Claude Haiku 5.5 is Claude's fastest and most affordable model, priced at $0.10/MTok input and $0.50/MTok output with a 1M context window. Added by the model-onboarding job on 2026-10-08. Prices confirmed by the provider pricing page and the LiteLLM cross-check. Release date from the provider model list. Not yet benchmarked, so never recommended.
Input $/MTok
$0.10
Output $/MTok
$0.50
Context window
1M
Cache read discount
90% off
| Rate | Input $/MTok | Output $/MTok |
|---|---|---|
| Standard | $0.10 | $0.50 |
| Cached read (90% off input) | $0.01 | - |
| Cached write (25% surcharge) | $0.13 | - |
| Batch (50% off) | $0.05 | $0.25 |
| Long context (≥100.001K tokens) | $0.50 | $2.50 |
All rates in USD per million tokens. Prices verified against provider documentation.
Confidence scores (0-100) and cross-provider rank for each task type. Rank 1 is best across all 76 models.
Not benchmarked. The third-party benchmark source used for confidence scores does not cover Claude models yet. Scores will appear here once independent benchmarks are published.
Estimated cost per API call using default token counts for each workload.
| Use case | Input tokens | Output tokens | Cost / call |
|---|---|---|---|
| Code Generation | 2,000 | 4,000 | $0.002200 |
| Unit Test Generation | 3,000 | 5,000 | $0.002800 |
| SQL Generation | 1,500 | 1,000 | $0.000650 |
| API Generation | 3,000 | 6,000 | $0.003300 |
| Code Refactoring | 4,000 | 4,000 | $0.002400 |
| Code Review | 5,000 | 2,000 | $0.001500 |
| PR Review | 8,000 | 3,000 | $0.002300 |
| Security Review | 6,000 | 2,500 | $0.001850 |
| Bug Detection | 5,000 | 2,000 | $0.001500 |
| Document Summarization | 10,000 | 1,000 | $0.001500 |
| PDF Summarization | 15,000 | 1,500 | $0.002250 |
| Meeting Notes | 8,000 | 2,000 | $0.001800 |
Projected monthly spend at different call volumes, using code generation as a representative workload (2,000 input / 4,000 output tokens per call).
| Calls / month | Without caching | With caching (90% read discount) |
|---|---|---|
| 1K | $2.2 | $2.07 |
| 10K | $22 | $20.74 |
| 100K | $220 | $207.4 |
| 500K | $1,100 | $1,037 |
| 1M | $2,200 | $2,074 |
Caching estimate assumes 70% of input tokens are cache reads. Your actual cache hit rate will depend on prompt structure and reuse.
Same-tier models from other providers, sorted by input price.
| Model | Provider | Input $/MTok | Output $/MTok | Input savings |
|---|---|---|---|---|
| GPT 5 Nano | GPT | $0.05 | $0.40 | 50% cheaper |
| GPT 4.1 Nano | GPT | $0.10 | $0.40 | Same price |
| GPT 6 Luna | GPT | $0.10 | $0.50 | Same price |
| Gemini 2.5 Flash-Lite | Gemini | $0.10 | $0.40 | Same price |
| GPT 4o Mini | GPT | $0.15 | $0.60 | 50% more |
| GPT 5.6 Luna | GPT | $0.20 | $1.20 | 100% more |
| GPT 5.4 Nano | GPT | $0.20 | $1.25 | 100% more |
| GPT 5 Mini | GPT | $0.25 | $2.00 | 150% more |
| Gemini 3.1 Flash-Lite | Gemini | $0.25 | $1.50 | 150% more |
| Gemini 3.5 Flash-Lite | Gemini | $0.30 | $2.50 | 200% more |
| Gemini 2.5 Flash | Gemini | $0.30 | $2.50 | 200% more |
| GPT 4.1 Mini | GPT | $0.40 | $1.60 | 300% more |
| GPT 3.5 Turbo | GPT | $0.50 | $1.50 | 400% more |
| GPT 3.5 Turbo (0125) | GPT | $0.50 | $1.50 | 400% more |
| Gemini 3 Flash | Gemini | $0.50 | $3.00 | 400% more |
| GPT 5.4 Mini | GPT | $0.75 | $4.50 | 650% more |
| Gemini 3.6 Flash | Gemini | $0.75 | $3.75 | 650% more |
| Gemini 3.7 Flash | Gemini | $0.75 | $3.75 | 650% more |
| Gemini 3.8 Flash | Gemini | $0.75 | $3.75 | 650% more |
| Gemini Robotics ER 2 | Gemini | $1.00 | $5.00 | 900% more |
| Grok Build 0.1 | Grok | $1.00 | $2.00 | 900% more |
| o3 Mini | GPT | $1.10 | $4.40 | 1000% more |
| o4 Mini | GPT | $1.10 | $4.40 | 1000% more |
| Gemini 2.5 Computer Use | Gemini | $1.25 | $10.00 | 1150% more |
| Gemini 3.5 Flash | Gemini | $1.50 | $9.00 | 1400% more |
| Gemini Omni 1.1 Flash | Gemini | $1.50 | $9.00 | 1400% more |
| Gemini Omni Flash | Gemini | $1.50 | $9.00 | 1400% more |
Fast / Budget / $1.00 in / $5.00 out
Mid-tier / $2.00 in / $10.00 out
Mid-tier / $2.00 in / $10.00 out
Mid-tier / $3.00 in / $15.00 out
Mid-tier / $3.00 in / $15.00 out
Flagship / $4.00 in / $20.00 out
Flagship / $5.00 in / $25.00 out
Flagship / $5.00 in / $25.00 out
Flagship / $5.00 in / $25.00 out
Flagship / $5.00 in / $25.00 out
Flagship / $5.00 in / $25.00 out
Flagship / $10.00 in / $50.00 out
Flagship / $10.00 in / $50.00 out
Flagship / $10.00 in / $50.00 out
Flagship / $10.00 in / $50.00 out
Input launched
$0.10/MTok at launch
See exactly how much you spend on Claude Haiku 5.5 and where you can save. Two-line wrapper install, no API keys shared.