every workload modelled here.
List prices checked
Specifications and rates
| Property | Claude Haiku 4.5 | Gemini 2.5 Flash |
|---|---|---|
| Input per 1M | $1.00 | $0.300 |
| Output per 1M | $5.00 | $2.50 |
| Cached input per 1M | $0.100 | $0.075 |
| Blended (3:1) | $2.00 | $0.850 |
| Context window | 200K | 1M |
| Max output | 64K | 66K |
| Inputs accepted | text, image | text, image, audio, video |
Source: Anthropic pricing (August 2026) · Google pricing (May 2026). Published list prices only — committed-use discounts, regional variation, and per-request charges are not included. Not yet independently re-checked against the vendor’s page.
Monthly cost by workload
Identical token volumes through both rate cards. Output-heavy profiles are where the ranking flips.
| Workload | Claude Haiku 4.5 | Gemini 2.5 Flash | Cheaper |
|---|---|---|---|
| In-app chat assistantA support or help assistant handling a few thousand conversations a month, with short prompts and short answers. | $45 | $19 | Gemini 2.5 Flashsaves $27/mo (59%) |
| RAG over documentsRetrieval-augmented answering where each request stuffs several retrieved passages into the prompt, so input dominates. | $375 | $128 | Gemini 2.5 Flashsaves $248/mo (66%) |
| Coding agentAn agentic loop that reads files and writes patches, generating heavy output and re-sending large context on every turn. | $900 | $370 | Gemini 2.5 Flashsaves $530/mo (59%) |
What each one is for
Claude Haiku 4.5
by Anthropic
The fast, cheap end of the Claude family, priced at a third of Sonnet while keeping the same context window. Suited to classification, extraction, and high-volume routing.
Gemini 2.5 Flash
by Google
The best price-to-context ratio on the market: a million tokens of multimodal input for a fraction of what frontier models charge, with optional thinking budgets.
Common questions
- Is Claude Haiku 4.5 or Gemini 2.5 Flash cheaper in 2026?
- Gemini 2.5 Flash, for every workload modelled here. On a blended 3:1 basis it costs $0.850 per million tokens against Claude Haiku 4.5's $2.00.
- Which has the larger context window?
- Gemini 2.5 Flash, at 1M tokens against 200K. A larger window only helps if you can afford to fill it — the cost of one full-context request is in the table above.
- Which is cheaper for output-heavy work like agents?
- Gemini 2.5 Flash, at $2.50 per million output tokens against $5.00. Reasoning tokens bill as output, so for agentic loops this axis usually decides the invoice regardless of what the input rates look like.
- What is not included in these figures?
- Batch-processing discounts, fine-tuning, long-context surcharges above a provider's standard tier, and any enterprise agreement. These are published pay-as-you-go list prices, checked against each provider's own pricing page on the date shown.
- Is switching from Claude Haiku 4.5 to Gemini 2.5 Flash worth it?
- On price alone it is about 57% cheaper on a blended basis. Whether that survives contact with your workload depends on output quality and on retry rate — a cheaper model that needs two attempts is not cheaper. Model the specific volumes in the calculator before you migrate.