Claude Haiku 5.5
nano-gpt/anthropic/claude-haiku-5.5 · family claude-haiku · in: text, image, pdf → out: text · price provider-declared (via models.dev). Capabilities: tools reasoning text image pdf.
$0.20
Blended $/1M (3:1)
$0.1
Input $/1M
$0.5
Output $/1M
$0.60
1M in + 1M out
$0.01 −90%
Cache read $/1M
#1720 of 7,964
Cheapest rank
- Provider
- NanoGPT (
nano-gpt) - Kind
- text (outputs text)
- Context
- 1,000,000 tokens
- Max output
- 128,000 tokens
- Capabilities
- tools reasoning text image pdf
Same model, other providers
“Claude Haiku 5.5” is offered by 14 providers — cheapest-effective first. This one (NanoGPT) is the cheapest.
| Provider | Input | Output | Blended | Context |
|---|---|---|---|---|
| NanoGPT (this) | $0.1 | $0.5 | $0.20 | 1M |
| Anthropic | $0.1 | $0.5 | $0.20 | 1M |
| Kilo Gateway | $0.1 | $0.5 | $0.20 | 1M |
| OpenRouter | $0.1 | $0.5 | $0.20 | 1M |
| Azure | $0.1 | $0.5 | $0.20 | 1M |
| Azure Cognitive Services | $0.1 | $0.5 | $0.20 | 1M |
| Vercel AI Gateway | $0.1 | $0.5 | $0.20 | 1M |
| Vertex (Anthropic) | $0.1 | $0.5 | $0.20 | 1M |
| Merge Gateway | $0.1 | $0.5 | $0.20 | 1M |
| OpenCode Go | $0.1 | $0.5 | $0.20 | 1M |
| OpenCode Zen | $0.1 | $0.5 | $0.20 | 1M |
| Amazon Bedrock | $0.1 | $0.5 | $0.20 | 1M |
| DevPass (LLM Gateway) | $0.1 | $0.5 | $0.20 | 1M |
Call it
jishie indexes & prices models; it does not proxy inference.
Most providers are OpenAI-compatible — point base_url at NanoGPT and pass this model id:
curl $BASE_URL/v1/chat/completions \
-H "Authorization: Bearer $API_KEY" -H "Content-Type: application/json" \
-d '{"model":"anthropic/claude-haiku-5.5","messages":[{"role":"user","content":"hello"}]}'
Route programmatically with MCP find_model / get_model, or fetch this record free (no wallet):